Papers by Xie Xie

Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time Scaling (2026.findings-acl)

Challenge:	Continual pre-training is the paradigm where pre-trained language models acquire fresh knowledge and gradually get upgraded.
Approach:	They propose to use adapted weights to recycle old PLMs for continual pre-training . they propose to combine initialization and distillation methods to achieve better performance .
Outcome:	The proposed method improves the convergence and performance of the upgraded PLM.

Copied to clipboard

Kai Zhang, Jiayi Liao, Chengpeng Li, Ziyuan Xie, Sihang Li, Xiang Wang

Agentic Knowledgeable Self-awareness (2025.acl-long)

Challenge:	Existing methods for testing time scales treat reasoning traces or tokens equally, ignoring substantial variations in trajectory quality and localized logical failures.
Approach:	They propose a chronological reasoning scorer that models each trajectory as a time series.
Outcome:	The proposed method achieves relative improvements of 34.21% over Pass@128 and 22.70% over Maj@135 on HMMT25, highlighting its effectiveness.

Copied to clipboard

Shuofei Qiao, Zhisong Qiu, Baochang Ren, Xiaobin Wang, Xiangyuan Ru, Ningyu Zhang, Xiang Chen, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

Challenge:	Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks.
Approach:	They propose a data-centric approach that applies agents with knowledgeable self-awareness like humans to a heuristic situation judgement criterion to mark special tokens on their self-explored trajectories for collecting training data.
Outcome:	The proposed paradigm outperforms baseline models on various tasks with minimal external knowledge.

Discovering Better Model Architectures for Medical Query Understanding (2021.naacl-industry)

Copied to clipboard

Wei Zhu, Yuan Ni, Xiaoling Wang, Guotong Xie

Challenge:	Neural architecture search (NAS) has attracted intense attention in computer vision and NLP.
Approach:	They propose to use neural architecture search to optimize model architectures for medical questions . they propose to modify the ENAS method to accelerate and stabilize the search results .
Outcome:	The proposed approach outperforms baseline models on two medical questions . it is compared with other NAS methods and shows that it provides the best results .

Can Pre-trained Language Models Interpret Similes as Smart as Human? (2022.acl-long)

Copied to clipboard

Qianyu He, Sijie Cheng, Zhixu Li, Rui Xie, Yanghua Xiao

Effective and Efficient Query-aware Snippet Extraction for Web Search (2022.emnlp-main)

Challenge:	Simile interpretation is a crucial task in natural language processing.
Approach:	They propose a task to let PLMs infer the shared properties of similes by probing textual corpora and human-designed questions.
Outcome:	The proposed task outperforms pre-trained language models on simile interpretation tasks while still underperforming humans.

Copied to clipboard

Jingwei Yi, Fangzhao Wu, Chuhan Wu, Xiaolong Huang, Binxing Jiao, Guangzhong Sun, Xing Xie

CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds (2025.naacl-long)

Challenge:	Existing methods to extract webpage snippets ignore contextual information of webpages, which may be sub-optimal.
Approach:	They propose a query-aware webpage snippet extraction method called DeepQSE that captures contextual information of webpages.
Outcome:	The proposed method can significantly improve the performance of DeepQSE without affecting its performance.

Copied to clipboard

Lei Wang, Jianxun Lian, Yi Huang, Yanqi Dai, Haoxuan Li, Xu Chen, Xing Xie, Ji-Rong Wen

Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training (2024.lrec-main)

Challenge:	Evaluating role-playing capabilities in large language models is challenging due to complex dynamics involved in role-playering.
Approach:	They propose a simulation sandbox that generates situational fine-grained character behavior trajectories to enhance LLM performance.
Outcome:	The proposed model generates situational fine-grained character behavior trajectories to enhance performance.

Copied to clipboard

Longhui Zhang, Dingkun Long, Meishan Zhang, Yanzhao Zhang, Pengjun Xie, Min Zhang

Exploring Question-Specific Rewards for Generating Deep Questions (2020.coling-main)

Challenge:	Pretrained language models (PLMs) have been successful in addressing word boundaries in Chinese sequence labeling tasks, but they rarely consider boundary information explicitly.
Approach:	They propose a method to integrate unsupervised boundary information into Chinese BERT's pre-training objectives and a supervised boundary-aware PLM.
Outcome:	The proposed model outperforms the vanilla version on Chinese sequence labeling tasks and in broader Chinese natural language understanding tasks.

Copied to clipboard

Yuxi Xie, Liangming Pan, Dongzhe Wang, Min-Yen Kan, Yansong Feng

Guiding Neural Machine Translation with Semantic Kernels (2022.findings-emnlp)

Challenge:	Recent question generation approaches use the sequence-to-sequence framework to optimize the log likelihood of ground-truth questions using teacher forcing.
Approach:	They propose to optimize for QG-specific objectives via reinforcement learning to improve question quality.
Outcome:	The proposed model improves the fluency, relevance, and answerability of generated questions.

Copied to clipboard

Ping Guo, Yue Hu, Xiangpeng Wei, Yubing Ren, Yunpeng Li, Luxi Xing, Yuqiang Xie

MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation (2024.lrec-main)

Challenge:	Empirical studies show that our approach gains approximately an improvement of 1 BLEU score on most benchmarks over the Transformer baseline.
Approach:	They propose to extract several semantic kernels from a source sentence to capture global semantic information.
Outcome:	Empirical results show that the proposed approach improves 1 BLEU score on benchmarks . it is also 1.7 times faster than previous works on average at inference time .

Copied to clipboard

Jianhui Pang, Baosong Yang, Derek F. Wong, Dayiheng Liu, Xiangpeng Wei, Jun Xie, Lidia S. Chao

RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid? (2026.findings-acl)

Challenge:	Existing models for multi-domain translation tasks only use monolingual data, whereas bilingual data is indispensable for improving the models.
Approach:	They propose a modular strategy that facilitates the cooperation of monolingual and bilingual knowledge in translation tasks by avoiding catastrophic forgetting.
Outcome:	The proposed model exhibits superior generalization and robustness over the conventional approach.

Copied to clipboard

Yuyang Dai, Yan Lin, Zhuohan Xie, Yuxia Wang

LongDocFACTScore: Evaluating the Factuality of Long Document Abstractive Summarisation (2024.lrec-main)

Challenge:	General-purpose models tend to over-commit and guess, while most finance-specialized models fail to clearly identify missing premises.
Approach:	They propose a bilingual benchmark that removes premises from exam-style questions while keeping them linguistically plausible.
Outcome:	The proposed model overcommits and guesses while most finance-specialized models fail to clearly identify missing premises.

Copied to clipboard

Jennifer A. Bishop, Sophia Ananiadou, Qianqian Xie

Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Existing metrics for text summarisation have restrictive token limits, limiting their effectiveness.
Approach:	They propose a human-annotated data set for evaluating automatic factuality metrics . they propose 'longDocFACTScore' framework which can be extended to any length document .
Outcome:	The proposed framework outperforms state-of-the-art metrics in evaluating long document summarisation data sets.

Copied to clipboard

Pengchao Feng, Ziyang Ma, Wenxi Chen, Yao Li, Sheng Wang, Kai Yu, Xie Chen

LCR-RAG: Enhancing Logical Consistency in Retrieval-Augmented Generation via Neuro-symbolic Reinforcement Learning (2026.acl-long)

Challenge:	End-to-end speech-to speech (S2S) dialogue systems face key challenges in incorporating external knowledge into their models.
Approach:	They propose a framework that directly retrieves relevant textual knowledge from speech queries.
Outcome:	The proposed framework improves the performance of end-to-end speech-tospeech dialogue systems while achieving higher retrieval efficiency.

Copied to clipboard

Wenxiang Zheng, Guo Tang, Shixin Jiang, Liangyu Huo, Xiyuan Zhang, Jian Xie, Ming Liu

Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning (2024.findings-acl)

Challenge:	Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge and improve factual accuracy.
Approach:	They propose a framework that integrates neuro-symbolic verification with reinforcement learning to optimize logical consistency.
Outcome:	The proposed framework outperforms strong RAG baselines on hotpotQA, ASQA, and TriviaQA.

Copied to clipboard

Zhouhang Xie, Bodhisattwa Prasad Majumder, Mengjie Zhao, Yoshinori Maeda, Keiichi Yamada, Hiromi Wakaki, Julian McAuley

Automatic Model Selection with Large Language Models for Reasoning (2023.findings-emnlp)

Challenge:	Motivational Interviewing (MI) requires a system that can infer how to motivate users to adopt positive lifestyle changes.
Approach:	They propose a framework that can learn and apply conversation strategies from expert demonstrations by using natural language inductive rules.
Outcome:	The proposed framework outperforms in-context demonstrations that are over 50 times longer and can learn natural language strategies from demonstrations.

Copied to clipboard

James Zhao, Yuxi Xie, Kenji Kawaguchi, Junxian He, Michael Xie

MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance (2024.emnlp-main)

Challenge:	Chain-of-Thought and Program-Aided Language Models offer different strengths and weaknesses.
Approach:	They propose a model selection method that uses a large language model to select between two different reasoning methods.
Outcome:	The proposed method shows significant performance improvements across eight reasoning datasets with Codex, ChatGPT, and GPT-4.

Copied to clipboard

Renjie Pi, Tianyang Han, Jianshu Zhang, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang

Fantastic Expressions and Where to Find Them: Chinese Simile Generation with Multiple Constraints (2023.acl-long)

Challenge:	MLLMs are deployed on limited image-text pairs, which makes them more vulnerable to catastrophic forgetting of their original abilities during safety fine-tuning.
Approach:	They propose a plug-and-play strategy that detects harmful visual inputs and transforms harmful ones into harmless ones.
Outcome:	The proposed approach mitigates the risks posed by malicious visual inputs without compromising the original performance of MLLMs.

Copied to clipboard

Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang, Xiangpeng Wei, Zhengyuan Liu, Jun Xie

TwiUSD: A Benchmark Dataset and Structure-Aware LLM Framework for User Stance Detection (2026.acl-long)

Challenge:	Existing attempts to generate similes as context-free tasks are not suitable for simile generation . however, simile generated under such settings might be undesirable, we argue .
Approach:	They propose a model to generate a simile with multiple simile elements . they propose to use a vehicle retrieval module to obtain the explicable comparison .
Outcome:	The proposed model can generate a simile with multiple simile elements, e.g., context and vehicle.

Copied to clipboard

Fuqiang Niu, Zini Chen, Zhiyu Xie, Hu Huang, Qing Liao, Qianlong Wang, Genan Dai, Bowen Zhang

Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers (2026.acl-long)

Challenge:	Existing benchmarks for political user-level stance detection rely on noisy heuristics or distant supervision.
Approach:	They propose a large-scale, expert-annotated benchmark for political user-level stance detection with explicit social network structure that integrates user content and followee signals.
Outcome:	The proposed framework outperforms baselines in terms of quality and reliability.

Copied to clipboard

Songhao Wu, Ang Lv, Ruobing Xie, Samm Sun, Di Wang, Rui Yan, Yankai Lin

Generative-to-Discriminative Test-Time Adaptation via Manifold-Aware Diffusion and Bayesian Distillation (2026.findings-acl)

Challenge:	Mixture-of-Experts (MoE) models rely on an external router to assign tokens to experts, resulting in suboptimal performance.
Approach:	They propose an MoE variant that performs "expert-autonomous routing" by pre-designating a fraction of neurons within each expert as "routing neurons" they pre-train UoE models with up to 3B parameters and show they outperform traditional MoEs with matched efficiency.
Outcome:	The proposed model outperforms existing models with 3B parameters and provides valuable insights into expert-autonomous selection and the broader routing mechanisms of MoE models.

Copied to clipboard

Boyun Zhang, Zequn Xie, Fangming Feng, Zihan Zhang, Yongbo He, Chuxin Wang, Sihang Cai, Tao Jin, Qifei Zhang

Addressing Healthcare-related Racial and LGBTQ+ Biases in Pretrained Language Models (2024.findings-naacl)

Challenge:	Existing discriminative approaches suffer from "confident but wrong" failure mode, blindly adapting to OOD noise leading to error accumulation.
Approach:	They propose a TTA framework that harmonizes the robustness of generative diffusion models with the efficiency of discriminative regression networks via Bayesian Diffusion Distillation (BDD).
Outcome:	The proposed framework reduces MAE from 0.6872 to 0.5673 and boosts binary accuracy by 5.81 percentage points (reaching 57.33%) it also reduces the MAE of the MOSI to SIMS shift and achieves an 11.18-point gain over the baseline.

Copied to clipboard

Sean Xie, Saeed Hassanpour, Soroush Vosoughi

Context-Interactive Pre-Training for Document Machine Translation (2021.naacl-main)

Challenge:	Pretrained language models (PLMs) propagate social stigmas and stereotypes, a critical concern given their widespread use.
Approach:	They adapt two intrinsic bias benchmarks to quantify racial and LGBTQ+ biases in prevalent PLMs and empirically evaluate the effectiveness of various debiasing methods in mitigating these biase.
Outcome:	The proposed methods reduce biases without compromising performance in downstream tasks.

Copied to clipboard

Pengcheng Yang, Pei Zhang, Boxing Chen, Jun Xie, Weihua Luo

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage (2026.findings-acl)

Challenge:	Document machine translation typically suffers from a lack of document-level bilingual data.
Approach:	They propose a document machine translation model that incorporates contextual information into the training signals by capturing cross-sentence dependency within the target document and cross sentence translation to make better use of contextual information.
Outcome:	The proposed model outperforms baselines on three benchmark datasets and significantly outperformed previous approaches.

Copied to clipboard

Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie

Challenge:	Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency.
Approach:	They propose an algorithm that detects threshold where information loss exceeds information gain during sparse decoding to reduce token consumption by up to 90% and a marginal accuracy degradation of less than 2%.
Outcome:	The proposed algorithm reduces token consumption by 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks.

RotateCT: Knowledge Graph Embedding by Rotation and Coordinate Transformation in Complex Space (2022.coling-1)

Copied to clipboard

Yao Dong, Lei Wang, Ji Xiang, Xiaobo Guo, Yuqiang Xie

SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization (2025.findings-emnlp)

Challenge:	Existing knowledge graph embedding methods fail to model non-commutative composition patterns . Existing methods are limited to complex space, resulting in a large number of parameters.
Approach:	They propose a knowledge graph embedding method that transforms the coordinates of each entity and then represents each relation as a rotation from head entity to tail entity in complex space.
Outcome:	The proposed method outperforms state-of-the-art methods on link prediction and path query answering.

Copied to clipboard

Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie

Shortcuts Arising from Contrast: Towards Effective and Lightweight Clean-Label Attacks in Prompt-Based Learning (2024.emnlp-main)

Challenge:	a recent study shows that code retrievers exhibit a strong bias towards well-documented code .
Approach:	They propose a framework that augments textual information with semantic information to mask specific features while preserving code functionality.
Outcome:	The proposed framework enhances textual information and reduces bias by augmenting code or structural knowledge with semantic information.

Copied to clipboard

Xiaopeng Xie, Ming Yan, Xiwen Zhou, Chenlong Zhao, Suli Wang, Yong Zhang, Joey Zhou

Enhancing Factual Consistency in Text Summarization via Counterfactual Debiasing (2025.coling-main)

Challenge:	Prompt-based learning paradigms are vulnerable to backdoor attacks, requiring false activations and false data augmentation.
Approach:	They propose a method that uses triggers to create stronger shortcuts by leveraging activation values and data selection strategies to create the shortcuts.
Outcome:	The proposed method is based on the concept that a backdoor acts as a shortcut and can achieve high effectiveness and stealthiness at low poisoning rates.

Copied to clipboard

Zhenqing Ling, Yuexiang Xie, Chenhe Dong, Ying Shen

MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models? (2025.findings-acl)

Challenge:	Abstractive text summarization has produced fluent and informative outputs, but factual inconsistency is a challenge.
Approach:	They propose a framework that mitigates the causal effects of language bias and irrelevancy bias by counterfactual estimation.
Outcome:	The proposed framework outperforms baseline methods on two widely used summarization datasets.

Copied to clipboard

Xixian Yong, Jianxun Lian, Xiaoyuan Yi, Xiao Zhou, Xing Xie

SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval (2026.findings-acl)

Challenge:	Existing benchmarks for large language models lack information asymmetry with real-world situations.
Approach:	They propose a benchmark to evaluate the human-like motivational and behavioral reasoning ability of LLMs with detailed, realistic situations.
Outcome:	The proposed benchmark compared LLMs with real-world scenarios on seven model families and found that the most advanced models struggle with understanding "love & belonging" needs.

Copied to clipboard

Xin Xie, Dongyun Xue, Wuguannan Yao, Mingxiao Feng, Wengang Zhou, Xiang Qi, Houqiang Li, Peng Zhang

FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining (2026.acl-long)

Challenge:	a new framework casts LLM planning as non-parametric retrieval, but high latency of inference-time search and supervised fine-tuning are limitations.
Approach:	They propose a framework that casts LLM planning as non-parametric retrieval . they leverage Monte Carlo Tree Search to explore the solution space .
Outcome:	Empirical results show that SGA-MCTS can match the performance of SOTA systems without task-specific fine-tuning.

Copied to clipboard

Xiquan Li, Xuenan Xu, Ziyang Ma, Wenxi Chen, Haolin He, Qiuqiang Kong, Xie Chen

PVTNL: Prompting Vision Transformers with Natural Language for Generalizable Person Re-identification (2025.findings-emnlp)

Challenge:	Existing audio-language models excel at clip-level understanding but struggle with frame-level tasks.
Approach:	They propose a novel training paradigm that advances both clip- and frame-level alignment in CLAP with heterogeneous data.
Outcome:	The proposed training paradigm improves both clip- and frame-level alignment in CLAP with heterogeneous data.

Copied to clipboard

null Wangning, Lei Xie, Sanglu Lu, Shiwei Gan

Improving Event Detection via Open-domain Trigger Knowledge (2020.acl-main)

Challenge:	Domain generalization person re-identification (DG-ReID) aims to train models on source domains and generalize to unseen target domains.
Approach:	They propose a framework to generalize person re-identification using a vision-language model . body-part cues are used to segment images into semantically coherent regions .
Outcome:	The proposed framework can generalize to unseen domains and generalize semantics to people . it leverages the pre-trained vision-language model BLIP to extract aligned visual and textual embeddings.

Copied to clipboard

Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, Jun Xie

Automatic, Meta and Human Evaluation for Multimodal Summarization with Multimodal Output (2024.naacl-long)

Challenge:	Existing methods for event detecting are prone to overfitting densely labeled trigger words due to the small scale of training data.
Approach:	They propose a novel Enrichment Knowledge Distillation model to leverage external open-domain trigger knowledge to reduce in-built biases to frequent trigger words in annotations.
Outcome:	The proposed model outperforms nine strong baselines and is especially effective for unseen/sparsely labeled trigger words.

Copied to clipboard

Haojie Zhuang, Wei Emma Zhang, Leon Xie, Weitong Chen, Jian Yang, Quan Sheng

Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference (2026.findings-acl)

Challenge:	Multimodal summarization with multimodal output (MSMO) has attracted increasing research interest . evaluation is an emerging yet underexplored research topic .
Approach:	They propose a framework that studies three research questions of MSMO evaluation . they propose an automatic evaluation metric and a meta-evaluation benchmark dataset .
Outcome:	The proposed evaluation metric and human-annotated meta-evaluation benchmark are used to assess the quality of evaluation metrics and show the framework is effective.

Copied to clipboard

Wenxuan Xie, Xuhong Wang

ToolSafety: A Comprehensive Dataset for Enhancing Safety in LLM-Based Agent Tool Invocations (2025.emnlp-main)

Challenge:	Existing solutions to integrate extensive, dynamic knowledge into Large Language Models (LLMs) are constrained by finite context windows, retriever noise, or the risk of catastrophic forgetting.
Approach:	They propose a dual-model architecture that explicitly decouples knowledge extraction from the reasoning process by compressing document chunks into implicit fact tokens conditioned on the query.
Outcome:	The proposed architecture significantly outperforms strong baselines among comparably sized models on long-context tasks while maintaining inference accuracy.

Copied to clipboard

Yuejin Xie, Youliang Yuan, Wenxuan Wang, Fan Mo, Jianmin Guo, Pinjia He

Challenge:	Current models exhibit notable vulnerabilities in maintaining safety during multi-step tool interactions and in indirect harm scenarios.
Approach:	They propose a safety fine-tuning dataset to fine- tune LLMs into assistants . they propose to use synthesized trajectories and realistic, context-aware sample generation .
Outcome:	The proposed model maintains safety in multi-step and indirect harm scenarios with little impact on helpfulness.

Privacy-Preserving News Recommendation Model Learning (2020.findings-emnlp)

Copied to clipboard

Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang, Xing Xie

Recurrent Attention Networks for Long-text Modeling (2023.findings-acl)

Challenge:	Existing news recommendation methods rely on centralized storage of user behavior data for model training, which may lead to privacy concerns and risks due to the privacy-sensitive nature of user behaviors.
Approach:	They propose a privacy-preserving method where user behavior data is locally stored on user devices to train accurate news recommendation models.
Outcome:	The proposed method can train accurate news recommendation models without centralized storage of user behavior data.

Copied to clipboard

Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, Qing Li

Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models (2025.emnlp-main)

Challenge:	Existing approaches to encoding long documents using self-attention have been limited by quadratic computational complexities and limited application in long text processing.
Approach:	They propose a long-document encoding model that allows the recurrent operation of self-attention.
Outcome:	The proposed model extracts global semantics in token-level and document-level representations, making it inherently compatible with both sequential and sequential tasks.

Copied to clipboard

Guangyu Xie, Yice Zhang, Jianzhu Bao, Qianlong Wang, Yang Sun, Bingbing Wang, Ruifeng Xu

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents (2026.acl-long)

Challenge:	Recent efforts to develop lightweight and practical sentiment analysis models are limited by manual instruction and large-scale user texts.
Approach:	They propose a framework for sentiment analysis that uses attribute-based instruction construction and difficulty-based data filtering to distill knowledge.
Outcome:	The proposed framework outperforms baseline methods in data efficiency and performance.

Copied to clipboard

Yi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan, Jiaqi Feng, Yaliang Li, Libing Wu

Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly (2025.emnlp-main)

Challenge:	Existing methods handle long-term memory (LTM) and short-term (STM) as separate components, relying on heuristics or auxiliary controllers, which limits adaptability and end-to-end optimization.
Approach:	They propose a framework that integrates LTM and STM management directly into the agent's policy and propose 'agentic memory' to train such unified behaviors.
Outcome:	The proposed framework outperforms strong memory-augmented baselines on five long-horizon benchmarks and achieves higher-quality long-term memory and more efficient context usage.

Copied to clipboard

Wenya Xie, Shaochen Zhong, Hoang Anh Duy Le, Zhaozhuo Xu, Jianwen Xie, Zirui Liu

Reveal and Release: Iterative LLM Unlearning with Self-generated Data (2025.findings-emnlp)

Challenge:	Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens.
Approach:	They propose a lightweight, turnkey component for Large Reasoning Models that is minimally invasive to its reasoning trajectory.
Outcome:	The proposed component is lightweight and low overhead, and lacks semantic value.

Copied to clipboard

Linxi Xie, Xin Teng, Shichang Ke, Hongyi Wen, Shenji Wan

Challenge:	Existing approaches to unlearning large language models assume full access to the forget dataset, overlooking two key challenges: (1) Forget data is often privacy-sensitive, rare, or legally regulated, making it expensive or impractical to obtain (2) The distribution of available forget data may not align with how that information is represented within the model.
Approach:	They propose a “Reveal-and-Release” method to unlearn with self-generated data, prompting the model to reveal what it knows using optimized instructions.
Outcome:	The proposed method removes the influence of undesirable data from the model.

Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Kepu Zhang, Guofu Xie, Weijie Yu, Mingyue Xu, Xu Tang, Yaxin Li, Jun Xu

UniEDU: Toward Unified and Efficient Large Multimodal Models for Educational Tasks (2025.emnlp-industry)

Challenge:	Existing legal mathematical reasoning models lack structured numerical reasoning . existing models perform poorly on LexNum, while LexPam improves both mathematical accuracy and legal coherence.
Approach:	They propose a legal mathematical reasoning benchmark LexNum and LexPam to address this problem . LexPam is a two-stage reinforcement learning framework for efficient legal reasoning training.
Outcome:	The proposed framework improves mathematical accuracy and legal coherence . it also improves legal cohesion and generalizes effectively across tasks and domains.

Copied to clipboard

Zhendong Chu, Jian Xie, Shen Wang, Zichao Wang, Qingsong Wen

GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning (2021.emnlp-main)

Challenge:	Existing research has focused on plain text, while real-world K-12 scenarios often involve multimodal data.
Approach:	They propose a unified language and vision assistant called UniEDU for educational applications . it excels across multiple educational tasks while maintaining strong generalization capabilities . authors propose to use UniEDu for industry-scale deployment .
Outcome:	The proposed model excels across multiple educational tasks while maintaining strong generalization capabilities.

Copied to clipboard

Wei Zhu, Xiaoling Wang, Yuan Ni, Guotong Xie

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization (2026.acl-long)

Challenge:	Existing approaches to improve the early exiting of natural language processing (NLP) are notoriously gigantic and slow in both training and inference.
Approach:	They propose a framework for improving the early exiting of BERT by asking each exit to distill knowledge from each other.
Outcome:	The proposed framework outperforms the state-of-the-art (SOTA) BERT early exiting methods on the GLUE benchmark.

Copied to clipboard

Wenxi Chen, Ruiqi Yan, Yushen Chen, Zhikang Niu, Ziyang Ma, Xiquan Li, Yuzhe Liang, null Wenhanlin, Shunshun Yin, Ming Tao, Xinsheng Wang, Xie Chen

RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation (2025.findings-acl)

Challenge:	Existing speech codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks.
Approach:	They propose a neural speech codec with semantic-acoustic dual-stream quantization that disentangles semantic and acousian modeling into two dedicated streams.
Outcome:	The proposed codec outperforms state-of-the-art speech tokenizers in auto-propagating text-to-speech models.

Copied to clipboard

Zhentao Xie, Chengcheng Han, Jinxin Shi, Wenjun Cui, Xin Zhao, Xingjiao Wu, Jiabao Zhao

ACENet: Attention Guided Commonsense Reasoning on Hybrid Knowledge Graph (2022.emnlp-main)

Challenge:	Multi-agent systems based on large language models are limited by high computational overhead, information loss, and robustness.
Approach:	They propose a Residual Mixture-of-Agents (RMoA) that integrates residual connections to optimize efficiency and reliability.
Outcome:	The proposed model achieves state-of-the-art performance on benchmarks of alignment, mathematical reasoning, code generation, and multitasking understanding, while significantly reducing computational overhead.

Copied to clipboard

Chuzhan Hao, Minghui Xie, Peng Zhang

Named Entity Recognition via Noise Aware Training Mechanism with Data Filter (2021.findings-acl)

Challenge:	Existing approaches estimate plausibility of candidate choices separately based on their respective KGs, without considering the interference among different choices.
Approach:	They propose an Attention guided Commonsense rEasoning Network to integrate hybrid knowledge into the neural network.
Outcome:	The proposed model outperforms existing methods on CommonsenseQA and OpenbookQA datasets and shows significant performance gains.

Copied to clipboard

Xiusheng Huang, Yubo Chen, Shun Wu, Jun Zhao, Yuantao Xie, Weijian Sun

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization (2024.findings-emnlp)

Challenge:	Existing methods for named entity recognition (NER) do not distinguish noisy from hard samples.
Approach:	They propose a noise-aware-with-filter method to help model identify noisy samples . they propose 'incomplete trust' loss function which boosts L CRF with a robust term .
Outcome:	The proposed method outperforms the existing methods on six real-world Chinese and English NER datasets.

Copied to clipboard

Yuxi Xie, Guanzhen Li, Xiao Xu, Min-Yen Kan

SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction (2022.findings-emnlp)

Challenge:	Existing large vision-language models suffer from hallucination due to over-reliance on the Large Language Model (LLM) backbone.
Approach:	They propose a method to improve visual context learning by using a large-scale preference learning algorithm to improve hallucination.
Outcome:	The proposed method improves on human-annotated hallucination datasets.

Copied to clipboard

Miao Peng, Ben Liu, Qianqian Xie, Wenjie Xu, Hua Wang, Min Peng

Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy (2025.coling-main)

Challenge:	Existing methods for linking knowledge graphs lack contextual information in entity neighborhoods, which leads to false prediction results.
Approach:	They propose a Schema-augmented Multi-level contrastive LEarning framework to conduct knowledge graph link prediction using a knowledge graph schema.
Outcome:	The proposed framework is based on a knowledge graph schema and is compared against state-of-the-art datasets.

Copied to clipboard

Min Zeng, Caiquan Liu, Shiqi Zhang, Li Xie, Chen Sang, Xiaoxin Chen

Defending against Indirect Prompt Injection by Instruction Detection (2025.findings-emnlp)

Challenge:	Existing methods for text classification based on large language models are difficult to apply directly to solve.
Approach:	They propose a data quality enhancement method to improve LLMs' performance in classification tasks by using a greedy algorithm to select data and then performing fine-tuning.
Outcome:	The proposed method improves the performance of large language models in text classification tasks and significantly improves training efficiency, saving nearly half of the training time.

Copied to clipboard

Tongyu Wen, Chenglong Wang, Xiyuan Yang, Haoyu Tang, Yueqi Xie, Lingjuan Lyu, Zhicheng Dou, Fangzhao Wu

Exploring Key Point Analysis with Pairwise Generation and Graph Partitioning (2024.naacl-long)

Challenge:	Indirect Prompt Injection attacks can be exploited by LLMs that are embedded with external data.
Approach:	They propose a detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.
Outcome:	The proposed approach reduces the success rate of attacks to 0.03% on the BIPIA benchmark.

Copied to clipboard

Xiao Li, Yong Jiang, Shen Huang, Pengjun Xie, Gong Cheng, Fei Huang

RaTEScore: A Metric for Radiology Report Generation (2024.emnlp-main)

Challenge:	Existing methods for key point analysis rely on semantic similarity instead of measuring the existence of shared key points .
Approach:	They propose a key point analysis approach with pairwise generation and graph partitioning to summarize arguments into a concise set of key points.
Outcome:	The proposed model surpasses existing models on ArgKP and QAM datasets.

Copied to clipboard

Weike Zhao, Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, Weidi Xie

Multi-target Backdoor Attacks for Code Pre-trained Models (2023.acl-long)

Challenge:	Existing metrics to evaluate the quality of medical reports are limited due to the complexity of clinical free-form texts.
Approach:	They propose a new metric to assess the quality of medical reports generated by AI models.
Outcome:	The proposed metric is based on a medical NER dataset and trained on NER models . it aligns more closely with human preference than existing metrics, the authors show .

Copied to clipboard

Yanzhou Li, Shangqing Liu, Kangjie Chen, Xiaofei Xie, Tianwei Zhang, Yang Liu

A Dual Contrastive Learning Framework for Enhanced Multimodal Conversational Emotion Recognition (2025.coling-main)

Challenge:	Existing work for backdoor attacks on neural code models insert triggers into task-specific data for code-related downstream tasks, limiting the scope of attacks.
Approach:	They propose task-agnostic backdoor attacks for code pre-trained models . they use two learning strategies to implant backdoors into code understanding and generation models - Poisoned Seq2Seq learning and token representation learning .
Outcome:	The proposed model is pre-trained with two learning strategies to support the multi-target attack of downstream code understanding and generation tasks.

Copied to clipboard

Yunhe Xie, Chengjie Sun, Ziyi Cao, Bingquan Liu, Zhenzhou Ji, Yuanchao Liu, Lili Shan

MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows (2026.acl-long)

Challenge:	Existing methods struggle to capture emotion shifts due to label replication and fail to preserve positive independent modality contributions during fusion.
Approach:	They propose a Dual Contrastive Learning Framework that enhances existing MERC models without additional data.
Outcome:	The proposed framework outperforms existing models on two MERC benchmark datasets and shows that it reduces label dependence and enhances emotion-sensitive independent modality features.

Copied to clipboard

Xiquan Li, Junxi Liu, Yuzhe Liang, Zhikang Niu, Wenxi Chen, Xie Chen

An End-to-End Contrastive Self-Supervised Learning Framework for Language Understanding (2022.tacl-1)

Challenge:	Recent advances in Text-to-Audio Generation (TTA) systems suffer from slow inference speed, authors report . authors demonstrate that MeanAudia achieves state-of-the-art performance in single-step audio generation .
Approach:	They propose a text-to-audio generator capable of rendering realistic sound with only one function evaluation.
Outcome:	The proposed system achieves state-of-the-art performance in single-step audio generation.

Copied to clipboard

Hongchao Fang, Pengtao Xie

IDP Accelerator: Agentic Document Intelligence from Extraction to Compliance Validation (2026.acl-demo)

Challenge:	Existing approaches to learning data representations using contrastive learning perform data augmentation and contrastive training separately.
Approach:	They propose a framework that performs data augmentation and contrastive learning end-to-end . they propose to combine data augmented with text encoders to optimize for contrastive training .
Outcome:	Experiments on GLUE and Gururangan datasets show the proposed framework is effective in NLP.

Copied to clipboard

Md Mofijul Islam, Md Sirajus Salekin, Joe King, Priyashree Roy, Vamsi Thilak Gudi, Spencer Romo, Akhil Nooney, Bob Strahan, Boyi Xie, Diego A. Socolinsky

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning (2026.acl-long)

Challenge:	Large Language Models (LLMs) are inadequate for extracting structured insights from unstructured documents.
Approach:	They propose a framework enabling agentic AI for end-to-end document intelligence with four key components: DocSplit, configurable Extraction Module, and Rule Validation Module.
Outcome:	The proposed framework achieves 98% classification accuracy, 80% reduced processing latency, and 77% lower operational costs over legacy baselines.

Copied to clipboard

Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu

Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning (2022.findings-emnlp)

Challenge:	Open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches.
Approach:	They propose a framework that compresses web agent trajectories via graph-based pruning.
Outcome:	The proposed framework reduces tool-call rounds by 20% while improving accuracy and efficiency while maintaining the same level of performance as existing models.

Copied to clipboard

Shuo Xie, Jiahao Qiu, Ankita Pasad, Li Du, Qing Qu, Hongyuan Mei

mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval (2024.emnlp-industry)

Challenge:	Existing approaches to transfer a pretrained language model include fine-tuning all the parameters in the language model and adapting all its subsets.
Approach:	They propose to select layers based on the variability of their hidden states given a task-specific corpus.
Outcome:	The proposed model reduces the computational cost of transfer learning methods without sacrificing performance.

Copied to clipboard

Xin Zhang, Yanzhao Zhang, Dingkun Long, Wen Xie, Ziqi Dai, Jialong Tang, Huan Lin, Baosong Yang, Pengjun Xie, Fei Huang, Meishan Zhang, Wenjie Li, Min Zhang

Tailoring Vaccine Messaging with Common-Ground Opinions (2024.findings-naacl)

Challenge:	Existing models for text retrieval are based on a multi-stage process that involves retrieving documents from a large corpus.
Approach:	They propose to build a multilingual text representation model and a cross-encoder reranker from scratch for text retrieval.
Outcome:	The proposed models outperform the state-of-the-art models on long-context retrieval benchmarks.

Copied to clipboard

Rickard Stureborg, Sanxing Chen, Roy Xie, Aayushi Patel, Christopher Li, Chloe Zhu, Tingnan Hu, Jun Yang, Bhuwan Dhingra

Challenge:	Vaccine interventions aim to answer concerns expressed about vaccination.
Approach:	They propose a dataset to evaluate how well responses are tailored to a common-ground opinion . they find that GPT-4-Turbo performs significantly better than others .
Outcome:	The proposed dataset outperforms fine tuned LLMs on the task of tailoring vaccine responses to common-ground opinions.

F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (2025.acl-long)

Copied to clipboard

Yushen Chen, Zhikang Niu, Ziyang Ma, Keqi Deng, Chunhui Wang, JianZhao JianZhao, Kai Yu, Xie Chen

Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey (2025.emnlp-main)

Challenge:	Recent research in Text-to-Speech (TTS) has experienced great advancement . current models can synthesize speech for any given text and mimic the speaker of audio prompt.
Approach:	They propose a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT) without complex designs such as duration model, text encoder, and phoneme alignment, the text input is simply padded with filler tokens to the same length as input speech, and then denoising is performed for speech generation.
Outcome:	The proposed system achieves an inference RTF of 0.15, which is greatly improved compared to state-of-the-art diffusion-based models.

Copied to clipboard

Tianxin Xie, Yan Rong, Pengfei Zhang, Wenwu Wang, Li Liu

CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models (2024.findings-acl)

Challenge:	Text-to-speech (TTS) has advanced from generating natural-sounding speech to enabling fine-grained control over speech attributes.
Approach:	They provide a review of controllable TTS methods from traditional control techniques to emerging approaches using natural language prompts.
Outcome:	The proposed methods are based on models, strategies, and features, and summarize challenges, datasets, and evaluations.

Copied to clipboard

Qian Lou, Xin Liang, Jiaqi Xue, Yancheng Zhang, Rui Xie, Mengxin Zheng

On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)

Challenge:	Existing certified robustness methods for certifying input-specific text perturbations have shown promise in certifyling UTPs, but masking only adversarial words can eliminate the attack.
Approach:	They propose a method to certify a language model’s robustness against UTPs by using random smoothing.
Outcome:	The proposed method achieves high certified accuracy under extensive masking and achieves state-of-the-art results in multiple settings.

Copied to clipboard

Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning (2024.findings-acl)

Challenge:	Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited.
Approach:	They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO).
Outcome:	The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness.

Copied to clipboard

Xiaohu Du, Ming Wen, Jiahao Zhu, Zifan Xie, Bin Ji, Huijun Liu, Xuanhua Shi, Hai Jin

AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents (2025.findings-acl)

Challenge:	Existing CodePre-trained models struggle to generalize due to superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities.
Approach:	They propose a framework that integrates multi-task learning with Large Language Models to effectively mine deep-seated vulnerability features.
Outcome:	The proposed framework surpasses seven state-of-the-art models in effectiveness, generalization, and robustness.

Copied to clipboard

Guhong Chen, Liyang Fan, Zihan Gong, Nan Xie, Zixuan Li, Ziqiang Liu, Chengming Li, Qiang Qu, Hamid Alinejad-Rokny, Shiwen Ni, Min Yang

Unified Demonstration Retriever for In-Context Learning (2023.acl-long)

Challenge:	Existing legal language models struggle with dynamic courtroom interactions, resulting in overfitting to standardized legal tasks.
Approach:	They propose a new adversarial evolutionary approach for agents that performs dynamic knowledge learning and evolution through structured adversarials in a simulated courtroom program.
Outcome:	The proposed approach outperforms existing LLM-based models in three critical dimensions: cognitive agility, professional knowledge, and logical rigor.

Copied to clipboard

Xiaonan Li, Kai Lv, Hang Yan, Tianyang Lin, Wei Zhu, Yuan Ni, Guotong Xie, Xiaoling Wang, Xipeng Qiu

Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning (2022.findings-emnlp)

Challenge:	In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction.
Approach:	They propose a single model to retrieve demonstrations for a wide range of tasks by combining training signals from various tasks into a unified list-wise ranking formulation by language model’s feedback.
Outcome:	The proposed model outperforms baselines on 30+ tasks across 13 task families and multiple data domains.

Copied to clipboard

Hongqiu Wu, Ruixue Ding, Hai Zhao, Boli Chen, Pengjun Xie, Fei Huang, Min Zhang

MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets (2024.naacl-long)

Challenge:	Empirical studies show that learning multiple training objectives in a single model makes the learned language representation barely converge to the desired optimum.
Approach:	They propose a meta-learning-based adaptive sampler which learns latent sampling pattern on arbitrary pre-training objectives.
Outcome:	Empirical studies show that learning multiple objectives in a single model makes it difficult to achieve the desired optimum.

Copied to clipboard

Hossein Aboutalebi, Hwanjun Song, Yusheng Xie, Arshit Gupta, Lijia Sun, Hang Su, Igor Shalyminov, Nikolaos Pappas, Siffi Singh, Saab Mansour

MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation (2024.acl-long)

Challenge:	Existing approaches to augment textual dialogues with retrieved images pose privacy, diversity, and quality constraints.
Approach:	They propose a framework to augment text-only dialogues with diverse and high-quality images by using a diffusion model and a feedback loop.
Outcome:	The proposed framework is comparable to or better than baselines, with significant improvements in human evaluation, especially against retrieval baselines where the image database is small.

Copied to clipboard

Xiaozhi Wang, Hao Peng, Yong Guan, Kaisheng Zeng, Jianhui Chen, Lei Hou, Xu Han, Yankai Lin, Zhiyuan Liu, Ruobing Xie, Jie Zhou, Juanzi Li

Pruning Pre-trained Language Models Without Fine-Tuning (2023.acl-long)

Challenge:	Existing datasets for event understanding have limited coverage due to complexity of tasks.
Approach:	They propose a dataset that augments MAVEN datasets with event argument annotations . they propose 98,591 events and 290,613 arguments obtained with laborious human annotation .
Outcome:	The proposed dataset is the first all-in-one dataset supporting event detection, event argument extraction, and event relation extraction.

Copied to clipboard

Ting Jiang, Deqing Wang, Fuzhen Zhuang, Ruobing Xie, Feng Xia

Structure Guided Retrieval-Augmented Generation for Factual Queries (2026.acl-long)

Challenge:	Existing methods to prune Pre-trained Language Models (PLMs) are overparameterized and require fine-tuning.
Approach:	They propose a pruning method that uses first-order pruning to prune PLMs while fine-tuning the remaining weights.
Outcome:	The proposed method outperforms first-order pruning and zero-order methods at sparsity levels.

Copied to clipboard

Miao Xie, Xiao Zhang, Yi Li, Chunli Lv

Pre-training Entity Relation Encoder with Intra-span and Inter-span Information (2020.emnlp-main)

Challenge:	Existing methods for RAG produce factually incorrect outputs, resulting in incorrect answers.
Approach:	They propose a novel problem that explicitly incorporates structural information into RAG for factual questions to satisfy all query conditions.
Outcome:	The proposed method significantly outperforms baselines on ERQA while maintaining reasonable computational overhead.

Copied to clipboard

Yijun Wang, Changzhi Sun, Yuanbin Wu, Junchi Yan, Peng Gao, Guotong Xie

Correctable-DST: Mitigating Historical Context Mismatch between Training and Inference for Improved Dialogue State Tracking (2022.emnlp-main)

Challenge:	Existing pre-trained models do not handle text spans and relation among text span pairs.
Approach:	They propose to integrate span-related information into pre-trained encoder for entity relation extraction task.
Outcome:	The proposed pre-training method outperforms distantly supervised pre-trained models on two entity relation extraction benchmark datasets.

Copied to clipboard

Hongyan Xie, Haoxiang Su, Shuangyong Song, Hao Huang, Bo Zou, Kun Deng, Jianghua Lin, Zhihui Zhang, Xiaodong He

ChartM3: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension (2025.findings-emnlp)

Challenge:	Existing dialogue state tracking approaches predict the dialogue state of a target turn sequentially based on the ground-truth previous dialogue state.
Approach:	They propose a method that predicts dialogue state sequentially based on previous dialogue state . they propose generating a previously “predicted” dialogue state using ground-truth previous dialogue states .
Outcome:	The proposed method achieves 67.51%, 68.24%, 70.30%, 71.38%, and 81.27% joint goal accuracy on MultiWOZ 2.0-2.4 datasets.

Copied to clipboard

Duo Xu, Hao Cheng, Xin Lin, Zhen Xie, Hao Henry Wang

DocLens: Multi-aspect Fine-grained Medical Text Evaluation (2024.acl-long)

Challenge:	Currently, research on complex chart understanding tasks is limited . a pipeline for visual reasoning datasets addresses these limitations .
Approach:	They propose a code-driven pipeline for generating visual reasoning datasets . pipeline integrates retrieval-augmented generation to retrieve professional chart templates .
Outcome:	The proposed pipeline enhances chart diversity and data quality through model-based evaluation.

Copied to clipboard

Yiqing Xie, Sheng Zhang, Hao Cheng, Pengfei Liu, Zelalem Gero, Cliff Wong, Tristan Naumann, Hoifung Poon, Carolyn Rose

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment (2026.acl-long)

Challenge:	Medical text generation systems are widely used to assist with administrative work and highlight salient information to support decision-making.
Approach:	They propose a set of metrics to evaluate completeness, conciseness, and attribution of medical text at a fine-grained level.
Outcome:	The proposed framework exhibits substantially higher agreement with medical experts than existing metrics.

Copied to clipboard

Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Roy Ka-Wei Lee

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Challenge:	Current alignment paradigms treat "human values" as a monolithic entity, ignoring the fact that many societies are a mosaic of diverse subgroups with distinct and sometimes conflicting values, preferences, and norms.
Approach:	They examine whether Large Language Models can emulate distinct cultural values of subgroups . they use a global value survey to examine the value landscape of a multicultural society .
Outcome:	The proposed model improves on unseen, out-of-distribution subgroups by 17.4% . the model widens the disparity between subgroup groups when measured by distance-aware metrics.

Copied to clipboard

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale (2025.findings-acl)

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

Copied to clipboard

Linghao Zhang, Junhao Wang, Shilin He, Chaoyun Zhang, Yu Kang, Bowen Li, Jiaheng Wen, Chengxing Xie, Maoquan Wang, Yufan Huang, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databases (2025.emnlp-main)

Challenge:	Existing studies highlight that dependency-related issues cause over 40% of observed runtime errors on the generated repository.
Approach:	They propose a large-scale benchmark and evaluation framework specifically designed to assess LLMs’ capability on dependency inference.
Outcome:	The proposed model achieves only a 48% execution pass rate on Python, indicating room for improvement.

Copied to clipboard

Mounica Maddela, Lingjue Xie, Daniel Preotiuc-Pietro, null Mausam

Unlocking LLMs’ Self-Improvement Capacity with Autonomous Learning for Domain Adaptation (2025.findings-acl)

Challenge:	Existing Text2SQL systems do not support SQL analysts in their primary work of performing complex analytics on specialized databases.
Approach:	They propose to decompose STARQA questions using SQL and Python to perform reasoning on specialized relational databases.
Outcome:	The proposed approach decomposes the task through a combination of SQL and Python, and achieves better performance on the more difficult questions.

Copied to clipboard

Ke Ji, Junying Chen, Anningzhe Gao, Wenya Xie, Xiang Wan, Benyou Wang

Inductive Topic Variational Graph Auto-Encoder for Text Classification (2021.naacl-main)

Challenge:	Existing models that use self-supervised and instruction fine-tuning can be trained using unlabeled corpora.
Approach:	They propose to use unlabeled target corpora to adapt large language models to new domains . they propose to employ self-supervised pre-training and instruction fine-tuning methods .
Outcome:	The proposed model can adapt to new domains using only a large amount of unlabeled target corpora.

Copied to clipboard

Qianqian Xie, Jimin Huang, Pan Du, Min Peng, Jian-Yun Nie

Emotion Classification by Jointly Learning to Lexiconize and Classify (2020.coling-main)

Challenge:	Existing methods for text classification do not assume explicit latent semantic structure of documents, making them less effective and difficult to interpret.
Approach:	They propose a model that integrates a topic model into variational graph-auto-encoder to capture hidden semantic information between documents and words.
Outcome:	The proposed model outperforms existing models on supervised and semi-supervised text classification and unsupervised representation learning.

Copied to clipboard

Deyu Zhou, Shuangzhi Wu, Qing Wang, Jun Xie, Zhaopeng Tu, Mu Li

Text Classification

Challenge:	Existing approaches to identify emotions in short text are limited and lack coverage and inaccuracies when applied to informal short text.
Approach:	They propose a novel emotional network to jointly learn sentence emotions and construct emotion lexicons which are dynamically adapted to a given context.
Outcome:	The proposed model outperforms several approaches proposed in previous studies and achieves new state-of-the-art on the benchmark Twitter dataset.

MATO: A Model-Agnostic Training Optimization for Aspect Sentiment Triplet Extraction (2025.naacl-long)

Copied to clipboard

Shaopeng Tang, Lin Li, Xiaohui Tao, Leqi Zhong, Qing Xie

A Group Fairness Lens for Large Language Models (2025.findings-emnlp)

Challenge:	Existing models with strong in-house performance may struggle to generalize to diverse expressions.
Approach:	They propose a model-agnostic t**raining method to improve ASTE model inference . they propose to compute the violation rate (VR) on each element of one triplet .
Outcome:	The proposed method can improve aspect sentiment triplet extraction models consistent with expected results facing triplet element diversity.

Copied to clipboard

Guanqun Bi, Yuqiang Xie, Lei Shen, Yanan Cao

Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search (2026.findings-acl)

Challenge:	Existing methods focusing on a few groups lack a comprehensive categorical perspective to evaluate LLMs’ potential biases and unfairness.
Approach:	They propose to evaluate LLM biases from a group fairness lens using a hierarchical schema characterizing diverse social groups.
Outcome:	The proposed method mitigates biases in LLMs from a group fairness lens and encapsulates target-attribute combinations across multiple dimensions.

Copied to clipboard

Zequn Xie, Guijin Luo, Chuxin Wang, Sihang Cai, Tao Jin, Zhou Zhao, Yixuan Tang

PodAgent: A Comprehensive Framework for Podcast Generation (2025.findings-acl)

Challenge:	Existing methods for person anomaly search fail to address the complexities of real-world security, authors say . Existing approaches fail to detect subtle semantic distinctions, authors argue .
Approach:	They propose a framework that decouples retrieval into two stages . structure-aware coarse retrieval and detective squad interaction are proposed .
Outcome:	The proposed framework achieves state-of-the-art performance by balancing efficiency and semantic reasoning.

Copied to clipboard

Yujia Xiao, Lei He, Haohan Guo, Feng-Long Xie, Tan Lee

Bridging Distance and Spectral Positional Encodings via Anchor-Based Diffusion Geometry Approximation (2026.acl-long)

Challenge:	Existing automatic audio generation methods struggle to generate podcast-like audio programs effectively.
Approach:	They propose a framework for creating podcast-like audio programs that generates informative topic-discussion content by designing a multi-agent collaboration system, builds a voice pool and uses LLM-enhanced speech synthesis to generate expressive conversational speech.
Outcome:	The proposed framework surpasses direct GPT-4 generation in topic-discussion dialogue content, and produces more expressive conversational speech.

Copied to clipboard

Yan Zimo, Zheng Xie, Runfan Duan, Chang Liu, Wumei Du

Reconstruction Attack on Instance Encoding for Language Understanding (2021.emnlp-main)

Challenge:	Molecular graph learning benefits from positional signals that capture local neighborhoods and global topology.
Approach:	They propose to use anchor-based distance encodings to approximate diffusion geometry.
Outcome:	The proposed model outperforms models without positional encodings on DrugBank with a shared GNP-based DDI backbone.

Copied to clipboard

Shangyu Xie, Yuan Hong

From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction (P18-1)

Challenge:	Existing private learning schemes which protect data privacy can be used to train models using instance encoding.
Approach:	They propose to recover the private training data and use it to break a private learning scheme TextHide.
Outcome:	The proposed attack would advance privacy-preserving machine learning in the context of natural language processing.

Copied to clipboard

Zihang Dai, Qizhe Xie, Eduard Hovy

Challenge:	equivalence between credit assignment problem and entropy regularized reinforcement learning is established . a wide range of successful sequence prediction algorithms have been developed .
Approach:	They propose to extend credit assignment in reward augmented maximum likelihood learning by credit assignment and entropy regularization.
Outcome:	The proposed algorithms outperform RAML and Actor-Critic on two benchmark datasets.

Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL (2025.coling-main)

Copied to clipboard

Geling Liu, Yunzhi Tan, Ruichao Zhong, Yuanzhen Xie, Lingchen Zhao, Qian Wang, Bo Hu, Zang Li

Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving (2021.findings-emnlp)

Challenge:	Existing text-to-SQL approaches have overlooked the critical aspect of system robustness.
Approach:	They propose a robust text-to-SQL solution that integrates with LLMs . their method achieves SOTA SQL execution accuracy levels of 82.1% and 58.9% .
Outcome:	The proposed solution achieves SOTA SQL execution accuracy levels of 82.1% and 58.9% on the general Spider and Bird benchmarks.

Copied to clipboard

Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang, Xing Xie

Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing (2026.acl-long)

Challenge:	Existing news recommendation methods rely on user behavior data to model user interests and user interests.
Approach:	They propose a unified news recommendation framework that uses user data locally stored in user clients to train models and serve users in a privacy-preserving way.
Outcome:	The proposed framework outperforms baseline methods and effectively protects user privacy.

Copied to clipboard

Tingyu Song, Yanzhao Zhang, Mingxin Li, Zhuoning Guo, Dingkun Long, Pengjun Xie, Siyue Zhang, Yilun Zhao, Shu Wu

Towards Rationality in Language and Multimodal Agents: A Survey (2025.naacl-long)

Challenge:	Composed Image Retrieval (CIR) is a complex task in multimodal understanding . current CIR benchmarks lack a robust evaluation pipeline and limited query categories .
Approach:	They construct a fine-grained CIR benchmark that allows for precise control over modification types and content.
Outcome:	The proposed benchmark covers 5,000 high-quality queries structured across five main categories and fifteen subcategories.

Copied to clipboard

Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Yuan Yuan, Zhuoqun Hao, Xinyi Bai, Weijie J Su, Camillo Jose Taylor, Tanwi Mallick

MUZO: Leveraging Multiple Queries and Momentum for Zeroth-Order Fine-Tuning of Large Language Models (2025.emnlp-main)

Challenge:	despite advances in language and multimodal agents, large language models lack rationality . despite their progress, large-scale models lack real-world grounding and feedback mechanisms .
Approach:	They propose to build more rational language and multimodal agents . they also examine what criteria define rationality in intelligent systems .
Outcome:	This paper assesses the state-of-the-art in language and multimodal agents . it also outlines open challenges and future research directions .

Copied to clipboard

Yuezhang Peng, Yuxin Liu, Fei Wen, Xie Chen

CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering (2025.emnlp-main)

Challenge:	Existing methods for fine-tuning large language models incur memory overhead due to the need for activation storage for back-propagation (BP).
Approach:	They propose a method that estimates gradients through finite differences without activation storage for back-propagation.
Outcome:	The proposed method demonstrates superior performance in fine-tuning various LLMs.

Copied to clipboard

Zongxi Li, Yang Li, Haoran Xie, S. Joe Qin

Self-supervised Regularization for Text Classification (2021.tacl-1)

Challenge:	Large language models (LLMs) generate unreliable responses due to their cognitive alignment of context and intent.
Approach:	They propose a benchmark to identify possible implicit assumptions in QA questions . they use retrieved Wikipedia fragments to identify interpretations for a given query .
Outcome:	The proposed benchmark identifies possible implicit assumptions and improves answer accuracy by 11.75% . retrieved Wikipedia fragments help identify possible interpretations for a given query .

Copied to clipboard

Meng Zhou, Zechen Li, Pengtao Xie

Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification (2024.lrec-main)

Challenge:	Text classification models are prone to overfitting when limited texts are available for training.
Approach:	They propose a data-dependent regularization approach based on self-supervised learning . they define auxiliary tasks on input data without using human-provided labels .
Outcome:	Experiments on 17 text classification datasets demonstrate the effectiveness of the proposed method.

Copied to clipboard

Zhipeng Xie, Yahe Li

Knowledge Graph-Guided Retrieval Augmented Generation (2025.naacl-long)

Challenge:	Existing methods for prompt-based finetuning are expensive and difficult to use.
Approach:	They propose a prompt-based method that uses a pretrained language model to discriminate between original and replacement tokens.
Outcome:	The proposed method outperforms state-of-the-art prompt-based few-shot methods on 10 widely-used text classification tasks.

Copied to clipboard

Xiangrong Zhu, Yuexiang Xie, Yi Liu, Yaliang Li, Wei Hu

MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation (2025.acl-long)

Challenge:	Existing studies on RAG focus on semantic retrieval of isolated relevant chunks, which ignore their intrinsic relationships.
Approach:	They propose a framework that utilizes knowledge graphs to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results.
Outcome:	Extensive experiments on the HotpotQA dataset and its variants demonstrate the advantages of KG2RAG compared to existing RAG-based approaches in terms of response quality and retrieval quality.

Copied to clipboard

Haochen Xue, Feilong Tang, Ming Hu, Yexin Liu, Qidong Huang, Yulong Li, Chengzhi Liu, Zhongxing Xu, Chong Zhang, Chun-Mei Feng, Yutong Xie, Imran Razzak, Zongyuan Ge, Jionglong Su, Junjun He, Yu Qiao

Towards Reliable Large Audio Language Model (2025.findings-acl)

Challenge:	Existing multimodal large language models lack the ability to memorize, recall, and reason in sustained interactions.
Approach:	They propose a multimodal real-world conversation benchmark for evaluating open-ended abilities of multimodal large language models.
Outcome:	The proposed benchmarks show that the models perform better in open-ended conversations.

Copied to clipboard

Ziyang Ma, Xiquan Li, Yakun Song, Wenxi Chen, Chenpeng Du, Jian Wu, Yuanzhe Chen, Zhuo Chen, Yuping Wang, Yuxuan Wang, Xie Chen

GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models (2025.findings-emnlp)

Challenge:	Recent advances in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound.
Approach:	They propose to use training-free and training-based methods to enhance LALM reliability to different extents.
Outcome:	The proposed methods improve the reliability of large audio language models to different extents.

Copied to clipboard

Min Zeng, Jingfei Sun, Xueyou Luo, Shiqi Zhang, Li Xie, Caiquan Liu, Xiaoxin Chen

Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (2024.findings-acl)

Challenge:	Reinforcement learning fine-tuning methods suffer from inefficient exploration and slow convergence . supervised fine- tuning methods have limited performance ceiling and less solid theoretical foundation .
Approach:	They propose a Guess-Think-Answer framework that combines supervised and supervised learning in a unified training paradigm.
Outcome:	The proposed framework outperforms both standalone SFT and RL training models on three text classification benchmarks.

Copied to clipboard

Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li

Each graph is a new language: Graph Learning with LLMs (2025.findings-acl)

Challenge:	In-context learning of large-language models has achieved remarkable success in the field of natural language processing . however, the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL.
Approach:	They propose a workflow paradigm method to enhance the attention and problem-solving scope of large-language models through decomposition.
Outcome:	The proposed method outperforms existing methods on three datasets and improves the upper limit of LLM-based approaches.

Copied to clipboard

Huachi Zhou, Jiahe Du, Chuang Zhou, Chang Yang, Yilin Xiao, Yuxuan Xie, Xiao Huang

Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration (2026.acl-demo)

Challenge:	Natural language is used to describe graphs, but graph descriptions become verbose and only relying on attribute embeddings limits LLM’s ability to capture adequate graph structural information.
Approach:	They propose a graph-defined language for large language model that translates the graph into a corpus instead of graph descriptions and pre-trains LLMs on this corpus to adequately understand the graph.
Outcome:	Experiments on five datasets show that the proposed framework outperforms description-based and embedding-based baselines by efficiently modeling different orders of neighbors.

Copied to clipboard

Yinghao Tang, Yupeng Xie, Yingchaojie Feng, Tingfeng Lan, Wei Chen

Challenge:	Recent LLM-based agents can automate content creation, but naively applying them yields uncontrollable and unverifiable outputs.
Approach:	They propose a human-agent collaborative system that generates interactive educational documents from a single topic input.
Outcome:	The proposed system generates documents comparable in quality to human-authored ones.

CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents (2025.findings-acl)

Copied to clipboard

Tianqi Xu, Linyao Chen, Dai-Jie Wu, Yanjun Chen, Zecheng Zhang, Xiang Yao, Zhiqiang Xie, Yongchao Chen, Shilong Liu, Bochen Qian, Anjie Yang, Zhaoxuan Jin, Jianbo Deng, Philip Torr, Bernard Ghanem, Guohao Li

Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience (2025.findings-acl)

Challenge:	Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexity of constructing tasks and evaluators.
Approach:	They propose a cross-environment agent benchmark framework that integrates graph-based evaluation and task generation methods.
Outcome:	The proposed framework supports multiple devices and can be easily extended to any environment with a Python interface.

Copied to clipboard

Jiawei Gu, Ziting Xian, Yuanzhen Xie, Ye Liu, Enjie Liu, Ruichao Zhong, Mochi Gao, Yunzhi Tan, Bo Hu, Zang Li

Reviews Meet Graphs: Enhancing User and Item Representations for Recommendation with Hierarchical Attentive Graph Neural Network (D19-1)

Challenge:	Large language models struggle to infer implicit relationships embedded in tabular formats . authors introduce a framework that builds experience memory representations and enhances generalization through contrastive In-Context Learning (ICL).
Approach:	They propose a framework that builds experience memory representations and enhances generalization through contrastive In-Context Learning to simulate human-like knowledge transfer.
Outcome:	Experiments on Text-to-SQL and TableQA show CoRE significantly improves performance . it achieves gains of 3.44% and 4.24%, with up to 17.2% on challenging tasks .

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Tao Qi, Suyu Ge, Yongfeng Huang, Xing Xie

Continuous Speech Tokenizer in Text To Speech (2025.findings-naacl)

Challenge:	Existing methods to learn user and item representations from review texts do not take into account the user-user and item-item relatedness of the user.
Approach:	They propose to use review content and user-item graphs to integrate them as different views.
Outcome:	The proposed approach can learn user and item representations from review content and user-item graphs.

Copied to clipboard

Yixing Li, Ruobing Xie, Xingwu Sun, Yu Cheng, Zhanhui Kang

InstructCoder: Instruction Tuning Large Language Models for Code Editing (2024.acl-srw)

Challenge:	Autoregressive modeling is a common method for processing language sequences and is effective in token prediction.
Approach:	They propose a text-to-speech model based on continuous speech tokens and a continuous tokenizer for speech compression.
Outcome:	The proposed model has better continuity and higher estimated Mean Opinion Scores (MoS) this is attributed to better information preservation rate across low and high frequencies in the frequency domain.

Copied to clipboard

Kaixin Li, Qisheng Hu, James Zhao, Hui Chen, Yuxi Xie, Tiedong Liu, Michael Shieh, Junxian He

DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling (2025.emnlp-main)

Challenge:	InstructCoder is the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing.
Approach:	They propose to use Large Language Models to edit code based on user instructions . they use a dataset to adapt LLMs to general-purpose code editing .
Outcome:	The proposed model can significantly improve code editing performance compared to proprietary models . the proposed model is based on a human-written execution-based benchmark .

Copied to clipboard

Hao Sun, Zile Qiao, Bo Wang, Guoxin Chen, Yingyan Hou, Yong Jiang, Pengjun Xie, Fei Huang, Yan Zhang

Few-shot Classification with Hypersphere Modeling of Prototypes (2023.findings-acl)

Challenge:	Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs).
Approach:	They propose a framework that decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding.
Outcome:	The proposed framework decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding.

Copied to clipboard

Ning Ding, Yulin Chen, Ganqu Cui, Xiaobin Wang, Haitao Zheng, Zhiyuan Liu, Pengjun Xie

Guiding Neural Story Generation with Reader Models (2022.findings-emnlp)

Challenge:	Existing methods for fewshot learning use embeddings in space, but they lack expressivity and are difficult to perform statistically.
Approach:	They propose a method where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere’s center and the radius.
Outcome:	The proposed method is much more expressive than embeddings and performs better than statistical modeling.

Copied to clipboard

Xiangyu Peng, Kaige Xie, Amal Alabdulkarim, Harshith Kayam, Samihan Dani, Mark Riedl

Automated Fine-Grained Mixture-of-Experts Quantization (2025.findings-acl)

Challenge:	Existing systems that generate narratives with neural language models require substantial knowledge engineering of logical constraints, limiting their generality.
Approach:	They propose a framework in which a reader model is used to reason about the storyshould progress.
Outcome:	The proposed model outperforms baseline models in plot plausibility and staying on topic.

Copied to clipboard

Zhanhao Xie, Yuexiao Ma, Xiawu Zheng, Fei Chao, Wanchen Sui, Yong Li, Shen Li, Rongrong Ji

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Challenge:	specialized quantization framework for Mixture of Experts architectures is inadequate for model compression.
Approach:	They propose a specialized quantization framework for Mixture of Experts architectures . they find that expert networks exhibit distinctive channel-wise outlier distributions ."
Outcome:	The proposed framework improves on the Mixtral-8x7b-v0.1 architecture while maintaining minimal computational overhead.

Copied to clipboard

Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen

FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning (2026.findings-acl)

Challenge:	Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach:	They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome:	The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .

Copied to clipboard

Yuxi Sun, Aoqi Zuo, Haotian Xie, Wei Gao, Mingming Gong, Jing Ma

Towards General Agentic Intelligence via Environment Scaling (2026.findings-acl)

Challenge:	Existing models generate explanations that appear coherent while containing unfaithful intermediate steps.
Approach:	They propose a causality-inspired framework for evaluating CoT quality using controlled perturbations as an instrumental signal to separate genuine step-to-step dependence from bias-driven artifacts.
Outcome:	Experiments on GSM8K, MATH, and CommonsenseQA show that FACT-E improves reasoning-trajectory selection and yields stronger in-context learning exemplars.

Copied to clipboard

Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Ningyu Zhang, Fei Huang, Wentao Zhang, Jingren Zhou

Psychology-guided Controllable Story Generation (2022.coling-1)

Challenge:	Diverse real-world APIs require precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments.
Approach:	They propose a framework that scales up environments to enable agentic intelligence . they use a two-phase agent fine-tuning strategy to first endow agents with basic agentic capabilities, then specializing them for domain-specific contexts.
Outcome:	Experiments on -bench, -Bench, and ACEBench show that the model significantly enhances the models’ function-calling capability.

Copied to clipboard

Yuqiang Xie, Yue Hu, Yunpeng Li, Guanqun Bi, Luxi Xing, Wei Peng

MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Existing controllable story generation systems ignore the psychological changes of the protagonists and focus on the appointed keywords or emotions.
Approach:	They propose a Psychology-guided Controllable Story Generation System (PICS) that generates stories that adhere to the given leading context and desired psychological state chains for the protagonist.
Outcome:	The proposed system outperforms baselines and shows that it can generate stories with more consistent psychological changes.

Copied to clipboard

Xingchen Xiao, Heyan Huang, Runheng Liu, Jincheng Xie

Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion (2022.findings-acl)

Challenge:	Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) when retrieved contexts are noisy, incomplete, or heterogeneous, a single generation process often struggles to reconcile evidence effectively.
Approach:	They propose a multi-agent synthesis approach to retrieval-augmented generation that structures evidence processing into multiple role-specialized agents.
Outcome:	Experiments on four benchmarks show that MASS-RAG consistently improves performance over strong RAG baselines.

Copied to clipboard

Yiqing Xie, Jiaming Shen, Sha Li, Yuning Mao, Jiawei Han

PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026.findings-acl)

Challenge:	Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document.
Approach:	They propose an evidence-enhanced framework that empowers document-level relation extraction (DocRE) Eider efficiently extracts evidence and effectively fuses extracted evidence in inference.
Outcome:	The proposed framework outperforms state-of-the-art methods on three benchmark datasets.

Copied to clipboard

Chengbing Wang, Wuqiang Zheng, Yang Zhang, Fengbin Zhu, Junyi Cheng, Yi Xie, Wenjie Wang, Fuli Feng

Towards Robust Few-Shot Relation Classification: Incorporating Relation Description with Agreement (2025.findings-emnlp)

Challenge:	Existing reward models evaluate empathy from a single perspective, overlooking bidirectional interaction nature of empathy.
Approach:	They propose a reward model that evaluates empathy from a single perspective . they propose PERM to integrate a bystander perspective to monitor overall interaction quality .
Outcome:	a new reward model outperforms state-of-the-art models on an emotional intelligence benchmark and an industrial daily conversation dataset.

Copied to clipboard

Mengting Hu, Jianfeng Wu, Ming Jiang, Yalan Xie, Zhunheng Wang, Rui Ying, Xiaoyi Liu, Ruixuan Xu, Hang Gao, Renhong Cheng

Exploring Forgetting in Large Language Model Pre-Training (2025.acl-long)

Challenge:	Existing approaches to recognize relational relationships with a few support samples are limited for unlimited queries.
Approach:	They propose a simple but effective framework that uses relation descriptions as external knowledge to enhance the model’s comprehension of the relation semantics.
Outcome:	The proposed framework outperforms strong baselines while being robust against various NOTA rates.

Copied to clipboard

Chonghua Liao, Ruobing Xie, Xingwu Sun, Haowen Sun, Zhanhui Kang

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment (2024.emnlp-main)

Challenge:	Existing research on task-level forgetting in LLMs has focused on pretraining . but, there is limited attention to finer-grained forgetting during training .
Approach:	They investigated the existence and measurement of forgetting in pre-training . they examined low-cost, straightforward methods to mitigate forgetting during the pre- training phase .
Outcome:	The proposed methods could be used to mitigate forgetting during the pre-training phase and offer insights into the dynamics of forgetting.

Copied to clipboard

Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong, Qi Liu

Meta-Information Guided Meta-Learning for Few-Shot Relation Classification (2020.coling-main)

Challenge:	Large vision-language models (LVLMs) are evolving rapidly and require data with human supervision to achieve better alignment.
Approach:	They introduce VLFeedback, the first large-scale vision-language feedback dataset . they train Silkie, an LVLM fine-tuned via direct preference optimization .
Outcome:	The proposed model outperforms its base model in helpfulness, visual faithfulness, and safety metrics and exhibits enhanced resilience against red-teaming attacks.

Copied to clipboard

Bowen Dong, Yuan Yao, Ruobing Xie, Tianyu Gao, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

Data Pollination: An Emergent Ecological Process Driving AI Population Evolution (2026.acl-long)

Challenge:	Existing meta-learning models rely on implicit instance statistics and are unreliability and weak interpretability.
Approach:	They propose a meta-information guided meta-learning framework that uses semantics to guide meta- learning . experimental results demonstrate the effectiveness of the proposed framework .
Outcome:	The proposed framework can establish connections between instance-based information and semantic-based data, enabling faster initialization and adaptation.

Copied to clipboard

Shufang Xie, Qizhi Pei, Ang Lv, Jingyang Hu, Lijun Wu, Rui Yan

Exploring Lottery Prompts for Pre-trained Language Models (2023.acl-long)

Challenge:	evidence from deployed systems suggests that language models interact through a shared data ecosystem.
Approach:	They propose to use data pollination to investigate stability dynamics under synthetic data training to investigate model collapse.
Outcome:	The proposed model can mitigate model collapse observed in recursive training, and improve performance across benchmarks.

Copied to clipboard

Yulin Chen, Ning Ding, Xiaobin Wang, Shengding Hu, Haitao Zheng, Zhiyuan Liu, Pengjun Xie

Tunable Soft Prompts are Messengers in Federated Learning (2023.findings-emnlp)

Challenge:	Existing approaches to optimize pre-trained language models are expensive and slow to scale.
Approach:	They propose to search for instance-level lottery prompts and generalize them to unseen data . they validate the assumption that for every instance, there is almost always a lottery prompt that induces the correct prediction from the PLM .
Outcome:	The proposed method can achieve comparable results with other gradient-free and optimization-free baselines.

Copied to clipboard

Chenhe Dong, Yuexiang Xie, Bolin Ding, Ying Shen, Yaliang Li

GALA: Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training (2026.findings-acl)

Challenge:	Existing methods to protect model privacy in federated learning (FL) are limited.
Approach:	They propose a federated learning approach that provides model privacy protection via tunable soft prompts.
Outcome:	The proposed approach provides protection for the global model while reducing communication and computation costs.

Copied to clipboard

Zhongwei Xie, Ruihao Liao, Zimo Wang, Chong Chen, Xian-Sheng Hua, Xiao Luo

Learning from Contrastive Prompts: An Automated Prompt Optimization Framework (2026.findings-acl)

Challenge:	Existing approaches to self-training are based on reject sampling and lack quality reasoning paths.
Approach:	They propose a framework for self-training using a generate-and-filter paradigm . they propose to identify diverse and informative samples from redundant data and exploit them more strategically.
Outcome:	The proposed framework exploits informative samples from redundant data and improves reasoning trajectory prospecting.

Copied to clipboard

Mingqi Li, Karan Aggarwal, Yong Xie, Aitzaz Ahmad, Stephen Lau

Low-Hallucination and Efficient Coreference Resolution with LLMs (2025.findings-emnlp)

Challenge:	Existing prompt optimization methods often underperform due to learning exclusively from incorrect samples.
Approach:	They propose a framework that leverages contrastive prompts to distinguish between high- and low-performing cases.
Outcome:	The proposed framework can generalize across open and proprietary models and NLU benchmarks.

Copied to clipboard

Yujian Gan, Yuan Liang, Jinxia Xie, Yanni Lin, Juntao Yu, Massimo Poesio

INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning (2024.acl-long)

Challenge:	Large Language Models have shown promising results in coreference resolution, but they face a critical issue: hallucinations.
Approach:	They propose a low-hallucination and efficient solution to the problem of hallucinations . they propose efficient constrained decoding for coreference resolution .
Outcome:	The proposed approach achieves better performance on the English OntoNotes development set.

Copied to clipboard

Yutao Zhu, Peitian Zhang, Chenghao Zhang, Yifei Chen, Binyu Xie, Zheng Liu, Ji-Rong Wen, Zhicheng Dou

Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models (2025.acl-long)

Challenge:	Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks, but their application to information retrieval tasks is still challenging due to the infrequent occurrence of many IR-specific concepts in natural language.
Approach:	They propose to use instruction tuning to enhance LLMs' proficiency in IR tasks by combining a dataset with manually written templates to analyze the effects of instruction design, template diversity, few-shot demonstrations, and the volume of instructions.
Outcome:	The proposed model can be used to perform query understanding, document understanding, and query-document relationship understanding tasks.

Copied to clipboard

Haoran Ye, TianZe Zhang, Yuhang Xie, Liyuan Zhang, Yuanyi Ren, Xin Zhang, Guojie Song

Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have raised concerns regarding their intrinsic values.
Approach:	They propose a psychologically grounded five-factor value system for Large Language Models that integrates psychological principles with cutting-edge AI priorities.
Outcome:	The proposed value system meets standard psychological criteria, improves LLM safety prediction, and enhances Llm alignment, when compared to the canonical Schwartz’s values.

Copied to clipboard

Simin Chen, Yiming Chen, Zexin Li, Yifan Jiang, Zhongwei Wan, Yixin He, Dezhi Ran, Tianle Gu, Haizhou Li, Tao Xie, Baishakhi Ray

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models (2024.acl-long)

Challenge:	In the era of evaluating large language models, data contamination is an increasingly prominent concern . static benchmarking has been used for evaluation, but there are limitations of dynamic benchmarks .
Approach:	They propose a series of optimal design principles for dynamic benchmarking and analyze the limitations of existing static benchmarks.
Outcome:	The proposed benchmarks highlight a critical gap in the evaluation of LLMs.

Copied to clipboard

Damai Dai, Chengqi Deng, Chenggang Zhao, R.x. Xu, Huazuo Gao, Deli Chen, Jiashi Li, Wangding Zeng, Xingkai Yu, Y. Wu, Zhenda Xie, Y.k. Li, Panpan Huang, Fuli Luo, Chong Ruan, Zhifang Sui, Wenfeng Liang

Why Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender System (2025.findings-acl)

Challenge:	Mixture-of-Experts (MoE) architectures face challenges in ensuring expert specialization . despite the promising performance, scaling language models to an extremely large scale is associated with exceedingly high computational costs.
Approach:	They propose an architecture that allows for ultimate expert specialization by segmenting experts into mN ones and activating mK from them.
Outcome:	The proposed architecture achieves comparable performance with GShard with 2B parameters and computation.

Copied to clipboard

Yongsen Zheng, Zongxuan Xie, Guohua Wang, Ziyao Liu, Liang Lin, Kwok-Yan Lam

OpenT2T: An Open-Source Toolkit for Table-to-Text Generation (2024.emnlp-demo)

Challenge:	Unfairness is a well-known challenge in Recommender Systems (RSs) some approaches have started to improve fairness in offline or static contexts, but it often exacerbates over time, leading to significant problems like the Matthew effect, filter bubbles, and echo chambers.
Approach:	They propose a framework to promote multi-interest diversity fairness in RSs by establishing diverse hypergraphs through contrastive learning.
Outcome:	The proposed framework achieves state-of-the-art performance while effectively alleviating unfairness in two CRS-based datasets.

Copied to clipboard

Haowei Zhang, Shengyun Si, Yilun Zhao, Lujing Xie, Zhijian Xu, Lyuhao Chen, Linyong Nan, Pengcheng Wang, Xiangru Tang, Arman Cohan

PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling (2025.acl-long)

Challenge:	Existing methods for table-to-text generation are limited and benchmarked on a limited number of datasets.
Approach:	They propose to use open-source tools to reproduce existing large language models for performance comparison and expedite the development of new models.
Outcome:	The proposed toolkit compares existing large language models on 9 table-to-text generation datasets and maintains a leaderboard to provide insights for future work.

Copied to clipboard

Haojie Xie, Yirong Chen, Xiaofen Xing, Jingkai Lin, Xiangmin Xu

Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation (2021.findings-emnlp)

Challenge:	Existing mental health LLMs do not consider the fact that different psychological counselors exhibit different personal styles.
Approach:	They propose a framework that uses LLMs to construct the digital twin of psychological counselor with personalized counseling style.
Outcome:	The proposed framework can synthesize multi-turn dialogues that closely resemble real-world counseling cases and demonstrate better performance compared to baselines.

Copied to clipboard

Yuexiang Xie, Fei Sun, Yang Deng, Yaliang Li, Bolin Ding

Retrieval Augmented Instruction Tuning for Open NER with Large Language Models (2025.coling-main)

Challenge:	Existing methods to evaluate factual consistency in text summarization neglect the intrinsic cause of factual inconsistency or rely on auxiliary tasks.
Approach:	They propose a method to evaluate the factual consistency in text summarization via counterfactual estimation, which formulates the causal relationship between source document, generated summary, and the language prior.
Outcome:	The proposed metric improves correlation with human judgments and convenience of usage on three public abstractive text summarization datasets.

Copied to clipboard

Tingyu Xie, Jian Zhang, Yan Zhang, Yuanyuan Liang, Qi Li, Hongwei Wang

Neural News Recommendation with Heterogeneous User Behavior (D19-1)

Challenge:	Existing studies have focused on integrating large language models (LLMs) with information extraction (IE) however, the best approach to incorporate information with LLMs for IE remains an open question.
Approach:	They propose to use a Chinese IT dataset to perform RA-IT for IE . they use semantically similar examples from the training dataset as the context .
Outcome:	The proposed approach is evaluated in English and Chinese scenarios.

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Mingxiao An, Tao Qi, Jianqiang Huang, Yongfeng Huang, Xing Xie

Event Detection as Graph Parsing (2021.findings-acl)

Challenge:	Existing news recommendation methods rely on news click history to model user interest, but data sparsity is a problem . other kinds of user behaviors such as webpage browsing and search queries can provide useful clues of users’ news reading interest.
Approach:	They propose to exploit heterogeneous user behaviors to learn news representations from their titles via CNN networks and apply attention networks to select important words.
Outcome:	The proposed approach exploits heterogeneous user behaviors on a real-world dataset.

Copied to clipboard

Jianye Xie, Haotong Sun, Junsheng Zhou, Weiguang Qu, Xinyu Dai

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026.acl-long)

Challenge:	Existing approaches to event detection focus on using syntactic dependency structures or external knowledge to boost the performance.
Approach:	They propose a graph parsing problem that explicitly models multiple event correlations and utilizes rich information conveyed by event type and subtype.
Outcome:	The proposed model outperforms existing models on the public ACE2005 dataset by 4.2% on the dataset.

Copied to clipboard

Zhuohan Xie, Daniil Orel, Rushil Thareja, Dhruv Sahnan, Hachem Madmoun, Fan Zhang, Debopriyo Banerjee, Georgi Nenkov Georgiev, Xueqing Peng, Lingfei Qian, Jimin Huang, Jinyan Su, Aaryamonvikram Singh, Rui Xing, Rania Elbadry, Chen Xu, Haonan Li, Fajri Koto, Ivan Koychev, Tanmoy Chakraborty, Yuxia Wang, Salem Lahlou, Veselin Stoyanov, Sophia Ananiadou, Preslav Nakov

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Challenge:	Existing benchmarks emphasize final numerical answers while neglecting intermediate reasoning steps.
Approach:	They propose a symbolic benchmark for verifiable Chain-of-Thought evaluation in finance . FINCHAIN spans 58 topics across 12 financial domains and three difficulty levels .
Outcome:	The proposed benchmark aims to bridge symbolic reasoning and factual verification.

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

Few-NERD: A Few-shot Named Entity Recognition Dataset (2021.acl-long)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Ning Ding, Guangwei Xu, Yulin Chen, Xiaobin Wang, Xu Han, Pengjun Xie, Haitao Zheng, Zhiyuan Liu

Extractive Entity-Centric Summarization as Sentence Selection using Bi-Encoders (2022.aacl-short)

Challenge:	Existing approaches to few-shot named entity recognition (NER) focus on coarse-grained entities with few examples, while most unseen entities are fine-grounded.
Approach:	They present a human-annotated few-shot named entity recognition dataset . they construct benchmark tasks to assess the generalization capability of models .
Outcome:	The proposed model is the first few-shot NER dataset and the largest human-crafted NER data set.

Copied to clipboard

Ella Hofmann-Coyle, Mayank Kulkarni, Lingjue Xie, Mounica Maddela, Daniel Preotiuc-Pietro

Revealing the Barriers of Language Agents in Planning (2025.naacl-long)

Challenge:	Entity-centric summarization is a type of controllable summarizing that aims to produce a summary specific to a given target entity.
Approach:	They propose to recast a sentence selection task as a controllable summarization using a dataset supported by EntSUM.
Outcome:	The proposed framework outperforms the current state-of-the-art in the sentence selection task and outperformed the competitive entity-centric Lead 3 heuristic by 1.1 F1.

Copied to clipboard

Jian Xie, Kexun Zhang, Jiangjie Chen, Siyu Yuan, Kai Zhang, Yikai Zhang, Lei Li, Yanghua Xiao

AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning (2024.naacl-long)

Challenge:	Existing studies show language agents lack human-level planning abilities . limitations and mechanisms to address them remain insufficiently understood .
Approach:	They apply a feature attribution study to identify key factors hindering agent planning . they identify the limited role of constraints and diminishing influence of questions .
Outcome:	The proposed model achieves 15.6% on a real-world planning benchmark.

Copied to clipboard

Ruiyi Zhang, Rushi Qiang, Sai Ashish Somayajula, Pengtao Xie

Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models (N19-1)

Challenge:	Large-scale pretraining followed by task-specific finetuning has achieved great success in various NLP tasks.
Approach:	They propose a meta learning based framework for automatically identifying the optimal rank of each LoRA layer.
Outcome:	The proposed framework is based on a meta learning based framework that can identify the optimal rank of each LoRA layer.

Copied to clipboard

Tiancheng Zhao, Kaige Xie, Maxine Eskenazi

Incorporating Global Information in Local Attention for Knowledge Representation Learning (2021.findings-acl)

Challenge:	Existing approaches to define action spaces for conversational agents have limitations . end-to-end dialog systems can handle complex domains with limited action space .
Approach:	They propose a latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods to induce its own action space from the data.
Outcome:	The proposed framework achieves better performance than word-level policy gradient methods on DealOrNoDeal and MultiWoz dialogs.

Copied to clipboard

Yu Zhao, Han Zhou, Ruobing Xie, Fuzhen Zhuang, Qing Li, Ji Liu

Diagnosing Failures in Large Language Models’ Answers: Integrating Error Attribution into Evaluation Framework (2025.findings-acl)

Challenge:	Graph Attention Networks (GATs) are a promising model that takes advantage of localized attention mechanism to perform knowledge representation learning (KRL) on graph-structure data.
Approach:	They propose to incorporate global information into the GAT family of models by using an attention-based global random walk algorithm.
Outcome:	Experimental results on KG entity prediction against the state-of-the-arts demonstrate the effectiveness of the proposed model.

Copied to clipboard

Zishan Xu, Shuyi Xie, Qingsong Lv, Shupei Xiao, Linlin Song, Sui Wenjuan, Fan Lin

Towards a Unified Multi-Domain Multilingual Named Entity Recognition Model (2023.eacl-main)

Challenge:	Existing evaluation models lack error attribution capability due to their proprietary nature.
Approach:	They propose a misattribution framework with 6 primary and 15 secondary categories to facilitate in-depth analysis.
Outcome:	The proposed framework is based on a dataset specifically designed for error attribution, along with the corresponding scores and feedback.

Copied to clipboard

Mayank Kulkarni, Daniel Preotiuc-Pietro, Karthik Radhakrishnan, Genta Indra Winata, Shijie Wu, Lingjue Xie, Shaohua Yang

Graph Relational Topic Model with Higher-order Graph Attention Auto-encoders (2021.findings-acl)

Challenge:	Named Entity Recognition is a key task whose performance is sensitive to genre and language.
Approach:	They propose a setup for Named Entity Recognition which includes multi-domain and multilingual training and evaluation across 13 domains and 4 languages.
Outcome:	The proposed model improves on 13 domains and 4 languages across 13 domain and 4 language domains.

Copied to clipboard

Qianqian Xie, Jimin Huang, Pan Du, Min Peng

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment (2024.emnlp-main)

Challenge:	Existing methods for learning low-dimensional representations of networked documents are largely ignored for document networks.
Approach:	They propose a graph relational topic model to explore document neighborhood information . the model can learn efficient networked document representations in the latent topic space .
Outcome:	The proposed model outperforms existing methods on unsupervised representation learning and other downstream tasks.

Copied to clipboard

Yiju Guo, Ganqu Cui, Lifan Yuan, Ning Ding, Zexu Sun, Bowen Sun, Huimin Chen, Ruobing Xie, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

Challenge:	Existing algorithms for achieving optimal alignment are mostly unidirectional . a recent study suggests that large language models can be ground with evident preferences .
Approach:	They propose to ground large language models with evident preferences . they propose to use controllable preference optimization to specify different objectives .
Outcome:	The proposed models can provide responses that match various preferences among the ”3H” desiderata.

Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level (2024.findings-naacl)

Copied to clipboard

Chenlong Zhao, Xiwen Zhou, Xiaopeng Xie, Yong Zhang

In-Context Former: Lightning-fast Compressing Context for Large Language Model (2024.findings-emnlp)

Challenge:	Existing methods for document summarization focus on one type of relation, neglecting the simultaneous effective modeling of both relations.
Approach:	They propose a graph neural network-based approach to local and global document summarization using hierarchical discourses.
Outcome:	The proposed approach improves on two benchmark datasets and shows that hierarchical structures are important for document summarization.

Copied to clipboard

Xiangfeng Wang, Zaiyi Chen, Tong Xu, Zheyong Xie, Yongyi He, Enhong Chen

EMPEC: A Comprehensive Benchmark for Evaluating Large Language Models Across Diverse Healthcare Professions (2025.findings-acl)

Challenge:	Existing methods to reduce inference costs of transformer-based large language models entail quadratic complexity . et al., 2017): transformer-derived large language model performance is a major challenge.
Approach:	They propose a method that compresses long contexts into short soft prompts . they use the self-attention mechanism of the large model to extract and condense information .
Outcome:	The proposed method reduces compression costs by 68 to 112 times while achieving 90% of baseline performance.

Copied to clipboard

Zheheng Luo, Chenhan Yuan, Qianqian Xie, Sophia Ananiadou

GSID: Generative Semantic Indexing for E-Commerce Product Understanding (2025.emnlp-industry)

Challenge:	Recent advances in Large Language Models (LLMs) show their potential in accurately answering biomedical questions, yet current healthcare benchmarks primarily assess knowledge mastered by medical doctors, neglecting other essential professions.
Approach:	They evaluated 17 LLMs including proprietary and open-source models and found they struggled with specialized fields and alternative medicine.
Outcome:	The examinations for medical PErsonnel in Chinese (EMPEC) features 157,803 exam questions across 124 subjects and 20 healthcare professions.

Copied to clipboard

Haiyang Yang, Qinye Xie, Qingheng Zhang, Chen Li Yu, Huike Zou, Chengbao Lian, Shuguang Han, Fei Huang, Jufeng Chen, Bo Zheng

FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction (2020.emnlp-main)

Challenge:	Structured product information is a major bottleneck for the efficiency of e-commerce platforms.
Approach:	They propose a data-driven approach to generate product structured representations using product metadata.
Outcome:	Extensive experiments show that GSID can generate better product representations on real-world e-commerce platforms.

Copied to clipboard

Dianbo Sui, Yubo Chen, Jun Zhao, Yantao Jia, Yuantao Xie, Weijian Sun

Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators (2021.acl-long)

Challenge:	Existing relation extraction methods require centralizing training data from different medical platforms while holding the privacy-sensitive data puts patients' privacy at risk.
Approach:	They propose a federated relation extraction model that trains a central model without sharing or exchange of private local data.
Outcome:	The proposed model trains a central model without uploading local parameters, and it performs well on three publicly available datasets.

Copied to clipboard

Peiyu Liu, Ze-Feng Gao, Wayne Xin Zhao, Zhi-Yuan Xie, Zhong-Yi Lu, Ji-Rong Wen

Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)

Challenge:	Existing methods for pre-trained language models (PLMs) use parameter reduction techniques.
Approach:	They propose a pre-trained language model compression approach based on the matrix product operator from quantum many-body physics.
Outcome:	The proposed approach can decompose an original matrix into central tensors and auxiliary tenses . it can be applied to the original or compressed PLMs in a general way, with a lighter network .

Copied to clipboard

Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han

Challenge:	Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents.
Approach:	They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation.
Outcome:	Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks.

Towards Database-Free Text-to-SQL Evaluation: A Graph-Based Metric for Functional Correctness (2025.coling-main)

Copied to clipboard

Yi Zhan, Longjie Cui, Han Weng, Guifeng Wang, Yu Tian, Boyi Liu, Yingxiang Yang, Xiaoming Yin, Jiajun Xie, Yang Sun

From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)

Challenge:	Existing metrics for evaluating functional correctness of SQL queries are prone to false positives due to inadequately prepared test databases.
Approach:	They propose a graph-based metric that uses a relational operator tree to extract rich semantic information from the logical execution plan of SQL queries and embed it into a diagram.
Outcome:	The proposed method eliminates the need for extensive test database preparation and performs graph matching on unseen SQL queries.

Copied to clipboard

Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu, Xintong Li, Ryan Aponte, Hanjia Lyu, Joe Barrow, Hongjie Chen, Franck Dernoncourt, Branislav Kveton, Tong Yu, Ruiyi Zhang, Jiuxiang Gu, Nesreen K. Ahmed, Yu Wang, Xiang Chen, Hanieh Deilamsalehy, Sungchul Kim, Zhengmian Hu, Yue Zhao, Nedim Lipka, Seunghyun Yoon, Ting-Hao Kenneth Huang, Zichao Wang, Puneet Mathur, Soumyabrata Pal, Koyel Mukherjee, Zhehao Zhang, Namyong Park, Thien Huu Nguyen, Jiebo Luo, Ryan A. Rossi, Julian McAuley

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection (2026.eacl-long)

Challenge:	Large Language Models (LLMs) have been used for selection and training of data for active learning.
Approach:	They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop.
Outcome:	The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances.

Copied to clipboard

Yuhang Liu, Pengxiang Li, Zishu Wei, Congkai Xie, Xueyu Hu, Xinchen Xu, Shengyu Zhang, Xiaotian Han, Hongxia Yang, Fei Wu

Reflect, Rewrite, Repeat: How Simple Arithmetic Enables Advanced Reasoning in Small Language Models (2026.findings-eacl)

Challenge:	Existing GUI Agents face challenges in multi-step reasoning and reliance on textual annotations, limiting their effectiveness.
Approach:	They propose an MLLM-based GUI Agent with a two-stage supervised fine-tuning pipeline that enhances GUI understanding and grounding.
Outcome:	InfiGUIAgent achieves competitive performance on several GUI benchmarks, highlighting the impact of native reasoning skills in enhancing GUI interaction for automation tasks.

Copied to clipboard

Mengdie Flora Wang, Haochen Xie, Mun Young Kim, Baishali Chaudhury, Meghana Ashok, Suren Gunturu, Sungmin Hong, Jae Oh Woo

A Neural Architecture for Automated ICD Coding (P18-1)

Challenge:	Recent advances in language model reasoning require computationally intensive reinforcement learning and massive datasets.
Approach:	They propose a framework that combines Direct Preference Optimization and Supervised Fine-Tuning with selective guidance from larger models and iteratively refining solutions through a "reflect, rewrite, repeat" cycle.
Outcome:	The proposed framework shows significant performance improvements across arithmetic, symbolic and cognitive reasoning benchmarks.

Copied to clipboard

Pengtao Xie, Eric Xing

Challenge:	Medical coding is time-consuming, expensive, and error prone.
Approach:	They propose to use diagnosis descriptions (DDs) of a patient as inputs to select the most relevant ICD codes.
Outcome:	The proposed algorithms perform on a clinical dataset with 59K patient visits.

To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion (2023.acl-long)

Copied to clipboard

Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, Xing Xie

Curriculum Learning for Natural Language Understanding (2020.acl-main)

Challenge:	Existing methods for embedding knowledge graphs implicitly memorize relation rules to infer missing links, but they are difficult to memorize due to the inherent deficiencies of such implicit memorization strategy.
Approach:	They propose a vertical learning paradigm that allows to explicitly copy target information from related factual triples for more accurate prediction.
Outcome:	The proposed model improves generalization ability and makes distant link prediction significantly easier.

Copied to clipboard

Benfeng Xu, Licheng Zhang, Zhendong Mao, Quan Wang, Hongtao Xie, Yongdong Zhang

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model (2025.findings-naacl)

Challenge:	Pre-trained language models can be fine tuned to perform NLU tasks in a straightforward manner.
Approach:	They propose a pretrain-finetune paradigm for natural language understanding (NLU) they propose 'a cross-trainset' approach that allows users to distinguish easy from difficult examples .
Outcome:	The proposed approach achieves significant performance improvements on a wide range of NLU tasks.

Copied to clipboard

Jiali Chen, Xusen Hei, Yuqi Xue, Zihan Wu, Jiayuan Xie, Yi Cai

Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights (2025.acl-long)

Challenge:	Recent large language models (LLMs) overlook children’s reading preferences, which poses challenges in CLA.
Approach:	They propose a method that augments large language models with children's reading preferences for adaptation by obtaining characters' personalities and narrative structure as additional information for fine-grained instruction tuning.
Outcome:	The proposed method significantly improves performance in automatic and human evaluation.

Copied to clipboard

Sooyung Choi, Jaehyeok Lee, Xiaoyuan Yi, Jing Yao, Xing Xie, JinYeong Bak

Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models (2024.findings-acl)

Challenge:	Value-aligned LLMs are more prone to harmful behavior than fine-tuned models . value-aligned models generate text according to the aligned values, which can amplify harmful outcomes.
Approach:	They propose to use in-context alignment methods to enhance the safety of value-aligned LLMs.
Outcome:	The proposed methods improve value alignment and safety, the authors say . value-aligned models are more prone to harmful behavior than fine-tuned models .

Copied to clipboard

Zhenyi Lu, Jie Tian, Wei Wei, Xiaoye Qu, Yu Cheng, Wenfeng Xie, Dangyang Chen

Text Classification

Challenge:	a new text classification framework for large language models addresses the problem of boundary ambiguity and inherent biases in LLMs.
Approach:	They propose a two-stage classification framework for large language models to mitigate bottlenecks . their approach uses pairwise comparisons to efficiently narrow down options .
Outcome:	The proposed framework reduces the number of options and improves on four datasets.

MAGI: Multi-Agent Guided Interview for Psychiatric Assessment (2025.findings-acl)

Copied to clipboard

Guanqun Bi, Zhuang Chen, Zhoufu Liu, Hongkai Wang, Xiyao Xiao, Yuqiang Xie, Wen Zhang, Yongkang Huang, Yuxuan Chen, Libiao Peng, Minlie Huang

Text-based inference of moral sentiment change (D19-1)

Challenge:	Existing large language models (LLMs) do not align with psychiatric diagnostic protocols.
Approach:	They propose a framework that transforms the Mini International Neuropsychiatric Interview into automatic computational workflows through coordinated multi-agent collaboration.
Outcome:	The proposed framework transforms the gold-standard Mini International Neuropsychiatric Interview (MINI) into automatic computational workflows through coordinated multi-agent collaboration.

Copied to clipboard

Jing Yi Xie, Renato Ferreira Pinto Junior, Graeme Hirst, Yang Xu

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)

Challenge:	Existing work in NLP treats moral sentiment as a flat classification problem, but our framework probes moral sentiment change at multiple levels and captures moral dynamics concerning relevance, polarity, and finegrained categories informed by Moral Foundations Theory.
Approach:	They propose a text-based framework that exploits implicit moral biases learned from diachronic word embeddings to probe moral sentiment change over a long historical period.
Outcome:	The proposed framework supports inferences of historical shifts in moral sentiment toward concepts such as slavery and democracy over centuries at three incremental levels: moral relevance, moral polarity, and fine-grained moral dimensions.

Copied to clipboard

Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu

Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference (2024.emnlp-main)

Challenge:	Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios.
Approach:	They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity.
Outcome:	The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues.

Copied to clipboard

Jianxing Yu, Shiqi Wang, Han Yin, Zhenlong Sun, Ruobing Xie, Bo Zhang, Yanghui Rao

Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Sampling (2025.emnlp-main)

Challenge:	a new method to detect clickbait posts on the Web is needed to detect such posts.
Approach:	They propose a method to detect clickbait posts on the Web using latent factors . they use features in multiple modalities to characterize the posts and causal inference to eliminate noise .
Outcome:	The proposed method can detect clickbait posts on popular social media platforms with good generalization ability.

Copied to clipboard

Zhenning Shi, Yijia Zhu, Yi Xie, Junhan Shi, Guorui Xie, Haotian Zhang, Yong Jiang, Congcong Miao, Qing Li

Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking (2024.eacl-long)

Challenge:	Large language models suffer from overconfidence and computational inefficiency due to fixed computation budgets and miscalibrated confidence estimates.
Approach:	They propose a framework for computationally efficient, trustworthy reasoning under uncertainty using Diversity-Aware Self-Signal Dilution and Convergent Adaptive Weighted Sampling techniques.
Outcome:	The proposed framework reduces inference cost by 70% while maintaining accuracy levels while reducing inference costs.

Copied to clipboard

Yong Cao, Ruixue Ding, Boli Chen, Xianzhi Li, Min Chen, Daniel Hershcovich, Pengjun Xie, Fei Huang

Enhancing Nursing and Elderly Care with Large Language Models: An AI-Driven Framework (2025.coling-main)

Challenge:	Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates.
Approach:	They propose a framework to integrate Chinese geographic semantics into re-ranking pipelines.
Outcome:	The proposed framework improves on two Chinese benchmark datasets.

Copied to clipboard

Qiao Sun, Jiexin Xie, Nanyang Ye, Qinying Gu, Shijie Guo

Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks (D19-60)

Challenge:	Experimental results demonstrate significant improvements, paving the way for AI-driven solutions to meet the growing demands of healthcare in aging populations.
Approach:	They introduce a Chinese nursing dataset and implement incremental pre-training and supervised fine-tuning techniques to enhance LLM performance in specialized tasks.
Outcome:	The proposed model performs better in real-time patient monitoring and interaction tasks than previous models.

Copied to clipboard

Xiepeng Li, Zhexi Zhang, Wei Zhu, Zheng Li, Yuan Ni, Peng Gao, Junchi Yan, Guotong Xie

GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent (2025.acl-long)

Challenge:	Existing approaches to represent knowledge in the low-dimensional space are to leverage large-scale unsupervised text corpus to train fixed or contextual representations.
Approach:	They propose to leverage large-scale unsupervised text corpus to train fixed or contextual language representations and to express knowledge into a knowledge graph (KG) they incorporate distributional representations of a KG onto the representations from pre-trained language models, via simply concatenation or multi-head attention.
Outcome:	The proposed models outperform the other models on the COIN: COmmonsense INference in Natural Language Processing (COIN) Workshop datasets.

Copied to clipboard

Bin Xie, Rui Shao, Gongwei Chen, Kaiwen Zhou, Yinchuan Li, Jie Liu, Min Zhang, Liqiang Nie

SubDocTrans: Enhancing Document-level Machine Translation with Plug-and-play Multi-granularity Knowledge Augmentation (2025.findings-emnlp)

Challenge:	GUI automation is a key challenge in dynamic environments.
Approach:	They propose a training-free GUI agent that integrates two mechanisms to explore trajectories in GUIs.
Outcome:	The proposed GUI-explorer shows significant improvements over existing agents.

Copied to clipboard

Hanghai Hong, Yibo Xie, Jiawei Zheng, Xiaoli Wang

MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Challenge:	Document translations generated by large language models suffer from poor consistency, weak coherence, and omission errors.
Approach:	They propose a document-level machine translation framework that extracts knowledge from documents to produce high-quality translations.
Outcome:	The proposed framework improves consistency and coherence, reduces omission errors, and mitigates hallucinations.

Copied to clipboard

Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen

Prompt Tuning for Discriminative Pre-trained Language Models (2022.findings-acl)

Challenge:	Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed .
Approach:	They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities.
Outcome:	The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech .

Copied to clipboard

Yuan Yao, Bowen Dong, Ao Zhang, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Leyu Lin, Maosong Sun, Jianyong Wang

MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity (2025.coling-main)

Challenge:	Recent studies have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing tasks.
Approach:	They propose a prompt tuning framework that reformulates NLP tasks into a discriminative language modeling problem.
Outcome:	The proposed framework improves on text classification and question answering tasks and prevents unstable tuning problems in low-resource settings.

Copied to clipboard

Xiaqiang Tang, Qiang Gao, Jian Li, Nan Du, Qi Li, Sihong Xie

A Black-Box Attack on Code Models via Representation Nearest Neighbor Search (2023.findings-emnlp)

Challenge:	Existing RAG frameworks either indiscriminately perform retrieval or rely on rigid single-label classifiers to select retrieval methods.
Approach:	They propose a framework that dynamically selects the most suitable retrieval strategy based on query complexity.
Outcome:	The proposed framework achieves state-of-the-art results on multiple single-hop and multi-hop datasets while reducing retrieval costs.

Copied to clipboard

Jie Zhang, Wei Ma, Qiang Hu, Shangqing Liu, Xiaofei Xie, Yves Le Traon, Yang Liu

Calibrating Language Models with Adaptive Temperature Scaling (2024.emnlp-main)

Challenge:	Existing methods for generating adversarial code examples face challenges such as limted availability of substitute variables and the creation of adversarials with noticeable perturbations.
Approach:	They propose a search seed based on historical attacks to find adversarial substitutes . they employ a pre-trained variable name encoder to map the search seed to a continuous vector space .
Outcome:	The proposed approach outperforms baseline methods in terms of ASR and QT.

Copied to clipboard

Johnathan Xie, Annie Chen, Yoonho Lee, Eric Mitchell, Chelsea Finn

FLAG-TRADER: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading (2025.findings-acl)

Challenge:	Large language models' confidence scores are degraded after fine-tuning with reinforcement learning from human feedback.
Approach:	They propose a post-hoc calibration method that predicts a temperature scaling parameter for each token prediction.
Outcome:	Adaptive temperature scaling improves calibration by over 10% compared to prior methods . RLHF fine-tuning improves model accuracy, but degradation is not significant .

Copied to clipboard

Guojun Xiong, Zhiyang Deng, Keyi Wang, Yupeng Cao, Haohang Li, Yangyang Yu, Xueqing Peng, Mingquan Lin, Kaleb E Smith, Xiao-Yang Liu, Jimin Huang, Sophia Ananiadou, Qianqian Xie

Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generation (2025.emnlp-main)

Challenge:	Large language models (LLMs) have impressive reasoning capabilities in financial tasks, but struggle with multi-step, goal-oriented scenarios in interactive financial markets.
Approach:	They propose a framework that integrates large language models with gradient-driven reinforcement learning (RL) policy optimization.
Outcome:	The proposed framework improves performance in trading and other financial domain tasks.

Copied to clipboard

Mert Inan, Anthony Sicilia, Alex Xie, Saujas Vaduguru, Daniel Fried, Malihe Alikhani

WR-One2Set: Towards Well-Calibrated Keyphrase Generation (2022.emnlp-main)

Challenge:	ambiguities in natural language can lead to outputs that seem correct but fail to reflect the speaker’s intent.
Approach:	They propose to identify and then resolve ambiguities in natural language and propose metrics to quantify them.
Outcome:	The proposed metrics better correlate with human annotations than uncertainty baselines.

Copied to clipboard

Binbin Xie, Xiangpeng Wei, Baosong Yang, Huan Lin, Jun Xie, Xiaoli Wang, Min Zhang, Jinsong Su

TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice (2026.acl-long)

Challenge:	Experimental results show that keyphrase generation has serious calibration errors . ONE2SET generates short phrases summarizing an input document .
Approach:	They propose a paradigm for keyphrase generation that generates short phrases summarizing an input document.
Outcome:	The proposed model over-estimates tokens and makes it well-calibrated on common datasets.

Copied to clipboard

Gang Hu, Yating Chen, Haiyan Ding, Wang Gao, Huang Jiajia, Min Peng, Qianqian Xie, Kun Yue

Challenge:	Large Language Models excel in general domains but lack real-world practical capabilities.
Approach:	They propose a benchmark for Chinese taxation practice that combines 10 traditional application tasks with 3 pioneering real-world scenarios.
Outcome:	The proposed benchmark combines 10 traditional tasks with 3 pioneering real-world scenarios.

MixTEA: Semi-supervised Entity Alignment with Mixture Teaching (2023.findings-emnlp)

Copied to clipboard

Feng Xie, Xin Song, Xiang Zeng, Xuechen Zhao, Lei Tian, Bin Zhou, Yusong Tan

LOHRec: Leveraging Order and Hierarchy in Generative Sequential Recommendation (2025.findings-emnlp)

Challenge:	Existing methods to learn informative entity embeddings are insufficient for semi-supervised entity alignment.
Approach:	They propose a semi-supervised method which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings.
Outcome:	The proposed method is superior to existing methods on benchmark datasets and further analyses.

Copied to clipboard

Jiawen Xie, Haiyang Wu, Deyi Ji, Yuekui Yang, Shaoping Ma

Challenge:	generative recommenders focus on maximizing the prediction probability of the next item in the temporal sequence, ignoring diverse potential items.
Approach:	They propose a learning framework that leverages order and hierarchy in generative recommendation using quantized identifiers to further explore performance ceiling of lightweight generative recommenders.
Outcome:	The proposed learning framework outperforms strong prior baselines across multiple datasets.

Domain-Specific NER via Retrieving Correlated Samples (2022.coling-1)

Copied to clipboard

Xin Zhang, Yong Jiang, Xiaobin Wang, Xuming Hu, Yueheng Sun, Pengjun Xie, Meishan Zhang

AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model (2023.acl-long)

Challenge:	Successful Named Entity Recognition models fail on texts from some special domains, for example, Chinese addresses and e-commerce titles.
Approach:	They propose to enhance NER models with correlated samples to help the text understanding . they draw correlated texts by the sparse BM25 retriever from large-scale in-domain unlabeled data .
Outcome:	Empirical results show that NER models can be enhanced with correlated samples . the proposed model can be used to reason out the correct answer on hard cases .

Copied to clipboard

I-Hung Hsu, Zhiyu Xie, Kuan-Hao Huang, Prem Natarajan, Nanyun Peng

EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding (2026.acl-long)

Challenge:	Existing generation-based EAE models focus on problem re-formulation and prompt design without incorporating additional information that has been shown to be effective for classification-based models.
Approach:	They propose to incorporate AMR into generation-based EAE models by generating AMR-aware prefixes for every layer of the generation model.
Outcome:	The proposed model generates AMR-aware prefixes for every layer of the generation model and improves the generation.

Copied to clipboard

Pengze Guo, Jingxi Liang, Zhiwen Xie, Qifeng Wang, Derek F. Wong

TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System (2025.findings-naacl)

Challenge:	Existing benchmarks fail to achieve ecological validity, signal clarity, and reliable fine-grained labeling in multimodal Emotion Recognition (MER) Existing datasets lack spontaneity of real-life interactions, resulting in poor quality and inconsistent data quality.
Approach:	They propose a bilingual benchmark to resolve limitations of ecological validity and noise in existing datasets by combining strictly filtered static slices with a dynamic Streaming Monologue subset.
Outcome:	EmoS provides trusted ground truth that captures continuous emotional evolution.

Copied to clipboard

Zeyu Zhang, Jianxun Lian, Chen Ma, Yaning Qu, Ye Luo, Lei Wang, Rui Li, Xu Chen, Yankai Lin, Le Wu, Xing Xie, Ji-Rong Wen

Reinforcement Learning with Token-level Feedback for Controllable Text Generation (2024.findings-naacl)

Challenge:	Trending topics bring in a new channel for poisoning attacks, resulting in negative impacts on society.
Approach:	They propose an LLM-based multi-agent system to simulate trending topics in social media . they propose a time-aware interaction mechanism, centralized message dissemination, and an interactive system .
Outcome:	The proposed system simulates trending topics under poisoning attacks on social media platforms.

Copied to clipboard

Wendi Li, Wei Wei, Kaihe Xu, Wenfeng Xie, Dangyang Chen, Yu Cheng

Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention (2022.emnlp-main)

Challenge:	Existing methods for controllable text generation are guided by coarse-grained feedback, which may lead to suboptimal performance owing to semantic twists or progressions within sentences.
Approach:	They propose a reinforcement learning algorithm which formulates TOken-LEvel rewards for controllable text generation and employs a "first-quantize-then-noise" paradigm to enhance the robustness of the RL algorithm.
Outcome:	The proposed algorithm can achieve superior performance on single-attribute and multi-attract control tasks.

Copied to clipboard

Wenhao Li, Xiaoyuan Yi, Jinyi Hu, Maosong Sun, Xing Xie

PlanningArena: A Modular Benchmark for Multidimensional Evaluation of Planning and Tool Learning (2025.acl-long)

Challenge:	Recent studies have shown that powerful Transformer architectures produce dull high-frequency phrases, severely hurting the diversity and novelty of generated text.
Approach:	They propose a method to control the sharpness of the attention distribution by python code and use it to learn a Bayesian approximation of posterior attention.
Outcome:	The proposed method improves diversity and novelty while maintaining comparable quality on conditional and unconditional generation tasks.

Copied to clipboard

Zihan Zheng, Tianle Cui, Chuwen Xie, Jiahui Pan, Qianglong Chen, Lewei He

DCP: Dual-Cue Pruning for Efficient Large Vision-Language Models (2025.emnlp-main)

Challenge:	Recent studies have shown that LLMs can be significantly improved by integrating external tools.
Approach:	They propose a framework that integrates external tools into large language models to evaluate their ability to generate action plans.
Outcome:	The proposed framework evaluates the ability of large language models to generate action plans and generate action plan templates.

Copied to clipboard

Lei Jiang, Zixun Zhang, Yuting Zeng, Chunzhao Xie, Tongxuan Liu, Zhen Li, Lechao Cheng, Xiaohua Xu

Knowledge Context Modeling with Pre-trained Language Models for Contrastive Knowledge Graph Completion (2024.findings-acl)

Challenge:	Existing pruning methods for large vision language models use visual tokens to prune . existing methods fail to balance efficiency and semantic alignment due to large number of visual token.
Approach:	They propose a cross-modal pruning framework that considers textual semantics and visual self-attention to combine them to achieve efficient inference acceleration.
Outcome:	The proposed pruning framework can retain only 25% of the visual tokens, with a minimal performance degradation of only 0.063% on LLaVA-1.5-13B.

Copied to clipboard

Guangqian Yang, Yi Liu, Lei Zhang, Licheng Zhang, Hongtao Xie, Zhendong Mao

COMBO: A Complete Benchmark for Open KG Canonicalization (2023.eacl-main)

Challenge:	Text-based knowledge graph completion methods neglect knowledge contexts in inferring process.
Approach:	They propose a framework which models the knowledge context as additional prompts with pre-trained language models for knowledge graph completion.
Outcome:	The proposed framework achieves state-of-the-art on FB15k-237, WN18RR and Wikidata5M datasets.

Copied to clipboard

Chengyue Jiang, Yong Jiang, Weiqi Wu, Yuting Zheng, Pengjun Xie, Kewei Tu

emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation (2024.findings-acl)

Challenge:	Existing datasets for open KG canonicalization only provide gold entity-level canonization for noun phrases.
Approach:	They propose a complete benchmark for open KG canonicalization that provides gold ontology-level canonization for relation phrases and source sentences for extraction.
Outcome:	The proposed method improves relation canonicalization and ontology-level canonization of the noun phrase.

Copied to clipboard

Ziyang Ma, Zhisheng Zheng, Jiaxin Ye, Jinchao Li, Zhifu Gao, ShiLiang Zhang, Xie Chen

AuriSRec: Adversarial User Intention Learning in Sequential Recommendation (2024.findings-emnlp)

Challenge:	Existing models for speech emotion recognition are not suitable for emotional tasks.
Approach:	They propose a universal speech emotion representation model that is pre-trained on open-source emotion data.
Outcome:	euphoria2vec outperforms state-of-the-art models and emotion specialist models . it shows consistent improvements among 10 different languages of speech emotion recognition datasets .

Copied to clipboard

Junjie Zhang, Ruobing Xie, Wenqi Sun, Leyu Lin, Xin Zhao, Ji-Rong Wen

ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code (2026.findings-acl)

Challenge:	Existing work focuses on capturing user implicit preferences from historical interactions and matching them with the next behavior, instead of predicting user explicit intentions.
Approach:	They propose an adversarial user intention learning approach for sequential recommendaiton . the approach explicitly predicts user current intentions by taking historical reviews as inputs .
Outcome:	The proposed approach explicitly predicts user intentions by inferring their decision-making process as explained in target reviews.

Copied to clipboard

Jian Xie, Zhendong Chu, Aoxiao Zhong, Kai Zhang, Mingzhe Han, Xing Fan, Jialie Shen, Qingsong Wen

Multi-class Hierarchical Question Classification for Multiple Choice Science Exams (2020.lrec-1)

Challenge:	Large Reasoning Models suffer from the "over-thinking" problem, causing performance degradation.
Approach:	They propose a unified model that balances reasoning performance and efficiency across multiple formats through a reinforcement learning framework augmented with length-aware optimization.
Outcome:	The proposed model reduces token costs while preserving performance compared to traditional models.

Copied to clipboard

Dongfang Xu, Peter Jansen, Jaycie Martin, Zhengnan Xie, Vikas Yadav, Harish Tayyar Madabushi, Oyvind Tafjord, Peter Clark

GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-Distribution Generalization Perspective (2023.findings-acl)

Challenge:	Prior work has demonstrated that question classification (QC) can help answer a question more accurately.
Approach:	They propose to use a large dataset for question classification (QC) that contains 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains to train a BERT-based model.
Outcome:	The proposed model achieves a large (+0.12 MAP) gain while also achieving state-of-the-art performance on benchmark open-domain and biomedical QC datasets.

Copied to clipboard

Linyi Yang, Shuibai Zhang, Libo Qin, Yafu Li, Yidong Wang, Hanmeng Liu, Jindong Wang, Xing Xie, Yue Zhang

SupMMD: A Sentence Importance Model for Extractive Summarization using Maximum Mean Discrepancy (2020.findings-emnlp)

Challenge:	Pre-trained language models (PLMs) have improved generalization performance but the out-of-distribution (OOD) generalization problem remains a challenge in many NLP tasks.
Approach:	They propose to create a benchmark for evaluating out-of-distribution (OOD) generalization in NLP models.
Outcome:	The proposed benchmarks highlight the importance of OOD robustness and provide insights on how to measure it and improve it.

Copied to clipboard

Umanga Bista, Alexander Mathews, Aditya Menon, Lexing Xie

Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion (2024.acl-long)

Challenge:	Existing work on multi-document summarization has focused on generic summarizing of information present in each document set.
Approach:	They propose a technique for generic and update summarization based on kernel two-sample testing.
Outcome:	The proposed technique exceeds the current state-of-the-art on two datasets.

Copied to clipboard

Rui Ying, Mengting Hu, Jianfeng Wu, Yalan Xie, Xiaoyi Liu, Zhunheng Wang, Ming Jiang, Hang Gao, Linlin Zhang, Renhong Cheng

The time scale of redundancy between prosody and linguistic context (2025.acl-long)

Challenge:	Current methods embed factual knowledge into continuous vector space and apply geometric operations to learn potential patterns in temporal knowledge graphs.
Approach:	They propose a temporal knowledge graph completion method that uses two geometric operations to learn missing facts in temporal graphs.
Outcome:	The proposed method significantly outperforms existing temporal knowledge graph embedding models.

Copied to clipboard

Tamar I Regev, Chiebuka Ohams, Shaylee Xie, Lukas Wolf, Evelina Fedorenko, Alex Warstadt, Ethan Wilcox, Tiago Pimentel

Challenge:	Prior work has shown that the information carried by prosodic features is substantially redundant with that carried by the surrounding words.
Approach:	They examine the time scale of this relationship, studying how it varies with the length of past and future contexts.
Outcome:	The results show that prosody features show some redundancy with future words, but only with a short scale of 1-2 words, consistent with reports of incremental short-term planning in language production.

Memp: Exploring Agent Procedural Memory (2026.findings-acl)

Copied to clipboard

Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Challenge:	Large Language Models (LLMs) based agents suffer from brittle procedural memory that is manually engineered or entangled in static parameters.
Approach:	They propose a procedural-memory repository that distills past agent trajectories into fine-grained, step-by-step instructions and higher-level, script-like abstractions.
Outcome:	The proposed repository can be used to improve agents' performance on travelplanner and Alfworld.

MolXPT: Wrapping Molecules with Text for Generative Pre-training (2023.acl-short)

Copied to clipboard

Zequn Liu, Wei Zhang, Yingce Xia, Lijun Wu, Shufang Xie, Tao Qin, Ming Zhang, Tie-Yan Liu

Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication (2024.findings-emnlp)

Challenge:	Experimental results show that Generative pre-trained Transformers (GPT) have great success in natural language processing.
Approach:	They propose a unified language model of text and molecules pre-trained on SMILES wrapped by text.
Outcome:	The proposed model outperforms strong baselines of molecular property prediction on MoleculeNet and performs comparably to the best model in text-molecule translation while using less than half of its parameters.

Copied to clipboard

Weize Chen, Chenfei Yuan, Jiarui Yuan, Yusheng Su, Chen Qian, Cheng Yang, Ruobing Xie, Zhiyuan Liu, Maosong Sun

MaCSC: Towards Multimodal-augmented Pre-trained Language Models via Conceptual Prototypes and Self-balancing Calibration (2024.naacl-long)

Challenge:	Natural language (NL) has long been the predominant format for human cognition and communication, but its utility in LLMs has not been thoroughly examined.
Approach:	They propose to allow LLMs to choose the most suitable format before reasoning or communicating, and to automate the selection process.
Outcome:	The proposed format improves reasoning efficiency and reduces token usage while maintaining communicative effectiveness.

Copied to clipboard

Xianwei Zhuang, Zhichang Wang, Xuxin Cheng, Yuxin Xie, Liming Liang, Yuexian Zou

Iterative Self-Correction for Text-Driven Person Re-Identification with Large Vision-Language Models (2026.findings-acl)

Challenge:	Existing approaches to training pre-trained language models (PLMs) focus on static image modality; inevitably encounter modality gaps and noise; and treat all modalities.
Approach:	They propose a multimodal-augmented framework that can infuse multimodal semantics into PLMs and facilitate a self-balancing calibration of information allocation.
Outcome:	The proposed framework outperforms baselines on multiple NLP tasks and outperformed existing frameworks.

Copied to clipboard

Guijin Luo, Zequn Xie, Sihang Cai, Chuxin Wang, Zhou Zhao, Yixuan Tang

STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)

Challenge:	Existing methods for Person Re-Identification (ReID) adopt a static "one-pass" paradigm, converting images to text once for retrieval.
Approach:	They propose a framework that reformulates ReID as an iterative "Think-and-Refine" process.
Outcome:	The proposed framework outperforms state-of-the-art methods in complex occlusion scenarios.

Copied to clipboard

Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma

Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning (2025.acl-long)

Challenge:	Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation.
Approach:	They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset.
Outcome:	The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations.

Copied to clipboard

Yexing Du, Youcheng Pan, Ziyang Ma, Bo Yang, Yifan Yang, Keqi Deng, Xie Chen, Yang Xiang, Ming Liu, Bing Qin

Optimizing Retrieval-Augmented Generation for E-Commerce How-To Assistance (2026.acl-industry)

Challenge:	Existing studies on English-centric translation tasks have focused on multimodal large language models, but the exploration of many-to-many translation is limited by the scarcity of parallel data.
Approach:	They propose a three-stage curriculum learning strategy that leverages the machine translation capabilities of large language models and adapts them to S2TT tasks.
Outcome:	The proposed strategy achieves state-of-the-art average performance in 1514 language pairs, requiring fewer than 10 hours of speech data per language to achieve competitive results.

Copied to clipboard

Gilad Fuchs, Leonid Ekimov, Fei Dong, Jiahong Xie, Wei Liu, Maxim Manco, Alexander Nus

SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training (2025.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have significantly improved Retrieval-Augmented Generation (RAG), enabling assistants that can reliably ground responses in external knowledge sources while maintaining high-quality natural language interaction.
Approach:	They propose a RAG-based How-To Assistant that groundes responses in a proprietary knowledge base to provide personalized customer support.
Outcome:	The proposed assistant can ground responses in a proprietary knowledge base while maintaining high-quality natural language interaction.

Copied to clipboard

Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen

Speech & Audio in NLP

Challenge:	a new spoken dialogue system with single-stage training is demonstrating its low latency and high quality . SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens .
Approach:	They propose a timbre-controllable, end-to-end voice interaction system with single-stage training.
Outcome:	The proposed system outperforms previous models on 4 GPUs with limited data.

SynC-LLM: Generation of Large-Scale Synthetic Circuit Code with Hierarchical Language Models (2025.emnlp-main)

Copied to clipboard

Shang Liu, Yao Lu, Wenji Fang, Jing Wang, Zhiyao Xie

Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models (2024.emnlp-main)

Challenge:	Recent years, AI-assisted integrated circuit design methods have shown great potential in boosting IC design efficiency. however, this emerging technique is limited by the serious scarcity of publicly accessible large-scale circuit design data, which are mostly private IPs owned by semiconductor companies.
Approach:	They propose a hierarchical framework that exploits LLM's ability to generate new large-scale synthetic digital circuits by learning sequential logic skeletons and annotating function descriptions.
Outcome:	The proposed framework generates large-scale synthetic circuits that are valid and fully functional, and can significantly improve AI models’ performance in multiple IC design tasks.

Copied to clipboard

Hongfu Liu, Yuxi Xie, Ye Wang, Michael Shieh

LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)

Challenge:	Recent efforts have identified adversarial suffixes capable of jailbreaking LLMs . however, GCG struggles with computational inefficiency, limiting further studies .
Approach:	They propose a two-stage transfer learning framework which decouples the search process into behavior-agnostic pre-searching and behavior-relevant post-search.
Outcome:	The proposed approach outperforms baseline on Llama2-chat-7b with ASRs of 43.9 (+ 22.2) and 39.0 (+ 19.5) on valid and test sets.

Copied to clipboard

Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang

Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning (2024.eacl-long)

Challenge:	LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases .
Approach:	They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website .
Outcome:	The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks.

Copied to clipboard

Kaige Xie, Tong Yu, Haoliang Wang, Junda Wu, Handong Zhao, Ruiyi Zhang, Kanak Mahadik, Ani Nenkova, Mark Riedl

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution (2025.findings-acl)

Challenge:	Existing prompt transfer techniques lack consideration for dialogue-specific information.
Approach:	They propose a method which leverages skeleton generation as extra supervision that functions as a medium connecting the distinct source and target task.
Outcome:	The proposed method significantly outperforms baselines on two dialogue summarization benchmarks.

Copied to clipboard

Chengxing Xie, Bowen Li, Chang Gao, He Du, Wai Lam, Difan Zou, Kai Chen

GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion (2026.acl-long)

Challenge:	Large Language Models excel in code generation benchmarks, but these benchmarks focus on single-file scenarios with constrained context scope.
Approach:	They propose an open-source framework to effectively resolve GitHub issues using a code file retrieval module and a model-based code editing module.
Outcome:	The proposed approach achieves state-of-the-art performance on two GitHub benchmarks.

Copied to clipboard

Qizhuo Xie, Yunhui Liu, Yu Xing, Qianzi Hou, Xudong Jin, Tao Zheng, Tieke He

Bi-directional CognitiveThinking Network for Machine Reading Comprehension (2020.coling-main)

Challenge:	Existing quantization-based approaches to knowledge Graph Completion (KGC) are incomplete.
Approach:	They propose a framework that generates semantically coherent discrete codes for KG entities . they introduce a Granular Semantic Enhancement module that injects hierarchical knowledge into the codebook .
Outcome:	The proposed framework outperforms existing text-based and embedding-based baselines in the KGC domain.

Copied to clipboard

Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Jing Yu, Yajing Sun, Xiangpeng Wei

StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion (2024.acl-long)

Challenge:	Existing methods for reading comprehension are still in their infancy at the level of cognitive intelligence.
Approach:	They propose a bi-directional cognitive knowledge framework to simulate reverse thinking and inertial thinking in the brain to answer questions.
Outcome:	The proposed framework shows that bi-directional knowledge helps the QA task.

Copied to clipboard

Zhichao Wang, Yuanzhe Chen, Xinsheng Wang, Lei Xie, Yuping Wang

Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition (2021.acl-long)

Challenge:	Existing LM-based VC models require offline conversion from source semantics to acoustic features, limiting their deployment to real-time applications.
Approach:	They propose a streaming LM-based model for zero-shot voice conversion that uses a fully causal context-aware LM with a temporal-independent acoustic predictor to facilitate real-time conversion given arbitrary speaker prompts and source speech.
Outcome:	The proposed model achieves comparable performance to non-streaming VC systems while maintaining a fully causal context-aware LM with a temporal-independent acoustic predictor.

Copied to clipboard

Xin Zhang, Guangwei Xu, Yueheng Sun, Meishan Zhang, Pengjun Xie

KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)

Challenge:	Experimental results show that crowdsourced annotations are highly effective under supervised conditions.
Approach:	They propose an annotator-aware representation learning model that is inspired by domain adaptation methods which attempt to capture effective domain-alike features.
Outcome:	The proposed model is highly effective on a benchmark dataset and achieves state-of-the-art performance with only a very small scale of expert annotations.

Copied to clipboard

Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang

Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation (2025.findings-emnlp)

Challenge:	Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question .
Approach:	They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance .
Outcome:	The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered .

Copied to clipboard

Jiahao Cheng, Tiancheng Su, Jia Yuan, Guoxiu He, Jiawei Liu, Xinqi Tao, Jingwen Xie, Huaxia Li

Constructing Interpretive Spatio-Temporal Features for Multi-Turn Responses Selection (P19-1)

Challenge:	Chain-of-Thought (CoT) prompting can mitigate hallucinations by encouraging step-by-step reasoning, but its impact on halluciation detection remains underexplored.
Approach:	They conduct an empirical evaluation of CoT prompting in Large Language Models (LLMs) to examine their impact on hallucination detection methods.
Outcome:	The proposed method significantly affects the internal states and token probability distributions of the LLM.

Copied to clipboard

Junyu Lu, Chenbin Zhang, Zeying Xie, Guang Ling, Tom Chao Zhou, Zenglin Xu

DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic (2025.emnlp-main)

Challenge:	Existing models for response selection do not perform well when there are many candidate responses.
Approach:	They propose a Spatio-Temporal Matching network (STM) for response selection . they use soft alignment to obtain local relevance between context and response .
Outcome:	The proposed model significantly outperforms the state-of-the-art model on two large-scale multi-turn response selection tasks.

Copied to clipboard

Yuheng Wu, Jianwen Xie, Denghui Zhang, Zhaozhuo Xu

Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation (2023.emnlp-main)

Challenge:	Theory-of-Mind (ToM) tasks pose a unique challenge for large language models (LLMs), which often lack the capability for dynamic logical reasoning.
Approach:	They propose a framework that decomposes ToM tasks into a sequence of belief updates grounded in Dynamic Epistemic Logic (DEL) they use data generated automatically via a DEL simulator to train a verifier, which is called the Process Belief Model (PBM).
Outcome:	The proposed framework improves verifiable ToM reasoning through inference-time scaling rather than architectural changes.

Copied to clipboard

Mingfeng Xue, Dayiheng Liu, Wenqiang Lei, Jie Fu, Jian Lan, Mei Li, Baosong Yang, Jun Xie, Yidan Zhang, Dezhong Peng, Jiancheng Lv

Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning (2024.findings-emnlp)

Challenge:	Existing unsupervised paraphrase generation methods require large-scale, manually annotated paraphrase datasets, which are labor-intensive to build.
Approach:	They propose a self-supervised pseudo-data construction method that generates diverse pseudo-paraphrases in distinct surface structures for a given sentence.
Outcome:	The proposed method generates diverse pseudo-paraphrases in distinct surface structures for a given sentence.

Copied to clipboard

Tianxiang Hu, Pei Zhang, Baosong Yang, Jun Xie, Derek Wong, Rui Wang

LLM Agents for Education: Advances and Applications (2025.findings-emnlp)

Challenge:	Achieving consistent high-quality machine translation across diverse domains remains a challenge due to limited and imbalanced parallel training data available in various domains.
Approach:	They propose a domain Chain of Thought technique that uses the multi-domain intelligence of LLMs to improve translation performance.
Outcome:	The proposed method achieves significant improvements in translation accuracy and domain robustness over traditional fine-tuning on a small dataset of four domains.

Copied to clipboard

Zhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu, Yibo Yan, Jingheng Ye, Aoxiao Zhong, Xuming Hu, Jing Liang, Philip S. Yu, Qingsong Wen

Modeling Historical Relevant and Local Frequency Context for Representation-Based Temporal Knowledge Graph Forecasting (2024.findings-emnlp)

Challenge:	Large Language Model (LLM) agents are transforming education by automating complex tasks and enhancing both teaching and learning processes.
Approach:	This survey analyzes recent advances in applying Large Language Model agents to educational settings . it highlights ethical issues, hallucination and overreliance, and integration with existing ecosystems .
Outcome:	The authors analyze the technologies enabling LLM agents and highlight key challenges in deploying them in educational settings.

Copied to clipboard

Shengzhe Zhang, Wei Wei, Rikui Huang, Wenfeng Xie, Dangyang Chen

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Challenge:	Existing representation-based approaches neglect candidate-specific temporal context, resulting in serious information loss or homogeneous prediction.
Approach:	They propose a temporal representation learning model that incorporates temporal contexts of candidates and models temporal contextual information from historiCal Relevant context and locAl Frequency contexT.
Outcome:	The proposed model can leverage temporal contextual information to achieve differential predictions on six benchmark datasets.

Copied to clipboard

Zhiwei Liu, Yupeng Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Md. Tariquzzaman, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Ming-Bin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou

Neural News Recommendation with Long- and Short-term User Representations (P19-1)

Challenge:	Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach:	They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome:	The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.

Copied to clipboard

Mingxiao An, Fangzhao Wu, Chuhan Wu, Kun Zhang, Zheng Liu, Xing Xie

Language Models “Grok” to Copy (2025.naacl-short)

Challenge:	Existing news recommendation methods learn a single representation for each user, which may be insufficient.
Approach:	They propose a neural news recommendation approach which can learn both long- and short-term user representations by using a news encoder and a user encoder.
Outcome:	The proposed approach can learn both long- and short-term user representations on a real-world dataset.

Copied to clipboard

Ang Lv, Ruobing Xie, Xingwu Sun, Zhanhui Kang, Rui Yan

LightVLP: A Lightweight Vision-Language Pre-training via Gated Interactive Masked AutoEncoders (2024.lrec-main)

Challenge:	We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context.
Approach:	They propose that Transformer-based language models develop copying abilities similarly to grokking . they argue that the connection between groking and context copying can improve in-context performance.
Outcome:	The proposed model development is similar to grokking, but the speed is independent of tokens trained.

Copied to clipboard

Xingwu Sun, Zhen Yang, Ruobing Xie, Fengzong Lian, Zhanhui Kang, Chengzhong Xu

VulLibGen: Generating Names of Vulnerability-Affected Packages via a Large Language Model (2024.acl-long)

Challenge:	Existing vision-language pre-training models use multi-modal encoders to encode image and text, causing noisy training corpora.
Approach:	They propose a vision-language pre-training framework with two autoencoders for efficient training . they propose masked tokens and a gated interaction mechanism to cope with noise .
Outcome:	The proposed model achieves 2.2% R@1 gains on COCO Text Retrieval and 1.1% on refCOCO+ on six datasets.

Copied to clipboard

Tianyu Chen, Lin Li, ZhuLiuchuan ZhuLiuchuan, Zongyang Li, Xueqing Liu, Guangtai Liang, Qianxiang Wang, Tao Xie

In-Context Learning for Few-Shot Dialogue State Tracking (2022.findings-emnlp)

Challenge:	Existing work on affected package identification is limited by large language models . a recent study shows that 84% third-party packages contain security vulnerabilities .
Approach:	They propose a method to use LLM to generate the affected package . they propose supervised fine-tuning, retrieval augmented generation and a local search algorithm .
Outcome:	The proposed method has an average precision of 0.806 for identifying vulnerable packages in four most popular ecosystems in GitHub Advisory.

Copied to clipboard

Yushi Hu, Chia-Hsuan Lee, Tianbao Xie, Tao Yu, Noah A. Smith, Mari Ostendorf

INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent (2025.acl-long)

Challenge:	Existing methods for zero-shot and few-shot learning dialogue state tracking are hard and expensive.
Approach:	They propose an in-context learning framework for zero-shot and few-shot learning dialogue state tracking (DST) a large pretrained language model takes a test instance and a few exemplars as input and directly decodes the dialogue state .
Outcome:	The proposed framework outperforms state-of-the-art models in few-shot settings . it is flexible and scalable, and requires less data to adapt to new domains and scenarios .

Copied to clipboard

Haohang Li, Yupeng Cao, Yangyang Yu, Shashidhar Reddy Javaji, Zhiyang Deng, Yueru He, Yuechen Jiang, Zining Zhu, K.p. Subbalakshmi, Jimin Huang, Lingfei Qian, Xueqing Peng, Jordan W. Suchow, Qianqian Xie

Entity Framing and Role Portrayal in the News (2025.findings-acl)

Challenge:	Recent advances have underscored the potential of large language model (LLM)-based agents in financial decision-making.
Approach:	They propose to evaluate LLM agents using 13 different LLMs as backbone models across various market environments and tasks.
Outcome:	The proposed framework assesses the reasoning and decision-making capabilities of 13 different LLMs across various market environments and tasks.

Copied to clipboard

Tarek Mahmoud, Zhuohan Xie, Dimitar Iliyanov Dimitrov, Nikolaos Nikolaidis, Purificação Silvano, Roman Yangarber, Shivam Sharma, Elisa Sartori, Nicolas Stefanovitch, Giovanni Da San Martino, Jakub Piskorski, Preslav Nakov

DeltaScore: Fine-Grained Story Evaluation with Perturbations (2023.findings-emnlp)

Challenge:	a dataset of news articles containing 22 fine-grained characters is annotated for entity framing and role portrayal . the dataset includes 1,378 recent news articles in five languages focusing on the Ukraine-Russia War and climate change .
Approach:	They propose a multilingual and hierarchical corpus annotated for entity framing and role portrayal in news articles.
Outcome:	The proposed dataset includes 1,378 recent news articles in five languages focusing on the Ukraine-Russia War and climate change . the authors report evaluation results on state-of-the-art multilingual transformers and hierarchical zero-shot learning using LLMs at the level of a document, paragraph, and sentence .

Copied to clipboard

Zhuohan Xie, Miao Li, Trevor Cohn, Jey Lau

Challenge:	Existing evaluation metrics for stories are limited in assessing intricate aspects of storytelling, such as fluency and interestingness.
Approach:	They propose a novel method that uses perturbation techniques to evaluate story aspects . they compare fluency, coherence, relatedness, logicality, interestingness and interestingness to existing metrics .
Outcome:	The proposed method shows that one specific perturbation is highly effective in capturing multiple aspects.

Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks (2023.findings-acl)

Copied to clipboard

Xuming Hu, Yong Jiang, Aiwei Liu, Zhongqiang Huang, Pengjun Xie, Fei Huang, Lijie Wen, Philip S. Yu

RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference (2026.acl-long)

Challenge:	Existing augmentation techniques manipulate words in the original text that break the semantic coherence of the text, or exploit generative models that ignore preserving entities in the text.
Approach:	They propose a novel Entity-to-Text based data augmentation technique called EnTDA to add, delete, replace or swap entities in the original text.
Outcome:	The proposed technique generates semantically coherent and entity preserving texts on thirteen NER tasks and two settings.

Copied to clipboard

Siran Liu, Guoxia Wang, Sa Wang, Jinle Zeng, Haoyang Xie, Siyu Lou, Jiabin Yang, Dianhai Yu, Haifeng Wang, Chao Yang

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks (2025.naacl-long)

Challenge:	Existing approaches to dynamic sparse attention require preprocessing, lack global evaluation, violate query independence, or incur high computational overhead.
Approach:	They propose a dynamic sparse attention method that achieves all desirable properties through a head round-robin (RR) sampling strategy.
Outcome:	Experiments on natural language understanding and multimodal video comprehension show that the proposed method achieves 2.4 speedup at 128K context length outperforming existing methods.

Copied to clipboard

Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, Jieping Ye

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Large visionlanguage models (LVLMs) are a powerful visual-language reasoning tool.
Approach:	They propose to integrate attention analysis with LLaVA-CAM to determine interactions between visual representations.
Outcome:	The proposed approach can be used to determine interactions between visual representations.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

LLM-Enhanced Query Generation and Retrieval Preservation for Task-Oriented Dialogue (2025.findings-acl)

Copied to clipboard

Jiale Chen, Xuelian Dong, Wenxiu Xie, Ru Peng, Kun Zeng, Tianyong Hao

COMMA: Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities (2022.coling-1)

Challenge:	Existing knowledge retrieval methods for task-oriented dialogues are limited by data scarcity and lack of data to annotate.
Approach:	They propose an LLM-enhanced model of query-guided knowledge retrieval for task-oriented dialogue . they propose to select the most relevant knowledge from retrieved top-K records and incorporate them as prompts to guide a generator in response generation.
Outcome:	The proposed model outperforms state-of-the-art in three benchmarks on three standard benchmarks.

Copied to clipboard

Yuqiang Xie, Yue Hu, Wei Peng, Guanqun Bi, Luxi Xing

Challenge:	Existing methods for modeling motivations, emotions and actions in language-based human activities have been limited.
Approach:	They propose to model motivations, emotions and actions in language-based human activities using a dataset called Story Commonsense.
Outcome:	The proposed model can better reveal the essential relationship between motivations, emotions and actions than existing methods.

A Simple yet Efficient Prompt Compression Method for Text Classification Data Annotation Using LLM (2025.coling-industry)

Copied to clipboard

Yiran Xie, Debin Xiao, Ping Wang, Shuming Liu

Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination (D18-1)

Challenge:	Existing methods to improve the accuracy of large language models (LLMs) are often impractical due to high costs and time consumption.
Approach:	They propose a method that uses keyword extraction to reduce prompt tokens in text annotation tasks.
Outcome:	The proposed method reduces prompt tokens while maintaining high accuracy.

Copied to clipboard

Jiali Zeng, Jinsong Su, Huating Wen, Yang Liu, Jun Xie, Yongjing Yin, Jianqiang Zhao

Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models (2023.findings-emnlp)

Challenge:	Experimental results on Chinese-English and English-French multi-domain translation tasks demonstrate the effectiveness of the proposed model.
Approach:	They propose to use mixed-domain parallel sentences to construct a unified model that allows translation to switch between different domains.
Outcome:	The proposed model distinguishes and exploits word-level domain contexts on Chinese-English and English-French translation tasks.

Copied to clipboard

Sean Xie, Soroush Vosoughi, Saeed Hassanpour

An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models (2023.acl-long)

Challenge:	Existing methods for interpreting LLMs are post hoc and focus on low-level features and lack of explainability at higher-level text units.
Approach:	They propose a prototypical network-based white-box framework that allows LLMs to learn immediately interpretable embeddings during the fine-tuning stage while maintaining competitive performance.
Outcome:	The proposed framework can learn interpretable embeddings during the fine-tuning stage while maintaining competitive performance.

Copied to clipboard

Zhongbin Xie, Thomas Lukasiewicz

Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers (2024.naacl-short)

Challenge:	Pre-trained language models inherit more human-like biases from the training corpora, causing computationally expensive problems.
Approach:	They propose parameter-efficient methods in combination with counterfactual data augmentation for bias mitigation.
Outcome:	The proposed methods are effective in mitigating gender bias, prompt tuning is more suitable for GPT-2 than BERT, and less effective when it comes to racial and religious bias.

Copied to clipboard

Roy Xie, Orevaoghene Ahia, Yulia Tsvetkov, Antonios Anastasopoulos

ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models (2023.emnlp-demo)

Challenge:	Identifying linguistic differences between dialects of a language often requires expert knowledge and meticulous human analysis.
Approach:	They propose a method to extract distinguishing lexical features of dialects by utilizing interpretable dialect classifiers in the absence of human experts.
Outcome:	The proposed method extracts key language-specific lexical features that contribute to dialectal variations.

Copied to clipboard

Baoli Zhang, Haining Xie, Pengfan Du, Junhao Chen, Pengfei Cao, Yubo Chen, Shengping Liu, Kang Liu, Jun Zhao

CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction (2025.acl-long)

Challenge:	Various types of LLMs have recently been rapidly developing, such as Llama2 and ChatGLM2 .
Approach:	They propose a benchmark that comprehensively evaluates LLMs across 7 ability dimensions covering 51 tasks.
Outcome:	The proposed benchmarks are comprehensive and systematic, with a high level of accuracy and authority.

Copied to clipboard

Jiali Chen, Xusen Hei, HongFei Liu, Yuancheng Wei, Zikun Deng, Jiayuan Xie, Yi Cai, Li Qing

A Joint Learning Framework for Restaurant Survival Prediction and Explanation (2022.emnlp-main)

Challenge:	Computer-aided design (CAD) is crucial in prototyping 3D objects through geometric instructions.
Approach:	They propose a CAD review task to automatically detect and correct potential errors . they propose CAD program repairer framework to provide helpful feedback on error correction .
Outcome:	The proposed framework outperforms existing MLLMs in detecting errors and providing feedback on error correction.

Copied to clipboard

Xin Li, Xiaojie Zhang, Peng JiaHao, Rui Mao, Mingyang Zhou, Xing Xie, Hao Liao

Fusing Highly Specialized Language Models for Comprehensive Expertise (2025.acl-long)

Challenge:	Recent advances in deep learning have various models that research reviews and interactions for different kinds of tasks, such as predicting restaurant survival.
Approach:	They propose a joint learning framework for explainable restaurant survival prediction based on multi-modal data of user-restaurant interactions and users’ textual reviews.
Outcome:	The proposed framework improves on two datasets showing that it can model restaurant interactions and users’ textual reviews.

Copied to clipboard

Ning Ding, Yulin Chen, Ganqu Cui, Xingtai Lv, Weilin Zhao, Kaiyan Zhang, Ruobing Xie, Bowen Zhou, Zhiyuan Liu, Maosong Sun

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking (2025.emnlp-main)

Challenge:	Existing models that focus on language, programming code, and mathematical symbols are not able to achieve mastery of all three domains simultaneously.
Approach:	They propose to fuse highly-specialized models that are already sufficiently trained on different domains to achieve a highly-specific model.
Outcome:	The proposed model could achieve mastery of the three crucial domains simultaneously.

Copied to clipboard

Zekun Xi, Wenbiao Yin, Jizhan Fang, Jialong Wu, Runnan Fang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning (2025.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in machine writing such as open domain long-form generation.
Approach:	They propose a slow-thinking machine writing framework that emulates the human-like process of iterative expansion and reflection to improve the knowledge density of generated articles.
Outcome:	The proposed framework improves the knowledge density of generated articles without compromising metrics such as coherence and depth.

Copied to clipboard

Zexiong Ma, Chao Peng, Pengfei Gao, Xiangxin Meng, Yanzhen Zou, Bing Xie

GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking (2025.acl-long)

Challenge:	Existing issue-resolving frameworks rely on commercial models, leading to high costs and privacy concerns.
Approach:	They propose a training approach to enhance issue resolving capability of LLMs by decomposing issue reasolving into subtasks.
Outcome:	The proposed approach improves issue-resolving performance and generalizes model . it is cost-effective and provides a cost-efficient alternative to commercial models .

Copied to clipboard

Yingjian Chen, Haoran Liu, Yinhong Liu, Jinxiang Xie, Rui Yang, Han Yuan, Yanran Fu, Peng Yuan Zhou, Qingyu Chen, James Caverlee, Irene Li

A Two-Stage Adaptation of Large Language Models for Text Ranking (2024.findings-acl)

Challenge:	Existing fact-checking methods that use large language models often generate subtle factual errors.
Approach:	They propose a fact-checking framework that uses extracted knowledge graphs to enhance text representation.
Outcome:	GraphCheck outperforms existing specialized fact-checkers on seven benchmarks spanning general and medical domains . Graph Neural Networks process extracted knowledge graphs as a soft prompt, enabling efficient fact- checking in a single inference call.

Copied to clipboard

Longhui Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Meishan Zhang, Min Zhang

A Multi-Task Learning Framework for Extracting Bacteria Biotope Information (D19-57)

Challenge:	Recent advances in pre-trained language models (PLMs) have significantly improved ranking performance in text ranking tasks.
Approach:	They propose a two-stage progressive paradigm to better adapt LLMs to text ranking by conducting continual pre-training on a large weakly-supervised corpus and performing SFT on high-quality data.
Outcome:	The proposed approach outperforms previous methods on in- and out-domain scenarios.

Copied to clipboard

Qi Zhang, Chao Liu, Ying Chi, Xuansong Xie, Xiansheng Hua

Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning (2026.acl-long)

Challenge:	Existing methods to extract information from unstructured text are slow or expensive to get.
Approach:	They propose a multi-task transfer multi-learning method for Bacteria Biotope rel+ner task . they use BERT and pre-train it using mask language models and next sentence prediction .
Outcome:	The proposed method achieves the best performance on all metrics including slot error rate, precision and recall in the Bacteria Biotope rel+ner subtask.

Copied to clipboard

Xin Guan, Zijian Li, Shen Huang, Pengjun Xie, Jingren Zhou, Jiuxin Cao

Emergent Modularity in Pre-trained Transformers (2023.findings-acl)

Challenge:	Evidence-Augmented Policy Optimization (EAPO) improves long-context reasoning performance . Xu et al., 2025): large language models are a critical part of NLP .
Approach:	They propose an Evidence-Augmented Reasoning paradigm that uses a group-relative reward to improve evidence quality.
Outcome:	EAPO significantly improves long-context reasoning performance compared to baselines.

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Chaojun Xiao, Xiaozhi Wang, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou

Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks (2022.coling-1)

Challenge:	Existing studies on pre-trained Transformers show that they learn fine-grained neuron functions.
Approach:	They examine the presence of modularity in pre-trained Transformers . they focus on Mixture-of-Experts, a promising candidate for modularity .
Outcome:	The proposed structure stabilizes at the early stage, which is faster than neuron stabilization.

Copied to clipboard

Xin Zhou, Ruotian Ma, Yicheng Zou, Xuanting Chen, Tao Gui, Qi Zhang, Xuanjing Huang, Rui Xie, Wei Wu

Gradient Inversion Attack in Federated Learning: Exposing Text Data through Discrete Optimization (2025.coling-main)

Challenge:	Large pre-trained language models (PLMs) have demonstrated superior performance in industrial applications.
Approach:	They propose a framework that re-uses existing parameter-efficient methods with a unified classifier.
Outcome:	The proposed framework improves the efficiency of existing parameter-efficient methods with a unified classifier.

Copied to clipboard

Ying Gao, Yuxin Xie, Huanghao Deng, Zukun Zhu

KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan (2025.acl-long)

Challenge:	federated learning could overcome the bottleneck of public text data in large language models . a novel attack method is proposed to fully expose text data from gradients .
Approach:	They propose a method to fully expose text data from gradients by using a network of clients and a server.
Outcome:	The proposed method shows it is possible to Fully Expose Text data from gradients.

Copied to clipboard

Mukhammed Togmanov, Nurdaulet Mukhituly, Diana Turmakhan, Jonibek Mansurov, Maiya Goloburda, Akhmed Sakip, Zhuohan Xie, Yuxia Wang, Bekassyl Syzdykov, Nurkhan Laiyk, Alham Fikri Aji, Ekaterina Kochmar, Preslav Nakov, Fajri Koto

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)

Challenge:	Kazakh language remains underrepresented in the field of natural language processing despite the country's population exceeding twenty million . however, there is a lack of dedicated models and benchmark evaluations specifically tailored to Kazakh languages.
Approach:	They propose to create a dataset specifically designed for Kazakh language with 23,000 questions sourced from authentic educational materials and manually validated by native speakers and educators.
Outcome:	The first MMLU-style dataset specifically designed for Kazakh language.

Copied to clipboard

Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu

Exploring the Secrets Behind the Learning Difficulty of Meaning Representations for Semantic Parsing (2022.emnlp-main)

Challenge:	Existing solutions for visual document understanding lack granularity of document textlines.
Approach:	They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts.
Outcome:	The proposed system performs better on various VDU tasks in English and Chinese.

Copied to clipboard

Zhenwen Li, Jiaqi Guo, Qian Liu, Jian-Guang Lou, Tao Xie

Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization (2023.findings-acl)

Challenge:	Existing studies show that the design of Meaning Representation (MR) greatly influences the final model performance of a neural semantic parser.
Approach:	They propose a data-aware metric called ISS to measure the final performance of MRs.
Outcome:	The proposed metric denoting incremental structural stability (ISS) of MRs can be used as an indicator for MR design to avoid the costly training-testing process.

Copied to clipboard

Jiawen Xie, Qi Su, Shaoting Zhang, Xiaofan Zhang

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models (2026.findings-acl)

Challenge:	Abstractive summarization systems have a severe mismatch between training and inference, i.e., exposure bias.
Approach:	They propose a multi-level contrastive learning framework for abstractive summarization and a tailored sparse decoder self-attention pattern to bridge the gap between training and inference.
Outcome:	The proposed framework outperforms the state-of-the-art models on two summarization datasets while adding relatively low overhead.

Copied to clipboard

Jinsong Shu, Chenyang Wu, Zhongle Xie, Baokun Wang, Lidan Shou

Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark (2023.acl-long)

Challenge:	Recent work suggests a prefill-stage KV cache selection method to estimate KV importance from prefilling statistics.
Approach:	They propose a training-free, decode-aware and strictly prefill-only KV selection method that retains key-value caching for decoding .
Outcome:	The proposed method outperforms existing methods under tight cache budgets on multimodal benchmarks.

Copied to clipboard

Wenjun Peng, Jingwei Yi, Fangzhao Wu, Shangxi Wu, Bin Bin Zhu, Lingjuan Lyu, Binxing Jiao, Tong Xu, Guangzhong Sun, Xing Xie

Multi-Granularity Contrasting for Cross-Lingual Pre-Training (2021.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated exceptional abilities in both text understanding and generation.
Approach:	They propose an Embedding Watermark method that implants backdoors on embeddings to protect copyright of large language models.
Outcome:	The proposed method protects the copyright of large language models without compromising service quality while minimizing the adverse impact on the original embeddings’ utility.

Copied to clipboard

Shicheng Li, Pengcheng Yang, Fuli Luo, Jun Xie

Scalable-DSC: A Structural Template Prompt Approach to Scalable Dialogue State Correction (2023.emnlp-main)

Challenge:	Existing approaches to pre-training focus on embedding alignment, but they neglect the modeling of bidirectional contexts.
Approach:	They propose a framework to learn languageuniversal representations using multi-granularity contrasting framework . they encode semantic equivalents from different languages into similar representations .
Outcome:	The proposed framework can achieve significant performance gains in machine translation and cross-lingual language understanding.

Copied to clipboard

Haoxiang Su, Hongyan Xie, Hao Huang, Shuangyong Song, Ruiyu Fang, Xiaomeng Huang, Sijie Feng

A Reinforced Generation of Adversarial Examples for Neural Machine Translation (2020.acl-main)

Challenge:	Existing approaches to correct wrong slot values in dialogue state tracking are intertwined with specific DST models, limiting their applicability to other DSTs.
Approach:	They propose a Scalable Dialogue State Correction model that corrects wrong slot values in predicted dialogue states by using a structural template prompt.
Outcome:	The proposed model achieves state-of-the-art results on MultiWOZ 2.0-2.4.

Copied to clipboard

Wei Zou, Shujian Huang, Jun Xie, Xinyu Dai, Jiajun Chen

A Multi-Level Optimization Framework for End-to-End Text Augmentation (2022.tacl-1)

Challenge:	Neural machine translation systems fail on less decent inputs, which may harm the credibility of these systems.
Approach:	They propose a paradigm that generates adversarial examples using reinforcement learning to expose pitfalls for a given performance metric.
Outcome:	The proposed paradigm produces stable attacks with meaning-preserving adversarial examples.

Copied to clipboard

Sai Ashish Somayajula, Linfeng Song, Pengtao Xie

Industry Scale Semi-Supervised Learning for Natural Language Understanding (2021.naacl-industry)

Challenge:	Existing methods for text augmentation perform data augmentation and downstream tasks separately.
Approach:	They propose a framework to perform text augmentation and the downstream task end-to-end.
Outcome:	The proposed framework performs text augmentation and the downstream task end-to-end on a text classification dataset.

Copied to clipboard

Luoxin Chen, Francisco Garcia, Varun Kumar, He Xie, Jianhua Lu

Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting (2023.findings-emnlp)

Challenge:	Obtaining human annotation is expensive and time-consuming process.
Approach:	They propose a semi-supervised learning pipeline which leverages millions of unlabeled examples to improve natural language understanding tasks.
Outcome:	The proposed pipeline can be used to improve natural language understanding tasks.

Copied to clipboard

Ke Wang, Jun Xie, Yuqi Zhang, Yu Zhao

Knowledge Boundary of Large Language Models: A Survey (2025.acl-long)

Challenge:	Existing methods focus on how to integrate multiple types of knowledge into NMT models .
Approach:	They propose a framework that integrates multiple types of knowledge into NMT models . they use multiple types as prefix-prompts of input for the encoder and decoder .
Outcome:	The proposed framework outperforms baselines on English-Chinese and English-German translation.

Copied to clipboard

Moxin Li, Yong Zhao, Wenxuan Zhang, Shuaiyi Li, Wenya Xie, See-Kiong Ng, Tat-Seng Chua, Yang Deng

Tree-Structured Topic Modeling with Nonparametric Neural Variational Inference (2021.acl-long)

Challenge:	Large language models (LLMs) store vast amount of knowledge in their parameters, but they still have limitations in the memorization and utilization of certain knowledge.
Approach:	They propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types.
Outcome:	The proposed definition of the LLM knowledge boundary and taxonomy categorizes knowledge into four distinct types . aims to offer a comprehensive overview, facilitate access to key issues, and inspire further advancements in LLM research.

Copied to clipboard

Ziye Chen, Cheng Ding, Zusheng Zhang, Yanghui Rao, Haoran Xie

Density-Aware Prototypical Network for Few-Shot Relation Classification (2023.findings-emnlp)

Challenge:	Existing methods for topic modeling learn topics with a flat structure . however, such methods have data scalability issues .
Approach:	They propose to use nonparametric neural variational inference to extract a tree-structured topic model with reasonable structure, low redundancy, and adaptable widths.
Outcome:	The proposed model extracts a tree-structured topic hierarchy with reasonable structure, low redundancy, and adaptable widths.

Copied to clipboard

Jianfeng Wu, Mengting Hu, Yike Wu, Bingzhe Wu, Yalan Xie, Mingming Liu, Renhong Cheng

RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning (2025.findings-acl)

Challenge:	Existing studies treat NOTA as an extra class and treat it the same as known relations.
Approach:	They propose a density-aware prototypical network to treat various instances distinctly . they separate known instances and isolate NOTA instances, respectively . their code will be made public after the paper is accepted .
Outcome:	The proposed method outperforms strong baselines with robustness towards different NOTA rates.

Copied to clipboard

Junhao Hu, Wenrui Huang, Weidong Wang, Zhenwen Li, Tiancheng Hu, Zhixia Liu, Xusheng Chen, Tao Xie, Yizhou Shan

Attention and Edge-Label Guided Graph Convolutional Networks for Named Entity Recognition (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated strong capabilities across various domains, but their large-scale deployment faces a major obstacle: the high computational cost of long-sequence inference.
Approach:	They propose an algorithm that retains key-value vectors until they are no longer needed to solve reasoning tasks.
Outcome:	The proposed algorithm achieves high accuracy with O(L) time but O(N) memory complexities.

Copied to clipboard

Renjie Zhou, Zhongyi Xie, Jian Wan, Jilin Zhang, Yong Liao, Qiang Liu

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge (2025.acl-long)

Challenge:	Named entity recognition (NER) is the recognition of entities with specific meanings in the text, mainly including person, organization, location, etc.
Approach:	They propose an edge-aware node joint update module and introduce a node-awful edge update module to explore hidden in structured information and solve the wrong dependency label information to some extent.
Outcome:	The proposed model can exploit the structured information on the dependency tree to improve the recognition of long entities.

Copied to clipboard

Xiaobao Wu, Liangming Pan, Yuxi Xie, Ruiwen Zhou, Shuai Zhao, Yubo Ma, Mingzhe Du, Rui Mao, Anh Tuan Luu, William Yang Wang

User-Assistant Bias in LLMs (2026.findings-acl)

Challenge:	Existing studies solve this challenge by updating benchmarks with newly collected data, but they fail to guarantee contamination-free evaluation as the newly collected knowledge may contain pre-existing knowledge.
Approach:	They propose an automated anti-leakage benchmarking framework that builds and updates benchmarks without human labor instead of using newly collected data.
Outcome:	The proposed framework significantly reduces the cost of benchmark maintenance to accommodate emerging LLMs.

Copied to clipboard

Xu Pan, Jingxuan Fan, Zidi Xiong, Ely Hahami, Jorin Overwiening, Ziqian Xie

Effect Generation Based on Causal Reasoning (2021.findings-emnlp)

Challenge:	Modern large language models are typically trained using structured role tags . asymmetries in training data associated with different role tags can potentially introduce inductive biases.
Approach:	They propose a task-agnostic benchmark to test user–assistant bias in large language models . they find human-preference alignment amplifies user bias, reasoning fine-tuning reduces it .
Outcome:	The proposed benchmark tests show that most instruction-tuned models exhibit strong user bias . human-preference alignment amplifies user bias, while reasoning fine-tuning reduces it.

Copied to clipboard

Feiteng Mu, Wenjie Li, Zhipeng Xie

Prompt Optimization via Adversarial In-Context Learning (2024.acl-long)

Challenge:	Existing methods for reasoning causalities on word level are limited . a word-level causal reasoning method may only predict the unintelligible effect of "quarrel"
Approach:	They propose a novel event-level causal reasoning method that structuralizes event-effect event pairs into an event causality network and shows its use in the task of effect generation.
Outcome:	The proposed method generates more reasonable effect sentences than well-designed competitors.

Copied to clipboard

Do Long, Yiran Zhao, Hannah Brown, Yuxi Xie, James Zhao, Nancy Chen, Kenji Kawaguchi, Michael Shieh, Junxian He

A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs (2025.emnlp-main)

Challenge:	Existing methods to optimize prompts for in-context learning are based on adversarial learning and are computationally efficient and extensible to other LLMs and tasks.
Approach:	They propose a method to optimize prompts for in-context learning by a generator and a discriminator.
Outcome:	The proposed method improves state-of-the-art prompt optimization techniques on 13 generation and classification tasks including summarization, arithmetic reasoning, machine translation, data-to-text generation, and the MMLU and big-bench hard benchmarks.

Copied to clipboard

Artem Shelmanov, Ekaterina Fadeeva, Akim Tsvigun, Ivan Tsvigun, Zhuohan Xie, Igor Kiselev, Nico Daheim, Caiqi Zhang, Artem Vazhentsev, Mrinmaya Sachan, Preslav Nakov, Timothy Baldwin

Neural Mixed Counting Models for Dispersed Topic Discovery (2020.acl-main)

Challenge:	Uncertainty quantification (UQ) is a framework for assessing the reliability of model outputs.
Approach:	They introduce pre-trained UQ heads for LLMs that are highly robust and generalized to languages they were not explicitly trained on.
Outcome:	The pre-trained heads significantly improve their ability to capture uncertainty compared to unsupervised methods.

Copied to clipboard

Jiemin Wu, Yanghui Rao, Zusheng Zhang, Haoran Xie, Qing Li, Fu Lee Wang, Ziye Chen

Unsupervised Preference-Aware Language Identification (2022.findings-acl)

Challenge:	Existing methods for inference of parameter parameters are time-consuming and difficult to use.
Approach:	They propose two efficient neural mixed counting models that use the negative binomial distribution as the prior for dispersed topic discovery.
Outcome:	The proposed models outperform state-of-the-art models in terms of perplexity and topic coherence on real-world datasets.

Copied to clipboard

Xingzhang Ren, Baosong Yang, Dayiheng Liu, Haibo Zhang, Xiaoyu Lv, Liang Yao, Jun Xie

ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition (2026.findings-acl)

Challenge:	Existing studies do not consider inter-personal variations due to the lack of user annotated training data.
Approach:	They propose to use user preferences to identify ambiguous texts in multilingual applications without user annotated training data to build a preference-aware LID model.
Outcome:	The proposed model significantly outperforms existing LID systems on handling ambiguous texts.

Copied to clipboard

Yujie Liu, Zonglin Yang, Tong Xie, Jinjie Ni, Ben Gao, Yuqiang Li, Shixiang Tang, Wanli Ouyang, Erik Cambria, Dongzhan Zhou

Exploring Sequence-to-Sequence Learning in Aspect Term Extraction (P19-1)

Challenge:	Large language models have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined due to the lack of a dedicated benchmark.
Approach:	They propose a benchmark for evaluating large language models on a sufficient set of scientific discovery sub-tasks.
Outcome:	The proposed framework extracts critical components from papers across 12 disciplines with expert validation confirming its accuracy.

Copied to clipboard

Dehong Ma, Sujian Li, Fangzhao Wu, Xing Xie, Houfeng Wang

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition (2021.acl-short)

Challenge:	Aspect term extraction (ATE) aims at identifying all aspect terms in a sentence . sequence labeling based methods cannot make full use of overall meaning of sentence if they have dependencies between labels.
Approach:	They propose to formalize ATE as a sequence-to-sequence (Seq2Seque) learning task . they propose gated unit networks and position-aware attention mechanism to make it suit to ATE .
Outcome:	The proposed learning task is effective when labels correspond to words one by one . the proposed learning system is gated unit networks and position-aware attention mechanism .

Copied to clipboard

Yubo Xie, Junze Li, Pearl Pu

FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering (2026.findings-acl)

Challenge:	Existing work on humor recognition does not examine the actual joke mechanism . a recent study focused on humor-specific stylistic features, but few have tried to establish a connection between them and humor theories.
Approach:	They propose to model the set-up and punchline as part developing semantic uncertainty and disrupt audience expectations.
Outcome:	The proposed features can tell jokes from non-jokes, compared with baselines.

Copied to clipboard

Yixi Zhou, Fan Zhang, YU Chen, Haipeng Zhang, Preslav Nakov, Zhuohan Xie

Question Answering

Challenge:	Existing reranking frameworks optimize semantic relevance, leading to unstable rankings and opaque decisions on long documents.
Approach:	They propose a structured reranking framework that reframes financial evidence selection as constraint satisfaction under a finance-aware schema.
Outcome:	FINCARDS improves early-rank retrieval over lexical and LLM-based reranking baselines while reducing ranking variance.

Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models (2024.eacl-long)

Copied to clipboard

Zhuowan Li, Cihang Xie, Benjamin Van Durme, Alan Yuille

Leveraging Bidding Graphs for Advertiser-Aware Relevance Modeling in Sponsored Search (2021.findings-emnlp)

Challenge:	Existing vision-and-language models perform better on multimodal tasks, but there is little understanding of how multimodal learning can help visual representations.
Approach:	They conduct a probing analysis of visual representations in existing vision-and-language models and vision-only models by probing on a broad range of tasks.
Outcome:	The proposed model improves vision-and-language models on label and attribute prediction tasks while vision-only models are stronger on dense prediction tasks.

Copied to clipboard

Shuxian Bi, Chaozhuo Li, Xiao Han, Zheng Liu, Xing Xie, Haizhen Huang, Zengxuan Wen

Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning (2026.findings-acl)

Challenge:	Existing relevance models rely on query-keyword pairs but keywords are usually short texts with scarce semantic information, which may not accurately reflect the underlying advertising purposes.
Approach:	They propose a bidding-graph augmented triple-based relevance model with three towers to deeply fuse the bidding graphs and semantic textual data.
Outcome:	The proposed model outperforms existing models on a large industry dataset and consistently outperformed existing models.

Copied to clipboard

Jie Deng, Hanshuang Tong, Jun Li, Shining Liang, Ning Wu, Hongzhi Li, Yutao Xie

When to Trust LLMs: Aligning Confidence with Response Quality (2024.findings-acl)

Challenge:	Large language models (LLMs) fine-tuned using rejection sampling retain only correct reasoning trajectories . however, this paradigm treats supervision as a binary filter that systematically excludes teacher-generated errors, leaving a gap in how reasoning failures are modeled during training.
Approach:	They propose a fine-tuning strategy that reframes rejection sampling as a structured supervision construction process.
Outcome:	The proposed approach outperforms RFT on multiple math benchmarks while retaining only correct reasoning trajectories.

Copied to clipboard

Shuchang Tao, Liuyi Yao, Hanxing Ding, Yuexiang Xie, Qi Cao, Fei Sun, Jinyang Gao, Huawei Shen, Bolin Ding

Challenge:	Existing methods express reliability by confidence level, but lack objective guidance . Existing approaches express reliability but lack guidance on when to trust LLMs .
Approach:	They propose a reward-based approach to align confidence with quality to ensure reliability . they propose 'conqORD' to help model to verbalize greater confidence for higher quality responses .
Outcome:	Experiments show that CONQORD significantly improves confidence and response accuracy . the proposed approach can be used to determine reliability of large language models .

Multi-task Learning for Paraphrase Generation With Keyword and Part-of-Speech Reconstruction (2022.findings-acl)

Copied to clipboard

Xuhang Xie, Xuesong Lu, Bei Chen

Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering (2023.acl-long)

Challenge:	PGKPR is a deep learning approach to generate paraphrases using key semantics of the source sentence.
Approach:	They propose a model with keyword and part-of-speech reconstruction for paraphrase generation using deep learning.
Outcome:	The proposed model outperforms comparative models on two commonly-used datasets.

Copied to clipboard

Hai Ye, Qizhe Xie, Hwee Tou Ng

Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation (2025.acl-demo)

Challenge:	Recent research on test-time adaptation suggests a possible way to improve the generalization ability of LLMs.
Approach:	They propose to use multi-armed bandit learning and multi-arm dueling bandits to solve a multi-source test-time model adaptation problem from user feedback.
Outcome:	The proposed model is more effective than other strong baselines on extractive question answering datasets.

Copied to clipboard

Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Yang Ou, Scarlett Li, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, James Evans, Xing Xie

Challenge:	Current evaluation methods for large language models face two key challenges: 1. evaluation validity and 2. Result interpretation reduce the pluralistic and incommensurable values to one-dimensional scores.
Approach:	They propose a platform for comprehensive value diagnosis of large language models (LLMs) that provides a generative evaluation paradigm that automatically creates real-world test items co-evolving with ever-advancing LLMs.
Outcome:	The proposed platform provides a framework for comprehensive value diagnosis of large language models (LLMs) with fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, customized comparisons, and visualized analysis of LLM’s alignment with cultural values.

Hierarchy-Aware Global Model for Hierarchical Text Classification (2020.acl-main)

Copied to clipboard

Jie Zhou, Chunping Ma, Dingkun Long, Guangwei Xu, Ning Ding, Haoyu Zhang, Pengjun Xie, Gongshen Liu

Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI (2026.acl-long)

Challenge:	Existing methods for hierarchical text classification are limited and lack holistic structural information.
Approach:	They propose a hierarchy-aware global model with two variants that learn hierarchy-based label embeddings through an encoder and conduct inductive fusion of label-alike text features.
Outcome:	The proposed model improves on three benchmark datasets.

Copied to clipboard

Yuxia Wang, Rui Xing, Jonibek Mansurov, Giovanni Puccetti, Zhuohan Xie, Minh Ngoc Ta, Jiahui Geng, Jinyan Su, Mervat Abassy, Saadeldine Eletter, Kareem Elozeiri, Nurkhan Laiyk, Maiya Goloburda, Tarek Mahmoud, Raj Vardhan Tomar, Alexander Aziz, Ryuto Koike, Masahiro Kaneko, Artem Shelmanov, Ekaterina Artemova, Vladislav Mikhailov, Akim Tsvigun, Alham Fikri Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov

Revisiting the Negative Data of Distantly Supervised Relation Extraction (2021.acl-long)

Challenge:	Prior studies have shown that distinguishing text generated by Large Language Models from human-written text is challenging for humans and often no better than random guessing.
Approach:	They conduct extensive case study to determine the upper bound of human detection accuracy.
Outcome:	The findings challenge previous conclusions on human detection accuracy across languages and domains.

Copied to clipboard

Chenhao Xie, Jiaqing Liang, Jingping Liu, Chengsong Huang, Wenhao Huang, Yanghua Xiao

DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population (2022.emnlp-demos)

Challenge:	Existing methods for relation extraction with distant supervision generate plenty of training samples but noisy labels and imbalanced training data cause problems.
Approach:	They propose a method that automatically labels a sentence with relational triples from a knowledge base.
Outcome:	The proposed method outperforms existing methods even with false positive samples.

Copied to clipboard

Ningyu Zhang, Xin Xu, Liankuan Tao, Haiyang Yu, Hongbin Ye, Shuofei Qiao, Xin Xie, Xiang Chen, Zhoubo Li, Lei Li

LLM-DetectAIve: a Tool for Fine-Grained Machine-Generated Text Detection (2024.emnlp-demo)

Challenge:	Existing knowledge extraction tools are not complete due to emerging entities and relations in real-world applications.
Approach:	They propose an open-source knowledge extraction toolkit DeepKE that supports low-resource, document-level and multimodal scenarios in the knowledge base population.
Outcome:	The proposed toolkit supports low-resource, document-level and multimodal scenarios in the knowledge base population.

Copied to clipboard

Mervat Abassy, Kareem Elozeiri, Alexander Aziz, Minh Ta, Raj Tomar, Bimarsha Adhikari, Saad Ahmed, Yuxia Wang, Osama Mohammed Afzal, Zhuohan Xie, Jonibek Mansurov, Ekaterina Artemova, Vladislav Mikhailov, Rui Xing, Jiahui Geng, Hasan Iqbal, Zain Mujahid, Tarek Mahmoud, Akim Tsvigun, Alham Aji, Artem Shelmanov, Nizar Habash, Iryna Gurevych, Preslav Nakov

Challenge:	a large number of machine-generated texts are often hard to distinguish between human-written and machine-generated text . this raises concerns about potential misuse, especially within educational and academic domains .
Approach:	They propose a system that can detect whether a text is human-written or machine-generated . they use a fine-grained classification schema to identify the use of machine-generated text .
Outcome:	The proposed system can distinguish between human-written and machine-generated text . it can detect attempts to obfuscate the fact that a text was machine- generated .

Dagger Behind Smile: Fool LLMs with a Happy Ending Story (2025.findings-emnlp)

Copied to clipboard

Xurui Song, Zhixin Xie, Shuo Huai, Jiayi Kong, Jun Luo

Incorporating Chinese Characters of Words for Lexical Sememe Prediction (P18-1)

Challenge:	Large Language Models (LLMs) have attracted significant attention from jailbreak attacks . existing manual designs are either easily detectable or require intricate interactions with LLMs.
Approach:	They propose a happy ending attack that wraps up a malicious request in a scenario template .
Outcome:	The proposed attack wraps up a malicious request in a scenario template involving a positive prompt formed mainly via a happy ending, fooling LLMs into jailbreaking either immediately or at a follow-up malicious request.

Copied to clipboard

Huiming Jin, Hao Zhu, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin

EchoSight: Advancing Visual-Language Models with Wiki Knowledge (2024.findings-emnlp)

Challenge:	Existing methods of lexical sememe prediction rely on external context information of words to represent meaning.
Approach:	They propose a character-enhanced sememe prediction framework for Chinese language that takes advantage of internal character information and external context information.
Outcome:	The proposed framework outperforms state-of-the-art methods on a Chinese sememe knowledge base and maintains robust performance even for low-frequency words.

Copied to clipboard

Yibin Yan, Weidi Xie

BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting (2023.acl-industry)

Challenge:	Existing knowledge-based visual question answering systems struggle with these tasks due to limited integration of external knowledge.
Approach:	They propose a framework that enables large language models to answer visual questions requiring encyclopedic knowledge.
Outcome:	The proposed framework improves retrieval outcomes and accuracy of knowledge-based visual question answering tasks.

Copied to clipboard

Wei Zhu, Peng Wang, Yuan Ni, Guotong Xie, Xiaoling Wang

Exploring the Impact of Model Scaling on Parameter-Efficient Tuning (2023.emnlp-main)

Challenge:	Recent years have witnessed the rise of many pre-trained language models (PLMs) such as GPT (Radford et al., 2019) and XLNet (Yang e.t al, 2019).
Approach:	They propose a framework which consists of two off-the-shelf methods for improving PLMs’ early exiting.
Outcome:	The proposed method can reduce the average latency of pre-trained language models and work with other inference speed-up methods like model pruning.

Copied to clipboard

Yusheng Su, Chi-Min Chan, Jiali Cheng, Yujia Qin, Yankai Lin, Shengding Hu, Zonghan Yang, Ning Ding, Xingzhi Sun, Guotong Xie, Zhiyuan Liu, Maosong Sun

Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking (2025.acl-long)

Challenge:	Parameter-efficient tuning (PET) methods can drive large pre-trained language models by training only minimal parameters.
Approach:	They propose a parameter-efficient tuning method that is compatible with a tunable module and uses a random number generator to optimize fewer table parameters.
Outcome:	The proposed method is compatible with a tunable module and tested on 11 NLP tasks.

Copied to clipboard

Yilong Chen, Junyuan Shang, Zhenyu Zhang, Yanxi Xie, Jiawei Sheng, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang

Language Adaptation of Large Language Models: An Empirical Study on LLaMA2 (2025.coling-main)

Challenge:	Large language models face inherent performance bottlenecks under parameter constraints . challenging tokens induce abrupt gradient spikes across layers, exposing stress points .
Approach:	They propose an inner thinking transformer that reimagines layer computations as implicit thinking steps.
Outcome:	Empirical results show that ITT outperforms Transformer/Loop variants in 11 benchmarks.

Copied to clipboard

Shumin Wang, Yuexiang Xie, Bolin Ding, Jinyang Gao, Yanyong Zhang

GR1: Reinforcement-Enhanced LLM for Geoscience Reasoning (2026.findings-acl)

Challenge:	Popularity of Large Language Models (LLMs) has seen a skyrocketing increase in recent years.
Approach:	They present a systematic review of the language adaptation process for Large Language Models including vocabulary expansion, continued pre-training, and instruction fine-tuning.
Outcome:	The proposed model is based on empirical studies conducted on LLaMA2 and discussions on various settings affecting the model's capabilities.

Copied to clipboard

Yule Xie, Jiaxin Ding, Cheng Deng, Shiqing Gao, Junran Zhang, Sibo Zhang, Zeyuan Wang, Ke Wu, Xin Ding, Luoyi Fu, Meng Jin, Xinbing Wang

DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation (2023.acl-long)

Challenge:	Recent advances in large language models have demonstrated RL's substantial capacity to enhance multi-step reasoning beyond what supervised instruction tuning achieves.
Approach:	They propose a framework that converts multimodal questions into descriptive text . they propose RL-enhanced geoscience reasoning that can be fine-tuned to a text-only level .
Outcome:	The proposed framework improves accuracy and accuracy on multimodal questions while preserving answerability and difficulty.

Copied to clipboard

Yuxi Feng, Xiaoyuan Yi, Xiting Wang, Laks Lakshmanan, V.S., Xing Xie

Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization (2024.lrec-main)

Challenge:	Existing approaches to augment self-training (ST) in attribute-controllable language generation are limited and limited.
Approach:	They propose a new ST framework that integrates self-generated pseudo text into attribute-controllable language generation.
Outcome:	The proposed framework can be applied to semi-supervised controllable language generation.

Copied to clipboard

Linzhi Wu, Xingyu Zhang, Yakun Zhang, Changyan Zheng, Tiejun Liu, Liang Xie, Ye Yan, Erwei Yin

Connecting Embeddings for Knowledge Graph Entity Typing (2020.acl-main)

Challenge:	Lip reading is a process of interpreting silent speech from visual lip movements . but lip reading in cross-speaker scenarios poses a challenging problem due to inter-speech variability .
Approach:	They propose to exploit lip landmark-guided visual clues instead of mouth-cropped images as input features.
Outcome:	Experimental results show that the proposed approach reduces speaker-specific appearance characteristics in cross-speaker scenarios.

Copied to clipboard

Yu Zhao, Anxiang Zhang, Ruobing Xie, Kang Liu, Xiaojie Wang

Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? (2020.findings-emnlp)

Challenge:	Existing knowledge graphs suffer from incompleteness and miss important facts, jeopardizing their usefulness in downstream tasks such as question answering.
Approach:	They propose a method which is trained by utilizing local typing knowledge from existing entity type assertions and global triple knowledge in KGs.
Outcome:	The proposed model favors inferences that agree with both entity type instances and triple knowledge in KGs.

Copied to clipboard

Peter Hase, Shiyue Zhang, Harry Xie, Mohit Bansal

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics (2026.findings-acl)

Challenge:	Existing models that generate NL explanations for tasks have been evaluated on the basis of surface-level similarities to human explanations, both through automatic metrics like BLEU and human evaluations.
Approach:	They propose to use a model as a proxy for a human observer to evaluate NL explanations from the model simulatability perspective.
Outcome:	The proposed model-generated explanations are evaluated on the basis of surface-level similarities to human explanations, both through automatic metrics like BLEU and human evaluations.

Copied to clipboard

Jinxiang Xie, Zihao Li, Wei He, Rui Ding, Shi Han, Dongmei Zhang

LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech (2026.acl-long)

Challenge:	Text analysis of tabular data relies on two core operations: summarization for corpus-level theme extraction and tagging for row-level labeling.
Approach:	They propose a framework that enhances output stability by constraining the model’s latent reasoning trajectory.
Outcome:	The proposed framework improves stability by constraining the model's latent reasoning trajectory.

Copied to clipboard

Bingshen Mu, Xian Shi, Xiong Wang, Hexin Liu, Jin Xu, Lei Xie

CGIM: A Cycle Guided Interactive Learning Model for Consistency Identification in Task-oriented Dialogue (2022.coling-1)

Challenge:	Existing methods for forcing alignment are language-specific and prone to temporal shifts.
Approach:	They propose a slot-filling paradigm that uses time indices to predict slot positions.
Outcome:	The proposed method reduces accumulated temporal shifts by 69% compared with prior methods.

Copied to clipboard

Libo Qin, Qiguang Chen, Tianbao Xie, Qian Liu, Shijue Huang, Wanxiang Che, Zhou Yu

MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models (2026.acl-long)

Challenge:	Consistency identification in task-oriented dialog usually consists of three subtasks . a proposed model for consistency identification in dialog is based on an explicit interaction paradigm .
Approach:	They propose a cycle guided interactive learning model that makes information exchange explicit from all the three tasks.
Outcome:	The proposed model achieves state-of-the-art performance pushing the overall score to 56.3% (5.0% point absolute improvement)

Copied to clipboard

Yang Shi, Yifeng Xie, Minzhe Guo, Liangsi Lu, Mingxuan Huang, Jingchao Wang, Zhihong Zhu, Boyan Xu, Zhiqi Huang

Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents (2025.findings-emnlp)

Challenge:	Recent advances in vision-language models have improved performance in multi-modal learning.
Approach:	They propose a multi-modal benchmark that embeds a single coherent reasoning error in 1997 samples.
Outcome:	The proposed benchmark is based on a set of 1997 samples embedding a single coherent reasoning error.

Copied to clipboard

Tianmi Ma, Jiawei Du, Wenxin Huang, Wenjie Wang, Liang Xie, Xian Zhong, Joey Tianyi Zhou

SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning (2025.acl-long)

Challenge:	Existing approaches to large language models are limited to historical backtesting and static data.
Approach:	a new large-language model is developed to simulate real-time trading in a virtual stock market . the agent trading arena simulates real-world bid-ask interactions and provides real-life trading scenarios .
Outcome:	The Agent Trading Arena simulates real-world market conditions and directly impacts price dynamics.

Copied to clipboard

Prabhat Pandey, Rupak Vignesh Swaminathan, K V Vijay Girish, Arunasish Sen, Jian. Xie, Grant Strimel, Andreas Schwarz

REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression (2026.acl-long)

Challenge:	Recent years have witnessed significant advancements in integrating speech and audio capabilities into large language models.
Approach:	They propose a 50M-example dataset for instruction fine-tuning and pre-training of speech-text large language models (LLMs) the dataset spans five languages and enables a diverse range of speech understanding and controllable speech generation instructions.
Outcome:	The proposed dataset outperforms existing speech-text LLMs on instruction-following benchmarks while achieving competitive performance on foundational speech tasks.

Copied to clipboard

Mengjie Li, Yuan Feng, Xike Xie, William J. Song

Over-Searching in Search-Augmented Large Language Models (2026.eacl-long)

Challenge:	Existing methods to evict keyvalue caches ignore diverse behavior in failure cases, such as bias and distraction.
Approach:	They propose a method to analyze attention head behaviors in success and failure scenarios by maximizing signal-to-noise ratio and minimizing noise from bias and distraction.
Outcome:	The proposed method achieves comparable accuracy to the strongest baseline, HeadKV-R2 on LongBench v2 while requiring 32x less space.

Copied to clipboard

Roy Xie, Deepak Gopinath, David Qiu, Dong Lin, Haitian Sun, Saloni Potdar, Bhuwan Dhingra

EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues (2025.naacl-long)

Challenge:	Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval.
Approach:	They conduct a systematic evaluation of over-searching across multiple dimensions including query types, model categories, retrieval conditions, and multi-turn conversations.
Outcome:	The proposed model improves answer accuracy on answerable queries but harms abstention on unanswerable ones .

Copied to clipboard

Qiming Feng, Qiujie Xie, Xiaolong Wang, Qingqiu Li, Yuejie Zhang, Rui Feng, Tao Zhang, Shang Gao

FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios (2026.findings-acl)

Challenge:	EmoCharacter evaluates emotional fidelity of role-playing agents in dialogues . current evaluations focus on personality fidelity, tone imitation, and knowledge consistency .
Approach:	They propose a benchmark to assess emotional fidelity of role-playing agents in dialogues using large language models.
Outcome:	The proposed benchmark measures emotional fidelity of role-playing agents and the characters they portray.

Copied to clipboard

Yutao Hou, Yihan Jiang, Yuhan Xie, Jian Yang, Liwen Zhang, Hailiang Huang, Guanhua Chen, Yun Chen

Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Challenge:	Existing large language models (LLMs) are prone to misuse and misinformation, posing serious compliance risks.
Approach:	They propose a bilingual red-teaming benchmark to test an LLM’s refusal of requests that violate financial compliance.
Outcome:	The proposed benchmark is based on real-world financial crime cases and ethical violations and includes 14 subcategories covering financial crimes and ethical breaches.

Copied to clipboard

Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li

UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction (2022.emnlp-main)

Challenge:	Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach:	They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome:	The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.

Copied to clipboard

Wei Tang, Benfeng Xu, Yuyue Zhao, Zhendong Mao, Yifeng Liu, Yong Liao, Haiyong Xie

Towards Visual Question Answering on Pathology Images (2021.acl-short)

Challenge:	Existing approaches to extract rich correlations between entities and relations are not fully exploited by existing methods.
Approach:	They propose to unify entities and relations by jointly encoding them within a concatenated natural language sequence and unify the modeling of interactions with a proposed Interaction Map.
Outcome:	The proposed method is more efficient and efficient than existing methods and can be scaled up to 2021.

Copied to clipboard

Xuehai He, Zhuo Cai, Wenlan Wei, Yichen Zhang, Luntian Mou, Eric Xing, Pengtao Xie

STARD: A Chinese Statute Retrieval Dataset Derived from Real-life Queries by Non-professionals (2024.findings-emnlp)

Challenge:	Pathology imaging is used for identifying the causes and effects of diseases or injuries.
Approach:	They propose a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images.
Outcome:	The proposed framework performs self-supervised pretraining and finetuning end-to-end to learn powerful visual and textual representations jointly and automatically identifies and excludes noisy self-controlled examples from pretraining.

Copied to clipboard

Weihang Su, Yiran Hu, Anzhe Xie, Qingyao Ai, Quezi Bing, Ning Zheng, Yun Liu, Weixing Shen, Yiqun Liu

DGLF: A Dual Graph-based Learning Framework for Multi-modal Sarcasm Detection (2024.emnlp-main)

Challenge:	Existing statute retrieval benchmarks emphasize formal and professional queries from sources like bar exams and legal case documents . existing retrieval approaches that lack domain-specific knowledge may struggle to capture the meanings of specialized terms accurately.
Approach:	They propose a dataset that captures the complexity and diversity of real queries from the general public.
Outcome:	The proposed dataset captures the complexity and diversity of real queries from the general public.

Copied to clipboard

Zhihong Zhu, Kefan Shen, Zhaorun Chen, Yunyan Zhang, Yuyan Chen, Xiaoqi Jiao, Zhongwei Wan, Shaorong Xie, Wei Liu, Xian Wu, Yefeng Zheng

Named Entity and Relation Extraction with Multi-Modal Retrieval (2022.findings-emnlp)

Challenge:	Existing methods for multimodal sarcasm detection neglect high-order relationships and underestimate high-frequency messages.
Approach:	They propose a Dual Graph-based Learning Framework to capture inter-modal inconsistencies . they propose combining a hypergraph and a vanilla graph to achieve enhanced propagation .
Outcome:	The proposed model outperforms existing state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Xinyu Wang, Jiong Cai, Yong Jiang, Pengjun Xie, Kewei Tu, Wei Lu

Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value (2024.naacl-long)

Challenge:	Existing approaches to name entity recognition and relation extraction are knowledge-based and may not be highly relevant.
Approach:	They propose a multi-modal named entity recognition framework that leverages image information to improve the performance of NER and relation extraction.
Outcome:	The proposed framework can achieve state-of-the-art on four multi-modal named entity recognition datasets and one multi-module relation extraction dataset.

Copied to clipboard

Jing Yao, Xiaoyuan Yi, Yifan Gong, Xiting Wang, Xing Xie

Cross-lingual Lexical Sememe Prediction (D18-1)

Challenge:	Existing work specifies values as risk criteria formulated in the AI community, e.g., fairness and privacy protection, suffering from poor clarity, adaptability and transparency.
Approach:	They propose a value alignment paradigm based on Schwartz's Theory of Basic Values as an instantiation and propose 'BaseAlign' to support this paradigm.
Outcome:	The proposed model covers existing risks and anticipates unidentified ones with a low-data set.

Copied to clipboard

Fanchao Qi, Yankai Lin, Maosong Sun, Hao Zhu, Ruobing Xie, Zhiyuan Liu

Pretraining Context Compressor for Large Language Models with Embedding-Based Memory (2025.acl-long)

Challenge:	Sememes are defined as the minimum semantic units of human languages . but most languages do not have sememe-based linguistic knowledge bases . a new framework is proposed to predict sememes for words in other languages based on semems .
Approach:	They propose a framework to model correlations between sememes and multi-lingual words in low-dimensional semantic space for sememe prediction.
Outcome:	The proposed model improves on baseline methods on real-world datasets.

Copied to clipboard

Yuhong Dai, Jianxun Lian, Yitian Huang, Wei Zhang, Mingyang Zhou, Mingqi Wu, Xing Xie, Hao Liao

Longtriever: a Pre-trained Long Text Encoder for Dense Document Retrieval (2023.emnlp-main)

Challenge:	Efficient processing of long contexts in large language models is essential for real-world applications such as retrieval-augmented generation and in-context learning.
Approach:	They propose a decoupled compressor-LLM framework that preserves contextual information within condensed embedding representations.
Outcome:	The proposed framework outperforms baseline models in three domains and across eight datasets while adapting to different downstream LLMs.

Copied to clipboard

Junhan Yang, Zheng Liu, Chaozhuo Li, Guangzhong Sun, Xing Xie

High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing (2026.findings-acl)

Challenge:	Existing PLMs are infeasible for processing long documents due to computational costs and incomprehensive document understanding.
Approach:	They propose a retrieval model that models local semantics and global context semantics in a tightly-coupled manner.
Outcome:	The proposed model overcomes three core challenges of long document retrieval: substantial computational cost, incomprehensive document understanding, and scarce annotations.

Copied to clipboard

Liangyu Wang, Huanyi Xie, Di Wang

Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition (2025.emnlp-main)

Challenge:	Zeroth-order (ZO) optimization is a memory-efficient alternative to fine-tuning large language models (LLMs).
Approach:	They propose a zeroth-order (ZO) optimization framework that offloads model parameters to CPU memory and overlapping transformer block transfer with dual forward computation on a single GPU.
Outcome:	The proposed framework achieves a 3x speedup over ZO2 on an OPT-175B model while maintaining memory efficiency and improving training throughput.

Copied to clipboard

Chenxin An, Zhihui Xie, Xiaonan Li, Ming Zhong, Shansan Gong, Lei Li, Jun Zhang, Jingjing Xu, Lingpeng Kong

HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation (2021.acl-long)

Challenge:	Existing research on long-context scaling in language models has focused on managing lengthy input prompts instead of producing long outputs.
Approach:	They propose a sequence-level curriculum learning framework that shifts a model’s focus from interpreting long chain-of-thoughts to generating them.
Outcome:	Experiments on rigorous reasoning benchmarks, including AIME24 and GPQA Diamond, show that the proposed approach surpasses standard fine-tuning by over 10% while maintaining robust performance on understanding tasks.

Copied to clipboard

Tao Qi, Fangzhao Wu, Chuhan Wu, Peiru Yang, Yang Yu, Xing Xie, Yongfeng Huang

CADMate: Generating CAD Assembly Plan with Geometric Chain-of-Thought and Spatial Physical Rewards (2026.acl-long)

Challenge:	Existing news recommendation methods learn a single user embedding for each user from their previous behaviors to represent their overall interest. Existing methods only learn 'one' embeddable representation vectors to model user interest.
Approach:	They propose a news recommendation method with hierarchical user interest modeling that captures user interest in news rather than a single user embedding.
Outcome:	The proposed method can better capture multi-grained user interest in news.

Copied to clipboard

Jiali Chen, DingBa Fu, Xusen Hei, Yuhang Liu, Yiyang Chen, Jiayuan Xie, Wenqi Fan, Yi Cai

Open Hierarchical Relation Extraction (2021.naacl-main)

Challenge:	Computer-aided design (CAD) is crucial in prototyping complex 3D objects . designers manually define assembly sequences for individual CAD parts .
Approach:	They propose a framework for computer-aided design that predicts actions for CAD parts . they use a reference design image and disassembled parts to generate 6-DoF transformations .
Outcome:	The proposed framework outperforms existing MLLMs in the design of CAD assemblies.

Copied to clipboard

Kai Zhang, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Challenge:	Existing OpenRE methods cast different relation types in isolation without considering their hierarchical dependency.
Approach:	They propose a framework to establish bidirectional connections between OpenRE and relation hierarchies by integrating hierarchy information into relation representations.
Outcome:	The proposed framework outperforms state-of-the-art models on relation clustering and hierarchy expansion.

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

Towards Linear Time Neural Machine Translation with Capsule Networks (D19-1)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Lei Li

Red-Teaming NSFW Image Classifiers as Text-to-Image Safeguards (2026.findings-acl)

Challenge:	Neural Machine Translation (NMT) is an endto-end learning approach to machine translation.
Approach:	They propose a capsule network with dynamic routing for linear time Neural Machine Translation . they map the source sentence into a matrix with pre-determined size and apply a deep LSTM network to decode the target sequence from the source representation.
Outcome:	The proposed network achieves comparable results with the Transformer system on English-German and English-French tasks.

Copied to clipboard

Tinghao Xie, Yueqi Xie, Alireza Zareian, Shuming Hu, Felix Juefei-Xu, Xiaowen Lin, Ankit Jain, Prateek Mittal, Li Chen

InfoEnh: Towards Multimodal Sentiment Analysis via Information Bottleneck Filter and Optimal Transport Alignment (2024.lrec-main)

Challenge:	Not Safe for Work (NSFW) image classifiers play a critical role in safeguarding text-to-image systems.
Approach:	They propose an automated red-teaming framework that leverages a set of generative AI tools to uncover NSFW image failures.
Outcome:	The proposed framework uncovers and interprets failure modes and enables it to be applied to real-world T2I and T2V systems.

Copied to clipboard

Yifeng Xie, Zhihong Zhu, Xuan Lu, Zhiqi Huang, Haoran Xiong

PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack (2022.coling-1)

Challenge:	Existing methods for multi-modal sentiment analysis have been developed to overcome these challenges.
Approach:	They propose a method that utilizes a masking technique as the bottleneck for information filtering and integrates all modalities into a common feature space via domain adaptation.
Outcome:	Extensive experiments on two benchmark MSA datasets show the proposed method performs better than baselines.

Copied to clipboard

Rui Zheng, Rong Bao, Qin Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Rui Xie, Wei Wu

Neural Automated Essay Scoring Incorporating Handcrafted Features (2020.coling-main)

Challenge:	Recent studies have shown that adversarial examples can be easily fooled by adversarially perturbed examples.
Approach:	They propose a pluggable defense module PlugAT to provide robust predictions by adding a few trainable parameters to the model inputs while keeping the original model frozen.
Outcome:	The proposed model improves robustness over several strong baselines whilst training only 9.1% parameters.

Copied to clipboard

Masaki Uto, Yikuan Xie, Maomi Ueno

How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior (2026.acl-long)

Challenge:	Automated essay scoring (AES) relies on handcrafted features, but recent studies have proposed a hybrid method that integrates handcrafted essay-level features into a DNN-AES model.
Approach:	They propose a method that integrates handcrafted features into a DNN-AES model.
Outcome:	The proposed method significantly improves the accuracy of existing methods.

Copied to clipboard

Zidi Xiong, Yuping Lin, Wenya Xie, Pengfei He, Zirui Liu, Jiliang Tang, Himabindu Lakkaraju, Zhen Xiang

ToViLaG: Your Visual-Language Generative Model is Also An Evildoer (2023.emnlp-main)

Challenge:	In practice, memory designs vary widely across agents due to their diverse objectives and functionalities.
Approach:	They conduct an empirical study on how memory management choices impact the LLM agents’ behavior, especially their long-term performance.
Outcome:	The proposed methods show that LLM agents display an experience-following property, which results in highly similar agent outputs.

Copied to clipboard

Xinpeng Wang, Xiaoyuan Yi, Han Jiang, Shanlin Zhou, Zhihua Wei, Xing Xie

Graph Enhanced Dual Attention Network for Document-Level Relation Extraction (2020.coling-main)

Challenge:	Recent large-scale Visual-Language Generative Models (VLGMs) generate toxic content, e.g., offensive text and pornography images, raising significant ethical risks.
Approach:	They propose a bottleneck-based detoxification method to reduce toxicity while maintaining comparable generation quality.
Outcome:	The proposed method could reduce toxicity while maintaining comparable generation quality.

Copied to clipboard

Bo Li, Wei Ye, Zhonghao Sheng, Rui Xie, Xiangyu Xi, Shikun Zhang

Building Multilingual Machine Translation Systems That Serve Arbitrary XY Translations (2022.naacl-main)

Challenge:	Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relation facts.
Approach:	They propose to characterize the interaction between sentences and potential relation instances via a Graph Enhanced Dual Attention network (GEDA) . they also propose a simple yet effective regularizer based on the natural duality of the S2R and R2S attentions, whose weights are also supervised by the supporting evidence of relation instances during training.
Outcome:	The proposed model achieves competitive performance on an existing large-scale dataset while the predictions can be interpretable and easily observed.

Copied to clipboard

Akiko Eriguchi, Shufang Xie, Tao Qin, Hany Hassan

Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling (2026.findings-acl)

Challenge:	Multilingual Neural Machine Translation (MNMT) systems are often limited to many-to-one directions and suffer from poor performance in one-to one directions.
Approach:	They propose to build multilingual machine translation systems that serve arbitrary X-Y directions while leveraging multilinguality with a two-stage training strategy of pretraining and finetuning.
Outcome:	The proposed system outperforms baseline bilingual models and pivot translation models in most directions without the need for architecture change or extra data collection.

Copied to clipboard

Shuliang Liu, Zhipeng Xu, Zhenghao Liu, Yukun Yan, Minghe Yu, Yu Gu, Chong Chen, Huiyuan Xie, Ge Yu

EvolveSearch: An Iterative Self-Evolving Search Agent (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) are used as automatic evaluators to provide accurate and reliable assessments.
Approach:	They propose a framework that integrates LLM-based judgment models into a multi-agent system and simulates the interactive client-server polling mechanism.
Outcome:	The proposed framework outperforms supervised models trained on annotated judgment data while requiring no human-labeled annotations.

Copied to clipboard

Ding-Chu Zhang, Yida Zhao, Jialong Wu, Liwen Zhang, Baixuan Li, Wenbiao Yin, Yong Jiang, Yu-Feng Li, Kewei Tu, Pengjun Xie, Fei Huang

MAFMO: Multi-modal Adaptive Fusion with Meta-template Optimization for Vision-Language Models (2025.findings-emnlp)

Challenge:	Existing approaches to enabling LLM web search proficiency struggle with data production in open-search domains, while supervised fine-tuning struggles with data utilization efficiency.
Approach:	They propose an iterative self-evolution framework that combines SFT and RL to enhance agentic web search capabilities without external human-annotated reasoning data.
Outcome:	EvolveSearch achieves 4.7% improvement over current state-of-the-art in seven benchmarks . supervised fine-tuning struggles with data production in open-search domains compared with RL .

Copied to clipboard

Mingrui Xie, Lulu Xu, Junliang Du

Matching-oriented Embedding Quantization For Ad-hoc Retrieval (2021.emnlp-main)

Challenge:	Existing approaches focus on single-modality adjustments, leading to suboptimal alignment and limited generalization.
Approach:	They propose a plug-and-play framework for visual recognition that integrates a Harmonic Cross-Modal Adapter and a Meta-Template Optimization module.
Outcome:	Extensive experiments across multiple fine-grained visual recognition benchmarks show that MAFMO consistently improves existing methods’ performance on both novel classes and harmonic mean while maintaining robustness under various challenging conditions with minimal computational overhead.

Copied to clipboard

Shitao Xiao, Zheng Liu, Yingxia Shao, Defu Lian, Xing Xie

Source-free Domain Adaptation for Aspect-based Sentiment Analysis (2024.lrec-main)

Challenge:	Product quantization (PQ) is a widely used technique for ad-hoc retrieval.
Approach:	They propose a match-oriented product quantization with a multinoulli contrastive loss objective.
Outcome:	The proposed method maximizes matching probability of query and ground-truth key, compared with previous methods on non-supervised datasets.

Copied to clipboard

Zishuo Zhao, Ziyang Ma, Zhenzhou Lin, Jingyou Xie, Yinghui Li, Ying Shen

DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation (2023.acl-long)

Challenge:	Unsupervised Domain Adaptation (UDA) of the Aspect-based Sentiment Analysis task is a data mining technique that involves aspect extraction and aspect sentiment classification subtasks.
Approach:	They propose a framework that allows model parameter transfer, not data transfer, between different domains.
Outcome:	The proposed framework performs competitively with traditional unsupervised domain adaptation methods under privacy conditions.

Copied to clipboard

Guanqun Bi, Lei Shen, Yanan Cao, Meng Chen, Yuqiang Xie, Zheng Lin, Xiaodong He

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus (2026.findings-acl)

Challenge:	Existing methods to generate empathetic responses are monotonous and generic, resulting in shallow empathy and few connections to the context.
Approach:	They propose to use explicit control to guide the empathy expression and a framework DiffusEmp to unify the utilization of dialogue context and attribute-oriented control signals.
Outcome:	The proposed framework outperforms baselines on EmpatheticDialogue in terms of controllability, informativeness, diversity, and diversity without the loss of context-relatedness.

Copied to clipboard

Yexing Du, Kaiyuan Liu, Bihe Zhang, Youcheng Pan, Bo Yang, Liangyu Huo, Xiyuan Zhang, Jian Xie, Daojing He, Yang Xiang, Ming Liu, Bing Qin

Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study (2022.findings-emnlp)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced Chinese Classical Studies (CCS) but the audio dimension of CCS remains underexplored due to a lack of high-quality, domain-specific audio corpora.
Approach:	They propose a 119-hour audio corpus comprising 22,000 audio samples to bridge this gap . it encompasses a diverse range of literary genres across six tasks .
Outcome:	The proposed corpus encompasses a diverse range of literary genres across six tasks: Automatic Speech Recognition (ASR), Speech-to-Text Translation (S2TT), Speech Emotion Captioning (SEC), Spoken Question Answering ( SQA), Speech Understanding (SU), and Speech Reasoning (SR).

Copied to clipboard

Xin Xu, Xiang Chen, Ningyu Zhang, Xin Xie, Xi Chen, Huajun Chen

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation (2022.findings-acl)

Challenge:	Existing approaches to extract relational facts from text are limited in their ability to learn from limited labeled data.
Approach:	They propose to use prompt-based methods with few-shot labeled data to evaluate performance . data augmentation technologies and self-training are also proposed to generate more labeles in-domain data.
Outcome:	The proposed methods perform well in low-resource settings with 8 relation extraction datasets.

Copied to clipboard

Tianxiang Sun, Xiangyang Liu, Wei Zhu, Zhichao Geng, Lingling Wu, Yilong He, Yuan Ni, Guotong Xie, Xuanjing Huang, Xipeng Qiu

Challenge:	Existing methods to measure instance difficulty use generalization and threshold-tuning . a new approach to learn to exit is based on hash functions to assign tokens to a fixed exiting layer.
Approach:	They propose a Hash-based Early Exiting approach that replaces learn-to-exit modules with hash functions to assign each token to a fixed exiting layer.
Outcome:	The proposed approach improves on learning to exit and predicting instance difficulty.

A Large-Scale Dataset for Empathetic Response Generation (2021.emnlp-main)

Copied to clipboard

Anuradha Welivita, Yubo Xie, Pearl Pu

Typos Correction Training against Misspellings from Text-to-Text Transformers (2024.lrec-main)

Challenge:	Existing empathetic datasets are limited in size and cost due to the cost of manual labor.
Approach:	They propose to annotate 1M dialogues with 32 fine-grained emotions and eight empathetic response intents and the Neutral category using a silver dataset.
Outcome:	The proposed pipeline compares the quality of the proposed dataset with a state-of-the-art gold dataset using offline experiments and visual validation methods.

Copied to clipboard

Guicai Xie, Ke Zhang, Lei Duan, Wei Zhang, Zeqian Huang

Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models (2023.findings-emnlp)

Challenge:	Existing dense retrieval systems suffer from typoed queries due to mistyping or phonetic typing errors.
Approach:	They propose a method that incorporates the spelling correction objective into the DR model and a prompt-based augmentation technique to enhance the alignment of the typoed query and its original query.
Outcome:	The proposed model outperforms existing typos-aware training approaches and sophisticated training advanced retrievers.

Copied to clipboard

Simon Stepputtis, Joseph Campbell, Yaqi Xie, Zhengyang Qi, Wenxin Zhang, Ruiyi Wang, Sanketh Rangreji, Charles Lewis, Katia Sycara

A Fine-Grained Domain Adaption Model for Joint Word Segmentation and POS Tagging (2021.emnlp-main)

Challenge:	Deception and persuasion play a critical role in long-horizon multi-party dialogues, especially when the interests, goals, and motivations of the participants are not aligned.
Approach:	They propose a game in which players must determine each other’s hidden identities to complete their team’s objective.
Outcome:	The proposed model can be used to determine the true player identities of six human players in a cooperative-competitive game.

Copied to clipboard

Peijie Jiang, Dingkun Long, Yueheng Sun, Meishan Zhang, Guangwei Xu, Pengjun Xie

GOBench: Stage-Wise Diagnostics and the Visual Paradox in Multimodal Graph Optimization (2026.findings-acl)

Challenge:	Experimental results show that joint models of word segmentation and POS tagging can lead to better performance because they are closely related.
Approach:	They propose a domain adaption method for Chinese word segmentation and POS tagging that uses a simple metric to model the gaps between target and target domains.
Outcome:	The proposed method can gain significant performance improvements over baselines on a benchmark dataset.

Copied to clipboard

Yinghao Chen, Wantong Xie, Shuli Zeng, Sijia Zhang, Xiaotian Pan, Feng Wu, Xiangyang Li

Fine-grained Interest Matching for Neural News Recommendation (2020.acl-main)

Challenge:	Existing benchmarks fail to represent multimodal problem specifications, score outcomes only and cannot localize where failures occur along the modeling pipeline.
Approach:	They propose a Graph Optimization benchmark that aligns multiple modalities with solver-derived oracles and a diagnostic protocol that evaluates intermediate artifacts as well as end results.
Outcome:	Graph Optimization benchmark (GOBench) evaluates intermediate artifacts as well as end results . vision reliably increases inference cost, while reliability impact is regime-dependent . current benchmarks fail to represent multimodal problem specifications, fail to localize failures .

Copied to clipboard

Heyuan Wang, Fangzhao Wu, Zheng Liu, Xing Xie

Empirical Study of Zero-Shot NER with ChatGPT (2023.emnlp-main)

Challenge:	Existing studies represent each user as a single vector and then match the candidate news vector, which may lose fine-grained information for recommendation.
Approach:	They propose a Fine-grained interest matching method for neural news recommendation based on multi-level representations and fine-grain matching between segment pairs of each browsed news and the candidate news at each semantic level.
Outcome:	The proposed model can capture more fine-grained interest matching signals by performing interactions between each pair of news at multi-level semantic granularities.

Copied to clipboard

Tingyu Xie, Qi Li, Jian Zhang, Yan Zhang, Zuozhu Liu, Hongwei Wang

Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers (2026.findings-acl)

Challenge:	Large language models (LLMs) have been a key component of natural language processing (NLP) .
Approach:	They propose to decompose the NER task into simpler subproblems by labels and propose a syntactic augmentation strategy to stimulate model's intermediate thinking.
Outcome:	The proposed methods achieve remarkable improvements for zero-shot NER across seven benchmarks, including Chinese and English datasets.

Copied to clipboard

Nguyen Viet Anh, Shiqian Zhao, Gia Dao, Runyi Hu, Yi Xie, Xiaobao Wu, Anh Tuan Luu

SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling (2020.emnlp-main)

Challenge:	Existing jailbreak methods struggle to balance effectiveness with robustness against adaptive safety mechanisms.
Approach:	They propose a novel approach that targets Large Reasoning Models through an adaptive encryption pipeline designed to overwhelm their reasoning capabilities.
Outcome:	The proposed approach achieves an attack success rate of 85.6% on OpenAI GPT-o4-mini, outperforming state-of-the-art baselines by a significant margin of 17.2%.

Copied to clipboard

Di Wu, Liang Ding, Fan Lu, Jian Xie

Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs (2025.emnlp-main)

Challenge:	Slot filling and intent detection are two main tasks in spoken language understanding systems.
Approach:	They propose a non-autoregressive slot filling model with two-pass iteration mechanism to handle uncoordinated slots problem.
Outcome:	The proposed model significantly outperforms previous models in slot filling task while speeding up decoding.

Copied to clipboard

Xin Gao, Ruiyi Zhang, Daniel Du, Saurabh Mahindre, Sai Ashish Somayajula, Pengtao Xie

SAHM: A Benchmark for Arabic Financial and Shari’ah-Compliant Reasoning (2026.acl-long)

Challenge:	Large Language Models (LLMs) are widely used for temporal prediction tasks . however, their reliance on pretraining data can lead to contamination concerns .
Approach:	They investigate the capability of prompting to simulate an earlier knowledge cutoff in large language models.
Outcome:	The proposed model fails to induce forgetting when the forgotten content is not directly asked but causally related to the query.

Copied to clipboard

Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl, Dani Bouch, Momina Ahsan, Muhra AlMahri, Marwa Elsaid Khalil, Yuxia Wang, Salem Lahlou, Sophia Ananiadou, Veselin Stoyanov, Jimin Huang, Xueqing Peng, Preslav Nakov, Zhuohan Xie

Nested Browser-Use Learning for Agentic Information Seeking (2026.acl-long)

Challenge:	English financial NLP has progressed rapidly through benchmarks for sentiment, document understanding, and financial question answering.
Approach:	They propose a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari’ah-compliant reasoning.
Outcome:	The proposed dataset contains 14,380 expert-verified instances spanning seven tasks . it includes financial sentiment analysis, extractive summarization, and event–cause reasoning .

Copied to clipboard

Baixuan Li, Jialong Wu, Wenbiao Yin, Kuan Li, Zhongwang Zhang, Huifeng Yin, Zhengwei Tao, Liwen Zhang, Pengjun Xie, Jingren Zhou, Yong Jiang, Wentao Zhang, Zhiqiang Gao

Challenge:	Existing information-seeking (IS) agents rely on the web for their information acquisition.
Approach:	They propose a browser-action framework that decouples interaction control from page exploration through a nested structure.
Outcome:	Empirical results show that NestBrowse offers clear benefits in practice.

One Token Is Enough: Improving Diffusion Language Models with a Sink Token (2026.findings-acl)

Copied to clipboard

Zihou Zhang, Zheyong Xie, Li Zhong, Haifeng Liu, Shaosheng Cao

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)

Challenge:	Existing Diffusion Language Models lack a structural constraint to stabilize attention sinks.
Approach:	They propose a simple but effective extra sink token that is constrained to attend to itself while remaining globally visible to all other tokens.
Outcome:	The proposed token is able to stabilize attention sinks and improve model performance.

Copied to clipboard

Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang

Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives (2025.findings-acl)

Challenge:	Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks.
Approach:	They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task.
Outcome:	The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines.

Copied to clipboard

Zhihu Wang, Shiwan Zhao, Yu Wang, Heyuan Huang, Sitao Xie, Yubo Zhang, Jiaxin Shi, Zhixing Wang, Hongyan Li, Junchi Yan

Challenge:	Existing approaches to solving complex tasks with large language models (LLMs) fail to decompose tasks accurately or execute subtasks effectively.
Approach:	They propose a Chain-of-Learning (CoL) paradigm that highlights task dependencies on specific capability items, further broken down into their constituent knowledge and skill components.
Outcome:	The proposed model improves Yi-1.5-9B and Llama3-Chinese-8B for legal tasks by 45.00% and 24.50% on different domains.

RENN: A Rule Embedding Enhanced Neural Network Framework for Temporal Knowledge Graph Completion (2024.lrec-main)

Copied to clipboard

Linlin Zong, Zhenrong Xie, Chi Ma, Xinyue Liu, Xianchao Zhang, Bo Xu

Explaining Answers with Entailment Trees (2021.emnlp-main)

Challenge:	Existing methods for temporal knowledge graph embedding do not account for structural dependencies between relations.
Approach:	They propose a framework that enhances temporal knowledge graph completion through rule embedding.
Outcome:	The proposed framework improves temporal knowledge graph completion through rule embedding.

Copied to clipboard

Bhavana Dalvi, Peter Jansen, Oyvind Tafjord, Zhengnan Xie, Hannah Smith, Leighanna Pipatanangkura, Peter Clark

Improving Model Factuality with Fine-grained Critique-based Evaluator (2025.acl-long)

Challenge:	ENTAILMENTBANK is the first dataset to contain multistep entailment trees.
Approach:	They propose to generate explanations in the form of entailment trees, a tree of multipremise entanglements steps from facts that are known to the hypothesis of interest.
Outcome:	The proposed model can generate explanations in the form of entailment trees . this is a tree of multipremise enttailment steps from facts known to the hypothesis of interest.

Copied to clipboard

Yiqing Xie, Wenxuan Zhou, Pradyot Prakash, Di Jin, Yuning Mao, Quintin Fettes, Arya Talebzadeh, Sinong Wang, Han Fang, Carolyn Rose, Daniel Fried, Hejia Zhang

Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes (2022.findings-emnlp)

Challenge:	Factuality evaluation aims to detect factual errors produced by language models and guide the development of more factual models.
Approach:	They propose a framework that leverages FenCE to improve the factuality of LM generators by constructing training data.
Outcome:	The proposed framework improves the factuality of LM generators by enhancing their training data.

Copied to clipboard

Kaige Xie, Sarah Wiegreffe, Mark Riedl

MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Challenge:	Recent work in multi-hop QA has shown that performance can be boosted by decomposing questions into simpler, single-hop questions.
Approach:	They propose to decompose multi-hop questions into simpler, single-hop ones to create explanations by probing a neural QA model with them.
Outcome:	The proposed approach can be used to generate explanations by probing a neural QA model with them.

Copied to clipboard

Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, Pengtao Xie

View Dialogue in 2D: A Two-stream Model in Time-speaker Perspective for Dialogue Summarization and beyond (2022.coling-1)

Challenge:	telemedicine is a medical practice that provides patient care remotely using video conferencing tools.
Approach:	They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance .
Outcome:	The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues.

Copied to clipboard

Keli Xie, Dongchen He, Jiaxin Zhuang, Siyuan Lu, Zhongfeng Wang

FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosure (2026.acl-demo)

Challenge:	Existing models for dialogue summarization focus on document summarizing on time and speaker-centered points, but this approach is limited in understanding the dialogue.
Approach:	They propose a 2D view of dialogue based on a time-speaker perspective where the time and speaker streams of dialogue can be obtained as strengthened input.
Outcome:	The proposed model outperforms existing models on the QMSum dataset and improves summary faithfulness and human evaluation.

Copied to clipboard

Fan Zhang, Mingzi Song, Rania Elbadry, Yankai Chen, Shaobo Wang, Yixi Zhou, Xunwen Zheng, Yueru He, Yuyang Dai, Georgi Nenkov Georgiev, Ayesha Gull, Muhammad Usman Safder, Fan Wu, Liyuan Meng, Fengxian Ji, Junning Zhao, Xueqing Peng, Jimin Huang, YU Chen, Xue Liu, Preslav Nakov, Zhuohan Xie

Challenge:	FinReporting is an agentic workflow for localized cross-jurisdiction financial reporting . existing approaches assume a single-market setting and overlook structural differences across jurisdictions .
Approach:	They propose a workflow that decomposes financial reporting into auditable stages . they use Large Language Models to extract and summarize corporate disclosures .
Outcome:	The proposed system decomposes reporting into auditable stages . it improves consistency and reliability under heterogeneous reporting regimes.

ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning (2023.findings-emnlp)

Copied to clipboard

Yuxi Xie, Guanzhen Li, Min-Yen Kan

Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data (D19-1)

Challenge:	ECHo is a diagnostic dataset of event causality inference grounded in visio-linguistic social scenarios.
Approach:	They propose a diagnostic dataset of event causality inference grounded in visio-linguistic social scenarios.
Outcome:	The proposed framework examines the reasoning capability of current AI systems on three human-centric tasks.

Copied to clipboard

Ruidong Wu, Yuan Yao, Xu Han, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis (2026.findings-acl)

Challenge:	Existing methods to extract relational facts from open domain corpora are time-consuming and human-intensive.
Approach:	They propose a framework to learn similarity metrics of relations from labeled data . they propose to transfer relational knowledge to identify novel relations in unlabeled data.
Outcome:	Experiments on two real-world datasets show that the proposed framework improves compared with state-of-the-art methods.

Copied to clipboard

Haitao Li, Chunxiang Jin, Chenglin Li, Wenhao Guan, Zhengxing Huang, Xie Chen

WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models (2023.emnlp-industry)

Challenge:	Recent controllable zero-shot text-to-speech systems can synthesize speech for unseen speakers from a short reference audio clip, but they also inherit the speaking style present in the reference.
Approach:	They propose a framework that enables continuous and reference-relative style control in zero-shot text-to-speech systems by combining style-specific LoRAs with Orthogonal LoRA Fusion.
Outcome:	The proposed framework reduces the model's dependence on reference style while preserving text fidelity while maintaining intelligibility and speaker timbre.

Copied to clipboard

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Yusen Hu, Bin Luo, Yifeng Geng, Xuansong Xie

TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs (2026.acl-long)

Challenge:	Existing typography solutions lack adaptability, creativity, and computational efficiency.
Approach:	They propose a user-driven framework for artistic typography synthesis based on the Large Language Model (LLM) the LLM Engine interprets user inputs and generates actionable prompts for the other modules, transforming abstract concepts into tangible designs.
Outcome:	The proposed framework incorporates four key modules: the LLM Engine, SemTypo, StyTyPo, and TexTyPO.

Copied to clipboard

Sibo Xiao, Fu Jinyuan, Zhongle Xie, Lidan Shou

Challenge:	Speculative decoding (SD) is a useful tool for accelerating large language models . but its utility is limited by a fundamental constraint: draft and target models must share the same vocabulary .
Approach:	They propose an algorithm that uses a draft token sequence to get a new target token sequence and then uses DTW to build a mapping to transfer probability distributions.
Outcome:	The proposed method shows 1.57x speedup on various tasks.

Toward Human-Like Evaluation for Natural Language Generation with Error Analysis (2023.acl-long)

Copied to clipboard

Qingyu Lu, Liang Ding, Liping Xie, Kanjian Zhang, Derek F. Wong, Dacheng Tao

HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)

Challenge:	Pre-trained language models (PLMs) have been used to evaluate language generation tasks . pretrained error analysis can be used to refine the generated sentence toward higher confidence .
Approach:	They propose to combine pretrained language model based metrics with human-like error analysis to improve sentence confidence.
Outcome:	The proposed method outperforms top-scoring metrics in 19/25 settings.

Copied to clipboard

An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu

Human or LLM as Standardized Patients? A Comparative Study in Medical Education (2026.acl-long)

Challenge:	Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization.
Approach:	They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts .
Outcome:	The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters.

Copied to clipboard

Bingquan Zhang, Xiaoxiao Liu, Yuchi Wang, Zhou Lei, Qianqian Xie, Benyou Wang

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents (2026.acl-long)

Challenge:	Standardized patients (VSPs) are indispensable for clinical skills training but remain expensive and difficult to scale.
Approach:	They propose a multi-agent VSP framework that separates case-grounded information disclosure from response generation to support stable, inquiry-conditioned patient behavior.
Outcome:	The proposed framework more closely matches human SP behavior than existing VSPs, particularly in case consistency and controlled disclosure.

Copied to clipboard

Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Yian Wang, Qingyun Li, Yu Qiao, Zun Wang, Zichen Ding

Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models (2025.emnlp-main)

Challenge:	Vision-Language Models (VLMs) lack visual-aware tutorial retrieval and historical visual context curation and pruning.
Approach:	They propose a framework that integrates an orchestrator and a Reflection-Memory Agent for robust automation.
Outcome:	Experimental results show that OS-Symphony delivers substantial performance gains across model scales.

Copied to clipboard

Xie Zhifei, Mingbao Lin, Zihang Liu, Pengcheng Wu, Shuicheng Yan, Chunyan Miao

MoVa: Towards Generalizable Classification of Human Morals and Values (2025.emnlp-main)

Challenge:	Recent advances in multimodal reasoning overlook the audio modality.
Approach:	They propose a large-scale audio language model for deep reasoning that leverages a multitask audio dataset.
Outcome:	The proposed model performs well across key benchmarks including MMAU-mini, AIR-Bench chat/foundation, and MELD.

Copied to clipboard

Ziyu Chen, Junfei Sun, Chenxi Li, Tuan Dung Nguyen, Jing Yao, Xiaoyuan Yi, Xing Xie, Chenhao Tan, Lexing Xie

Text Classification

Challenge:	Identifying human morals and values embedded in language is essential to empirical studies of communication.
Approach:	They propose a framework for generalizable classification of human morals and values . they recommend a classification strategy that scores all related concepts simultaneously .
Outcome:	The proposed method outperforms fine-tuned models across domains and frameworks.

UCL-Bench: A Chinese User-Centric Legal Benchmark for Large Language Models (2025.findings-naacl)

Copied to clipboard

Ruoli Gan, Duanyu Feng, Chen Zhang, Zhihang Lin, Haochen Jia, Hao Wang, Zhenyang Cai, Lei Cui, Qianqian Xie, Jimin Huang, Benyou Wang

GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis (2024.acl-long)

Challenge:	Existing legal benchmarks focusing on knowledge and logic evaluate LLMs on various tasks in legal domain, but few have explored the practical application of LLM by actual users.
Approach:	They propose a Chinese user-centric legal benchmark that aims to assess the practical application of LLMs by real users.
Outcome:	The proposed model outperforms existing models on various tasks in legal domain but does not outperfect ChatGPT.

Copied to clipboard

Yueqi Xie, Minghong Fang, Renjie Pi, Neil Gong

ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods (2024.emnlp-main)

Challenge:	Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs.
Approach:	They propose a method which scrutinizes the gradients of safety-critical parameters in large LLMs to detect jailbreak prompts.
Outcome:	The proposed method outperforms Llama Guard in detecting jailbreak prompts despite extensive finetuning with a large dataset.

Copied to clipboard

Roy Xie, Junlin Wang, Ruomin Huang, Minxing Zhang, Rong Ge, Jian Pei, Neil Gong, Bhuwan Dhingra

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts (2024.findings-emnlp)

Challenge:	ReCaLL (Relative Conditional Log-Likelihood) is a membership inference attack that can detect LLMs’ pretraining data by leveraging their conditional language modeling capabilities.
Approach:	They propose a membership inference attack to detect LLMs’ pretraining data by leveraging their conditional language modeling capabilities.
Outcome:	The proposed model achieves state-of-the-art performance on the WikiMIA dataset, even with random and synthetic prefixes, and can be further improved using an ensemble approach.

Copied to clipboard

Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, Tong Zhang

MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria (2025.naacl-long)

Challenge:	Reinforcement learning from human feedback (RLHF) is the primary method for aligning large language models with human preferences.
Approach:	They propose to train an Absolute-Rating Multi-Objective Reward Model with multi-dimensional absolute-rating data.
Outcome:	The proposed model outperforms the LLM-as-a-judge method on RewardBench . it achieves state-of-the-art performance on the benchmark .

Copied to clipboard

Wentao Ge, Shunian Chen, Hardy Chen, Nuo Chen, Junying Chen, Zhihong Chen, Wenya Xie, Shuo Yan, ChenghaoZhu ChenghaoZhu, Ziyue Lin, Dingjie Song, Xidong Wang, Anningzhe Gao, Zhang Zhiyi, Jianquan Li, Xiang Wan, Benyou Wang

SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)

Challenge:	Existing evaluation methodologies for multimodal large language models are limited in evaluating objective queries without considering real-world user experiences.
Approach:	They propose to evaluate multimodal large language models with per-sample criteria using potent MLLM as the judge.
Outcome:	The proposed evaluation paradigm shows that it can be used to evaluate multimodal large language models with per-sample criteria.

Copied to clipboard

Yiyang Gu, Junwei Yang, Junyu Luo, Ye Yuan, Bin Feng, Yingce Xia, Shufang Xie, Kaili Liu, Bohan Wu, Qi Shi, Haoran Li, Beier Xiao, Zhiping Xiao, Xiao Luo, Weizhi Zhang, Philip S. Yu, Zequn Liu, Ming Zhang

LLM-Based Dialogue Labeling for Multiturn Adaptive RAG (2025.emnlp-industry)

Challenge:	Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases.
Approach:	They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs.
Outcome:	The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs.

Copied to clipboard

Zhiyu Chen, Biancen Xie, Sidarth Srinivasan, Manikandarajan Ramanathan, Rajashekar Maragoud, Qun Liu

SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes (2026.acl-long)

Challenge:	Retrieval-Augmented Generation (RAG) models integrate large language models with external knowledge retrieval . however, building multi-turn RAG-based chatbots for real-world customer service requires additional complexities.
Approach:	They propose methods to automatically generate labels for adaptive retrieval components using real customer-agent dialogue data.
Outcome:	The proposed method generates labels for components using real customer-agent dialogue data.

Copied to clipboard

Wenxuan Xie, Yaxun Dai, Wenhao Jiang

Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement (2024.emnlp-main)

Challenge:	Existing approaches depend on static, pre-processed database information, which restricts the model’s capacity to deeply comprehend the underlying database content.
Approach:	They propose a framework that empowers LLMs to perform Self-Driven Exploration of databases during inference.
Outcome:	Evaluated on the BIRD benchmark with Qwen2.5-72B-Instruct, SDE-SQL achieves an 8.02 % improvement in execution accuracy over the baseline.

Copied to clipboard

Pengwei Zhan, Zhen Xu, Qian Tan, Jie Song, Ru Xie

Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning (2020.emnlp-main)

Challenge:	Large language models (LLMs) demonstrate exceptional instruct-following ability to complete downstream tasks.
Approach:	They propose a black-box combinatorial optimization framework that iteratively improves lexical choices in prompts by a search strategy related to word influence.
Outcome:	The proposed framework recovers the model's ability to instruct-follow and solve downstream tasks even when the variations are imperceptible to humans.

Copied to clipboard

Yuning Mao, Yanru Qu, Yiqing Xie, Xiang Ren, Jiawei Han

Sparsifying Mamba (2025.findings-emnlp)

Challenge:	Recent studies on single-document summarization (SDS) benefit from advances in neural sequence learning, but they produce unsatisfactory results on multi-document summary (MDS).
Approach:	They propose a neural sequence learning method that unifies advanced neural SDS methods and statistical measures used in classical MDS.
Outcome:	The proposed method achieves state-of-the-art performance on benchmark MDS datasets.

Copied to clipboard

An Wang, Ruobing Xie, Shuaipeng Li, Xingwu Sun, Zhanhui Kang

Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation (2021.naacl-main)

Challenge:	Existing attempts to integrate sparsification with Mamba fail to leverage Mamba's internal structure for fine-grained sparsifying.
Approach:	They propose to use Mamba to integrate sparsification into Mamba and propose a flexible and effective mechanism for parameter scalability.
Outcome:	The proposed framework can independently achieve parameter scalability and has stronger performance.

Copied to clipboard

Shuhao Gu, Yang Feng, Wanying Xie

EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions (2026.findings-acl)

Challenge:	Existing methods for domain adaptation suffer from catastrophic forgetting, large domain divergence, and model explosion.
Approach:	They propose a method which prunes the model and keeps the important neurons or parameters responsible for both general-domain and in-domain translation.
Outcome:	The proposed method improves on different language pairs and domains compared with strong baselines.

Copied to clipboard

Weiyu Sun, Liangliang Chen, Yongnuo Cai, Huiru Xie, Yi Zeng, Ying Zhang

Readability Controllable Biomedical Document Summarization (2022.findings-emnlp)

Challenge:	Multimodal Large Language Models (MLLMs) are a promising tool for traditional education but lack authentic and domain-specific benchmarks to accurately interpret student handwritten solutions.
Approach:	They propose to use MLLMs to interpret unconstrained STEM student handwritten solutions with intertwined mathematical formulas, diagrams, and textual reasoning to bridge this gap.
Outcome:	The proposed model can detect and rectify recognition errors with minimal human intervention on unseen student solutions.

Copied to clipboard

Zheheng Luo, Qianqian Xie, Sophia Ananiadou

FIRE: Fact-checking with Iterative Retrieval and Verification (2025.findings-naacl)

Challenge:	Existing controllable summarization systems for biomedical documents have little attention to readability control, leaving users with incompatible summaries .
Approach:	They propose a task of readability controllable summarization for biomedical documents to generate summaries that are incompatible with users' levels of expertise.
Outcome:	The proposed model is based on pre-trained language models with prevalent controlling and generation techniques and evaluates the readability discrepancy between lay and technical summaries.

Copied to clipboard

Zhuohan Xie, Rui Xing, Yuxia Wang, Jiahui Geng, Hasan Iqbal, Dhruv Sahnan, Iryna Gurevych, Preslav Nakov

Knowledge-Guided Cross-Topic Visual Question Generation (2024.lrec-main)

Challenge:	Fact-checking long-form text is challenging, and breaking it down into multiple atomic claims is not cost-effective.
Approach:	They propose a novel agent-based framework that integrates evidence retrieval and claim verification in an iterative manner.
Outcome:	The proposed framework reduces large language model (LLM) costs by an average of 7.6 times and search costs by 16.5 times while retaining the same performance.

Copied to clipboard

Hongfei Liu, Guohua Wang, Jiayuan Xie, Jiali Chen, Wenhao Fang, Yi Cai

Automated Essay Scoring via Pairwise Contrastive Regression (2022.coling-1)

Challenge:	Existing methods for visual question generation use answers or question types as constraints to generate questions.
Approach:	They propose a knowledge-guided cross-topic visual question generation task to generate unseen topics in cross-section scenarios.
Outcome:	The proposed model outperforms baselines and can generate unseen topic-related questions in cross-topic scenarios.

Copied to clipboard

Jiayi Xie, Kaiwei Cai, Li Kong, Junsheng Zhou, Weiguang Qu

Challenge:	Existing approaches to automate essay scoring use regression or ranking objectives . a novel neural pairwise ranking model is developed to optimize both objectives based on the same loss .
Approach:	They propose a novel Neural Pairwise Contrastive Regression model that optimizes both objectives simultaneously as a single loss.
Outcome:	The proposed model outperforms previous methods on the public Automated Student Assessment Prize dataset.

GRETEL: Graph Contrastive Topic Enhanced Language Model for Long Document Extractive Summarization (2022.coling-1)

Copied to clipboard

Qianqian Xie, Jimin Huang, Tulika Saha, Sophia Ananiadou

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains (2025.naacl-long)

Challenge:	Existing approaches to capture and integrate global semantic information are limited due to their limited ability to capture long-range dependencies.
Approach:	They propose a graph contrastive topic enhanced language model that integrates a neural topic model with a pre-trained language model to capture global contextual semantics.
Outcome:	The proposed model outperforms existing methods on general domain and biomedical datasets.

Copied to clipboard

Ran Xu, Hui Liu, Sreyashi Nag, Zhenwei Dai, Yaochen Xie, Xianfeng Tang, Chen Luo, Yang Li, Joyce C. Ho, Carl Yang, Qi He

Leveraging AMR Graph Structure for Better Sequence-to-Sequence AMR Parsing (2024.lrec-main)

Challenge:	Retrieval-augmented generation (RAG) enhances the question answering abilities of large language models (LLMs) however, adapting general-purpose RAG systems to specialized fields poses unique challenges due to distribution shifts and limited access to domain-specific data.
Approach:	They propose a method that equips large language models with joint capabilities of question answering and question generation for domain adaptation.
Outcome:	Experiments on 11 datasets across three different domains verify the efficacy of SimRAG over baselines by 1.2%–8.6%.

Copied to clipboard

Linyu Fan, Wu Wu Yiheng, Jun Xie, Junhui Li, Fang Kong, Guodong Zhou

Global Attention Decoder for Chinese Spelling Error Correction (2021.findings-acl)

Challenge:	Recent studies on AMR parsing often regard this task as a seq2seq translation problem.
Approach:	They propose to translate AMR graphs into AMR token sequences in pre-processing and recover AMR from sequences after decoding.
Outcome:	The proposed approach outperforms baseline and achieves 85.5 0.1 and 84.2 0.2 Smatch scores on AMR 2.0 and AMR 3.0.

Copied to clipboard

Zhao Guo, Yuan Ni, Keqiang Wang, Wei Zhu, Guotong Xie

DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function (2023.acl-long)

Challenge:	Existing methods for Chinese spelling error correction focus on local contextual information, thus misleading the user and reducing performance.
Approach:	They propose a global attention decoder that learns the global relationship of correct input characters and candidates of potential error characters.
Outcome:	The proposed method outperforms all competitor models by a large margin of up to 6.2% on three human-annotated datasets.

Copied to clipboard

Haiming Wang, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, Lin Li, Jian Yin, Zhenguo Li, Xiaodan Liang

Implicit Reasoning in Transformers is Reasoning through Shortcuts (2025.findings-acl)

Challenge:	Recent advances in neural theorem-proving resort to large language models and tree searches.
Approach:	They propose a Dynamic-Tree Driven Theorem Solver to accommodate general theoremes by guiding the search procedure with state confidence and proof-level values.
Outcome:	The proposed method outperforms state-of-the-art methods on two popular theorem-proving datasets with a 6.65% improvement on average in terms of success rate.

Copied to clipboard

Tianhe Lin, Jian Xie, Siyu Yuan, Deqing Yang

CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples (2024.findings-acl)

Challenge:	Language models can perform step-by-step reasoning and achieve high accuracy in both in-domain and out-of-domain tests via implicit reasoning.
Approach:	They train GPT-2 from scratch on a curated multi-step mathematical reasoning dataset and conduct analytical experiments to investigate how language models perform implicit reasoning in multi- step tasks.
Outcome:	The proposed model performs better on multi-step tasks than the explicit reasoning model.

Copied to clipboard

Jianrui Zhang, Mu Cai, Tengyang Xie, Yong Jae Lee

DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents (2026.findings-acl)

Challenge:	Using high-performing text and image generation models, we can improve compositional reasoning capabilities for large multimodal models.
Approach:	They propose a framework to improve visio-linguistic compositional reasoning capability for multimodal models by leveraging physical grounding and using image-based models for semantic counterfactual fine-tuning.
Outcome:	The proposed framework outperforms GPT-4V and DALLE-3 on a new dataset and checkpoints.

Copied to clipboard

Kai Shi, Jun Yang, Ni Yang, Binqiang Pan, Qingsong Xie, null Zhangchao, Zhenyu Yang, Tianhuang Su, Haonan Lu

MVP-Bench: Can Large Vision-Language Models Conduct Multi-level Visual Perception Like Humans? (2024.findings-emnlp)

Challenge:	Mobile Phone Agents (MPAs) have attracted huge attention due to their practicability in a multitude of scenarios.
Approach:	They propose a data mixture optimization solution that extrapolates optimal data mixtures from a trainable network.
Outcome:	The proposed model outperforms existing methods on open-source benchmarks and on open source benchmarks.

Copied to clipboard

Guanzhen Li, Yuxi Xie, Min-Yen Kan

Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting (2022.naacl-main)

Challenge:	Existing LVLMs perform visual perception at multiple levels, but they are not able to perform multi-level tasks.
Approach:	They propose a visual–language benchmark to evaluate LVLMs' perceptions . they use manipulated images to examine how LVLs can perform multi-level tasks .
Outcome:	The proposed model performs poorly on high-level perception tasks, the authors show . they also show that current models do not generalize in understanding semantics of synthetic images .

Copied to clipboard

Linzhi Wu, Pengjun Xie, Jie Zhou, Meishan Zhang, Ma Chunping, Guangwei Xu, Min Zhang

WebWalker: Benchmarking LLMs in Web Traversal (2025.acl-long)

Challenge:	Prior research has focused on reducing noise for specific methods to achieve an effective integration.
Approach:	They propose to use token substitution and mixup to improve named entity recognition (NER) using a meta-reweighting strategy, which is extensible and requires little effort.
Outcome:	The proposed method is extensible, imposing little effort on a specific self-augmentation method.

Copied to clipboard

Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, Fei Huang

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks.
Approach:	They propose a benchmark to assess the ability of LLMs to perform web traversal by using an explore-critic paradigm.
Outcome:	The proposed framework mimics human-like web navigation through an explore-critic paradigm and demonstrates the effectiveness of RAG combined with WebWalker in real-world scenarios.

Copied to clipboard

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning (2025.findings-emnlp)

Challenge:	Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach:	They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome:	The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.

Copied to clipboard

Sai Ashish Somayajula, Bokai Hu, Qi Cao, Xin Pan, Pengtao Xie

PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness (2024.findings-emnlp)

Challenge:	Instruction-fine-tuned large language models (LLMs) under 14B parameters underperform on NLU tasks . we explore a framework to improve the NLU capabilities of LLMs .
Approach:	They propose to use Proximal Policy Optimization to improve NLU capabilities . they frame NLU as a reinforcement learning environment and optimize for reward signals .
Outcome:	The proposed framework outperforms supervised fine-tuning on GLUE and superGLUE tasks.

Copied to clipboard

Wenjin Yao, Yidong Wang, Zhuohao Yu, Rui Xie, Shikun Zhang, Wei Ye

Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling (2022.emnlp-main)

Challenge:	Large language models (LLMs) depend on vast amounts of text data sourced from the Internet for their training.
Approach:	They propose a new alignment paradigm that reformulates risky queries into highly relevant yet harmless ones before feeding them into LLMs.
Outcome:	The proposed approach eliminates the high costs of training base LLMs and achieves a promising balance of harmlessness and helpfulness.

Copied to clipboard

Peijie Jiang, Dingkun Long, Yanzhao Zhang, Pengjun Xie, Meishan Zhang, Min Zhang

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Experimental results show that Boundary-Aware BERT can improve Chinese sequence labeling tasks.
Approach:	They propose to encode boundary information directly into pre-trained language models . they propose to use unsupervised boundary information instead of supervised boundary info .
Outcome:	The proposed architecture improves Chinese sequence labeling tasks on ten benchmarks.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation (2025.emnlp-main)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Yubo Xie, Chenkai Wang, Zongyang Ma, Fahui Miao

Specificity-Driven Cascading Approach for Unsupervised Sentiment Modification (D19-1)

Challenge:	Large language models (LLMs) are trained on vast amounts of text from the Internet, but do they understand the viral content that rapidly spreads online?
Approach:	They introduce a dataset for CHinese Internet Meme Explanation that includes popular phrase-based memes from the Chinese Internet.
Outcome:	The proposed dataset includes popular phrase-based memes from the Chinese Internet, annotated with detailed information on their meaning, origin, example sentences, types, etc.

Copied to clipboard

Pengcheng Yang, Junyang Lin, Jingjing Xu, Jun Xie, Qi Su, Xu Sun

Disco-RAG: Discourse-Aware Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Existing methods for unsupervised sentiment modification lack specific information in text generated without parallel data . specificity-driven cascading approach can improve specificity of generated text and content preservation .
Approach:	They propose a specificity-driven cascading approach for unsupervised sentiment modification . the method performs target sentiment addition and content reconstruction independently .
Outcome:	The proposed method outperforms competitive systems by a large margin on Yelp and Amazon datasets.

Copied to clipboard

Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang, Jian Li, Jiangning Zhang, Yabiao Wang

Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography (2026.findings-acl)

Challenge:	Existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents.
Approach:	They propose a framework that explicitly injects discourse signals into the generation process.
Outcome:	Experiments on question answering and long-document summarization benchmarks show the efficacy of the proposed framework.

Copied to clipboard

Jiuan Zhou, Yu Cheng, Yuan Xie, Zhaoxia Yin

Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games (2026.findings-acl)

Challenge:	prevailing methods rely on hand-crafted or pre-specified strategies and struggle to balance efficiency, imperceptibility, and security, particularly at high embedding rates.
Approach:	They propose an agent-driven self-evolving framework that is the first to realize self-changing steganographic strategies by automatically discovering, composing, and adapting strategies at inference time.
Outcome:	The proposed framework achieves 42.2% perplexity and 1.6% anti-steganalysis performance over SOTA methods at high embedding rates.

Copied to clipboard

Keyang Zhong, Junlin Xie, Hefeng Wu, Haofeng Li, Guanbin Li

MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples (2025.coling-main)

Challenge:	Vision-language models have shown impressive capabilities in perceptual tasks . however, they degrade in complex multi-hop reasoning under multi-player game settings .
Approach:	They propose a multi-agent framework for evaluating and synthesizing role-driven game scripts . they use curated and synthetic datasets to model uncertainty and deception .
Outcome:	The proposed model significantly boosts the performance of VLMs in narrative reasoning and hidden fact extraction under uncertain, adversarial, and socially complex conditions.

Copied to clipboard

Shuo Xie, Fangzhi Zhu, Jiahui Wang, Lulu Wen, Wei Dai, Xiaowei Chen, Junxiong Zhu, Kai Zhou, Bo Zheng

Challenge:	Existing preference optimization methods such as DPO and KTO are inherently derived from PPO, requiring a reference model that adds GPU memory resources and relies heavily on abundant preference data.
Approach:	They propose an algorithm that leverages the average likelihood of model responses to fit the reward function and maximizes the utilization of preference data.
Outcome:	The proposed algorithm outperforms DPO, ORPO, and SimPO on MT-Bench and Arena-Hard.

PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling (2024.acl-long)

Copied to clipboard

Xianwei Zhuang, Xuxin Cheng, Liming Liang, Yuxin Xie, Zhichang Wang, Zhiqi Huang, Yuexian Zou

BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models (2026.acl-long)

Challenge:	Spoken language understanding (SLU) suffers from error propagation from automatic speech recognition (ASR) in actual scenarios.
Approach:	They propose a framework which calibrates bias and errors and achieves adaptive-balanced decoupling training by a prototype-based loss model.
Outcome:	The proposed framework outperforms existing approaches and achieves state-of-the-art performance on three datasets.

Copied to clipboard

Xin Gao, Ruiyi Zhang, Meixi Du, Peijia Qin, Pengtao Xie

MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training (2026.acl-long)

Challenge:	despite the success of large language models, their performance in highly specialized domains remains unsatisfactory.
Approach:	They propose a biomedical tool-calling dataset designed for fine-tuning LLMs . the dataset contains 34 frequently used tools from the NCBI, Ensembl, and UniProt databases .
Outcome:	The proposed dataset outperforms commercial LLMs on biomedical domains.

Copied to clipboard

Biao Wu, Yutong Xie, Zeyu Zhang, Vu Minh Hieu Phan, Qi Chen, Ling Chen, Qi Wu

CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models (2025.acl-long)

Challenge:	Existing vision-and-language pretraining methods face challenges in reconstructing pathological features due to limited data.
Approach:	They propose a method that uses masked modeling to enhance visual and linguistic learning.
Outcome:	MMCLIP integrates unpaired data through disease-kind prompts to achieve state-of-the-art performance in zero-shot and fine-tuning across five benchmarks.

Copied to clipboard

Xiaqiang Tang, Jian Li, Keyu Hu, Nan Du, Xiaolong Li, Xi Zhang, Weigao Sun, Sihong Xie

Creating Suspenseful Stories: Iterative Planning with Large Language Models (2024.eacl-long)

Challenge:	Existing benchmarks focus on “factual statements” that rephrase source materials, but ignore “cognitive statements” . evaluating and detecting "faithfulness hallucinations" remains challenging .
Approach:	They propose a framework to assess faithfulness of cognitive statements and introduce a dataset to scale easily across models.
Outcome:	The proposed framework assesses faithfulness of cognitive statements and scales easily across models.

Copied to clipboard

Kaige Xie, Mark Riedl

Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models (2023.findings-emnlp)

Challenge:	Automated story generation has been a challenge in NLP for many years.
Approach:	They propose an iterative-prompting-based method that is grounded in two theoretical foundations of story suspense from cognitive psychology and narratology.
Outcome:	The proposed method works in a fully zero-shot manner and does not rely on any supervised story corpora.

Copied to clipboard

Weize Chen, Xiaoyue Xu, Xu Han, Yankai Lin, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

MatchTime: Towards Automatic Soccer Game Commentary Generation (2024.emnlp-main)

Challenge:	Parameter-shared pre-trained language models (PLMs) have emerged as a successful approach in resource-constrained environments.
Approach:	They propose a method to enhance the inference efficiency of parameter-shared PLMs by pre-training models that can achieve even greater acceleration.
Outcome:	The proposed method improves inference efficiency on autoregressive and autoencoding models.

Copied to clipboard

Jiayuan Rao, Haoning Wu, Chang Liu, Yanfeng Wang, Weidi Xie

A Mixture-of-Experts Model for Antonym-Synonym Discrimination (2021.acl-short)

Challenge:	Existing data on soccer commentary are often unsatisfactory, and the quality of existing data is often poor.
Approach:	They propose to manually annotate timestamps for 49 soccer matches and then use them to create a model to correct and filter existing data.
Outcome:	The proposed model improves the viewing experience of soccer and can be trained on the curated dataset.

Copied to clipboard

Zhipeng Xie, Nan Zeng

MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows (2025.findings-naacl)

Challenge:	Anatomy-synonymy discrimination (ASD) is a crucial problem in lexical semantics and is difficult to distinguish between antonyms and synonyms.
Approach:	They propose a divide-and-conquer strategy where localized experts focus on their own domains to learn their specialties.
Outcome:	The proposed method achieves state-of-the-art performance on the Antonymy-synonymy discrimination task.

Copied to clipboard

Xingjian Zhang, Yutong Xie, Jin Huang, Jinge Ma, Zhaoying Pan, Qijia Liu, Ziyang Xiong, Tolga Ergen, Dongsub Shim, Honglak Lee, Qiaozhu Mei

Challenge:	Scientific innovation is driven by detailed workflows, which include critical steps such as contextualizing literature, generating ideas, validating ideas, and planning new research.
Approach:	They propose to use large language models to extract five key aspects from scientific publications to optimize scientific workflows.
Outcome:	The proposed dataset includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years.

RESEMO: A Benchmark Chinese Dataset for Studying Responsive Emotion from Social Media Content (2024.findings-acl)

Copied to clipboard

Bo Hu, Meng Zhang, Chenfei Xie, Yuanhe Tian, Yan Song, Zhendong Mao

Understanding and Patching Compositional Reasoning in LLMs (2024.findings-acl)

Challenge:	Existing studies on social media text processing do not focus on responsive emotion analysis.
Approach:	They propose a Chinese dataset named ResEmo for responsive emotion analysis, including 3813 posts with 68,781 comments collected from Weibo, the largest social media platform in China.
Outcome:	The proposed dataset includes 3813 posts with 68,781 comments collected from weibo, the largest social media platform in China.

Copied to clipboard

Zhaoyi Li, Gangwei Jiang, Hong Xie, Linqi Song, Defu Lian, Ying Wei

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization (2024.findings-emnlp)

Challenge:	LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
Approach:	They propose a lightweight method to patch compositional reasoning errors via editing the located MHSA modules in LLMs.
Outcome:	The proposed method can be used to patch compositional reasoning errors using MHSA modules located within the layers of the LLMs.

Copied to clipboard

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu, Zheng Liu, Tun Lu, Xing Xie, Ning Gu

Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers (2026.acl-long)

Challenge:	Existing methods to steer LLMs towards human preference suffer from noisy positive-negative training pairs.
Approach:	They propose a distributional preference optimization method which maximizes discrepancy between dispreferred responses and generated non-negative ones.
Outcome:	The proposed method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence.

Copied to clipboard

Xin Chen, Feng Jiang, Yiqian Zhang, Hardy Chen, Shuo Yan, Wenya Xie, Min Yang, Shujian Huang

Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation (2021.emnlp-main)

Challenge:	Existing reasoning-oriented LLMs lack a blind self-thinking paradigm . current models fail to recognize when their reasoning is underinformed or based on ambiguous user instructions .
Approach:	They propose a new reasoning paradigm that transforms LLMs into proactive inquirers that interleave reasoning with clarification.
Outcome:	The proposed model outperforms baseline models on mathematical reasoning, code generation, and document editing.

Copied to clipboard

Jingwei Yi, Fangzhao Wu, Chuhan Wu, Ruixuan Liu, Guangzhong Sun, Xing Xie

Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference (2025.emnlp-main)

Challenge:	Existing news recommendation methods rely on centralized storage of user click behavior data, which may lead to privacy concerns and hazards.
Approach:	They propose a federated learning framework for privacy-preserving news recommendation . they propose aggregation of news representations and user model by a client .
Outcome:	The proposed framework reduces computation and communication cost on clients while keeping promising model performance.

Copied to clipboard

Zhuo Chen, Xinyu Wang, Yong Jiang, Zhen Zhang, Xinyu Geng, Pengjun Xie, Fei Huang, Kewei Tu

Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling (2025.findings-naacl)

Challenge:	Existing methods to detect the knowledge boundary of Vision Large Language Models (VLLMs) are expensive and require indiscriminate retrieval to address questions that require real-time information or are knowledge-intensive.
Approach:	They propose a method that fine-tunes a VLLM on an automatically constructed dataset for boundary identification.
Outcome:	The proposed method reduces indiscriminate retrieval while maintaining or improving the performance of a VLLM on an automatically constructed dataset.

Copied to clipboard

Zile Qiao, Wei Ye, Yong Jiang, Tong Mo, Pengjun Xie, Weiping Li, Fei Huang, Shikun Zhang

Selective Labeling: How to Radically Lower Data-Labeling Costs for Document Extraction Models (2023.emnlp-main)

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced their performance in various natural language processing tasks.
Approach:	They propose a robust and pluggable knowledge rewriter that is optimized for LLM generation by supporting the model's supportiveness.
Outcome:	The proposed model can be used to rewrite knowledge in a supervised manner.

Copied to clipboard

Yichao Zhou, James Wendt, Navneet Potti, Jing Xie, Sandeep Tata

Enhancing Multimodal Retrieval via Complementary Information Extraction and Alignment (2025.acl-long)

Challenge:	a key bottleneck in developing automatic extraction models for visually rich documents is the cost of acquiring labeled documents.
Approach:	They propose selective labeling to provide "yes/no" labels for candidate extractions predicted by a model trained on partially labeled documents.
Outcome:	The proposed method reduces the cost of acquiring labeled data by 10 with a negligible loss in accuracy.

Copied to clipboard

Delong Zeng, Yuexiang Xie, Yaliang Li, Ying Shen

LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts (2025.acl-long)

Challenge:	Existing studies focus on capturing information in multimodal data that is similar to their paired texts, but often ignores the complementary information contained in multimodule data.
Approach:	They propose a multimodal retrieval approach that employs Complementary Information Extraction and Alignment to capture complementary information in multimodal data.
Outcome:	The proposed approach achieves significant improvements over divide-and-conquer models and universal dense retrieval models.

Copied to clipboard

Qibing Ren, Hao Li, Dongrui Liu, Zhanxu Xie, Xiaoya Lu, Yu Qiao, Lei Sha, Junchi Yan, Lizhuang Ma, Jing Shao

Tailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text Generation (2023.acl-long)

Challenge:	Current safety training focuses on teaching models to reject harmful queries, but recent research shows that adversarial attacks or jailbreak methods bypass these safety mechanisms.
Approach:	They propose to use a new attack method to craft multi-turn toxic prompts that gradually lead LLMs to reveal unsafe content.
Outcome:	The proposed method outperforms existing methods in diversity, effectiveness, and efficiency across aligned LLMs.

Copied to clipboard

Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang, Mingfeng Xue, Boxing Chen, Jun Xie

ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents (2025.emnlp-main)

Challenge:	Existing work focuses on generating sentences satisfying pre-specified attributes such as topic and sentiment, yet suffers from increases in storage and inference time.
Approach:	They propose a method that uses a pre-trained continuous vector to generate a fixed pre-trainable language model to satisfy a specified attribute.
Outcome:	The proposed model can achieve improvements on eleven attribute-specific generation tasks with 0.08% extra training parameters.

Copied to clipboard

Qiuchen Wang, Ruixue Ding, Zehui Chen, Weiqi Wu, Shihang Wang, Pengjun Xie, Feng Zhao

Latent Part-of-Speech Sequences for Neural Machine Translation (D19-1)

Challenge:	Existing benchmarks focus on image-based question answering (QA) but ignore the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents.
Approach:	They propose a novel multi-agent RAG framework tailored for complex reasoning across visual documents that employs a Gaussian Mixture Model (GMM)-based hybrid strategy to handle multi-modal retrieval.
Outcome:	The proposed framework outperforms existing methods by over 10% on the competitive ViDoSeek benchmark.

Copied to clipboard

Xuewen Yang, Yingru Liu, Dongliang Xie, Xin Wang, Niranjan Balasubramanian

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs (2026.findings-acl)

Challenge:	Existing methods for learning target side syntactic structure are greedy and only allow them to explore a limited portion of the latent space.
Approach:	They propose a new latent variable model, LaSyn, that captures the co-dependence between syntax and semantics while allowing for effective inference over the latent space.
Outcome:	The proposed model captures the co-dependence between syntax and semantics while allowing for efficient inference over the latent space.

Copied to clipboard

Junjie Li, Xinrui Guo, Yuhao Wu, Roy Ka-Wei Lee, Hongzhi Li, Yutao Xie

FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs (2025.findings-acl)

Challenge:	Existing story generation benchmarks focus mainly on plot quality and fluency, leaving consistency errors unexplored.
Approach:	They propose a benchmark to evaluate narrative consistency in long-form story generation.
Outcome:	Evaluating LLMs, we find consistency errors are common in factual and temporal dimensions . authors say the findings can inform future efforts to improve consistency in long-form narrative generation.

Copied to clipboard

Zengyi Gao, Yukun Cao, Hairu Wang, Ao Ke, Yuan Feng, S Kevin Zhou, Xike Xie

Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification (2025.emnlp-industry)

Challenge:	Existing methods for retrieval-augmented generation struggle with a trade-off between flexibility and retrieval quality.
Approach:	They propose a flexible modular KG-RAG framework that uses query text instead of KGs . they propose to use query text to infer the structural information of reasoning paths .
Outcome:	The proposed method achieves state-of-the-art performance with high efficiency and low resource consumption.

Copied to clipboard

Huike Zou, Haiyang Yang, Yindu Su, Chen Li Yu, Qinye Xie, Chengbao Lian, Qingheng Zhang, Shuguang Han, Fei Huang, Jufeng Chen

Can Hallucination Correction Improve Video-Language Alignment? (2025.findings-acl)

Challenge:	Existing methods for product attribute value identification suffer from cascading errors and lack of generalization capability.
Approach:	They propose a multi-level retrieval scheme that uses products and attribute values as distinct hierarchical levels in PAVI domain.
Outcome:	The proposed method performs better than the state-of-the-art methods on a real-world industrial dataset.

Copied to clipboard

Lingjun Zhao, Mingyang Xie, Paola Cascante-Bonilla, Hal Daumé Iii, Kwonjoon Lee

Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning (2023.findings-acl)

Challenge:	Existing work on hallucination correction for large vision-language models focuses on mitigating hallucisations, but a new approach is needed to improve video-language alignment.
Approach:	They propose a self-training framework learning to correct hallucinations in descriptions that do not align with the video content.
Outcome:	The proposed framework improves video-language alignment by identifying and correcting inconsistencies in descriptions that do not align with the video content.

Copied to clipboard

Genta Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, Daniel Preotiuc-Pietro

An Analysis and Mitigation of the Reversal Curse (2024.emnlp-main)

Challenge:	Existing methods to handle catastrophic forgetting fail to retain knowledge learnt in the past when sudden shifts occur in training data distributions.
Approach:	They propose a learning rate scheduling method that preserves new information without strongly overwriting past knowledge.
Outcome:	The proposed method preserves new information without overwriting past knowledge in a multilingual continuous learning framework.

Copied to clipboard

Ang Lv, Kaiyi Zhang, Shufang Xie, Quan Tu, Yuhan Chen, Ji-Rong Wen, Rui Yan

𝒮2IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction (2025.findings-naacl)

Challenge:	Recent research observes a phenomenon in large language models called the "reversal curse" when dealing with two entities, LLMs excel in handling sequences in the form of "aRb" but when asked "who is Mary Lee Pfeiffer's son?" the LLM exhibits considerable confusion and fails to provide a as the answer .
Approach:	They conduct the first-ever study of how the reversal curse happens in large language models . they find that LLMs excel in handling sequences in the form of "aRb" but struggle to provide a satisfactory answer when asked "who is Mary Lee Pfeiffer's son?"
Outcome:	The proposed study shows that the reversal curse can stem from specific training objectives . the study also shows that a reverse query can be difficult to understand .

Copied to clipboard

Bingfeng Chen, Chenjie Qiu, Yifeng Xie, Boyan Xu, Ruichu Cai, Zhifeng Hao

Towards Interpretable Mental Health Analysis with Large Language Models (2023.emnlp-main)

Challenge:	Aspect Sentiment Quad Prediction (ASQP) is an extractive task that focuses on predicting tuples of sentiment-related elements from a given text.
Approach:	They propose a stepwise syntax integration tuning framework that integrates syntactic structure knowledge into LLMs through a multi-step tuning process.
Outcome:	The proposed framework integrates syntactic structure knowledge into large language models . it decomposes the quadruple generation task into two stages . the proposed framework significantly improves state-of-the-art performance across multiple datasets .

Copied to clipboard

Kailai Yang, Shaoxiong Ji, Tianlin Zhang, Qianqian Xie, Ziyan Kuang, Sophia Ananiadou

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction (2025.findings-emnlp)

Challenge:	Existing studies on large language models lack adequate evaluations and prompting strategies for explainability.
Approach:	They evaluate the mental health analysis and emotional reasoning ability of large language models (LLMs) using 11 datasets across 5 tasks.
Outcome:	The proposed model shows strong in-context learning ability but still has a significant gap with advanced task-specific methods.

Copied to clipboard

Yuanbo Xie, Yingjie Zhang, Tianyun Liu, Duohe Ma, Tingwen Liu

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services (2026.acl-industry)

Challenge:	Jailbreak attacks pose persistent threats to large language models . current safety alignment methods have insufficient safety alignment depth and unrobust internal defense mechanisms.
Approach:	a new safety alignment framework is developed to overcome jailbreak attacks . the framework forces the model to dynamically rebuild its refusal mechanisms from jailbreak states .
Outcome:	a new safety alignment framework reduces attack success rates by approximately 95% on four open-source LLM families and six representative attacks.

Copied to clipboard

Fei zhao, Chonggang Lu, Haofu Qian, Fangcheng Shi, Zijie Meng, Jianzhao Huang, Zheyong Xie, Shaosheng Cao

Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)

Challenge:	Social networking services (SNS) are critical infrastructure for global interaction . supervised fine-tuning (SFT) can improve in-domain performance, but it often induces a ”seesaw” trade-off with out-of-domain robustness .
Approach:	They propose an SNS-oriented LLM with a progressive, RL-prioritized post-training paradigm for fast and stable adaptation.
Outcome:	The proposed model improves over the previous 7B model by 2.41 on average . it also yields an 8.74 average gain over its Qwen3-4B base .

Copied to clipboard

Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu

KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering (2026.acl-long)

Challenge:	Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations.
Approach:	They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability.
Outcome:	The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants .

Copied to clipboard

Zhiyang Li, Ao Ke, Yukun Cao, Xike Xie

Neural Chinese Address Parsing (N19-1)

Challenge:	Existing approaches to Visual Question Answering lack synergistic potential of scene graphs and scene graph.
Approach:	They propose a retrieval-and-fusion pipeline that fuses scene graphs and commonsense graphs to enable multi-modal reasoning.
Outcome:	Experiments on FVQA 2.0+ and MVQA benchmarks show that KG-ViP outperforms existing methods.

Copied to clipboard

Hao Li, Wei Lu, Pengjun Xie, Linlin Li

Challenge:	Recent research shows that systems that perform address parsing can be useful for building e-commerce or product recommendation systems.
Approach:	They propose a task of parsing Chinese addresses into semantically meaningful chunks using a linear-chain structure.
Outcome:	The proposed model is able to capture complex dependencies between labels that cannot be readily captured by a simple linear-chain structure.

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation (2024.emnlp-main)

Copied to clipboard

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen

Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation (2025.acl-long)

Challenge:	Large language models (LLMs) often produce factual errors due to limited internal knowledge.
Approach:	They propose a retrieval-augmented generation framework that generates plan tokens to guide subsequent generation.
Outcome:	The proposed framework improves the accuracy of large language models with external knowledge sources.

Copied to clipboard

Guofu Xie, Xiao Zhang, Ting Yao, Yunsheng Shi

RD-MCSA: A Multi-Class Sentiment Analysis Approach Integrating In-Context Classification Rationales and Demonstrations (2025.emnlp-main)

Challenge:	Existing approaches focus on merging language models tuned on single objectives . existing approaches ignore the impacts of competing objectives on model tuning .
Approach:	They propose a model merging approach that seeks a series of backbone models and merges them according to user preferences.
Outcome:	The proposed approach exhibits strong controllability and Pareto optimality in controllable multi-objective generation.

Copied to clipboard

Haihua Xie, Yinzhu Cheng, Yaqing Wang, Miao He, Mingming Sun

UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)

Challenge:	Existing methods for multi-class sentiment analysis (MCSA) are difficult due to subtle semantic differences between adjacent sentiment levels and the scarcity of high-quality annotated data.
Approach:	They propose a framework to integrate classification rationales with adaptively selected demonstrations to enhance MCSA performance under limited supervision.
Outcome:	The proposed framework outperforms baseline and standard ICL methods on five benchmark datasets.

Copied to clipboard

Yuzhe Yang, Yifei Zhang, Yan Hu, Yilin Guo, Ruoli Gan, Yueru He, Mingcong Lei, Xiao Zhang, Haining Wang, Qianqian Xie, Jimin Huang, Honghai Yu, Benyou Wang

TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction (2024.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have expanded their potential applications in finance.
Approach:	They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions.
Outcome:	The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios.

Copied to clipboard

Kuan-Hao Huang, I-Hung Hsu, Tanmay Parekh, Zhiyu Xie, Zixuan Zhang, Prem Natarajan, Kai-Wei Chang, Nanyun Peng, Heng Ji

An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation (2025.emnlp-main)

Challenge:	Recent studies suggest that event extraction evaluations may not accurately reflect the true performance.
Approach:	They propose a standardized, fair, and reproducible benchmark for event extraction . they use standardized scripts and splits for 16 datasets spanning eight domains .
Outcome:	The proposed benchmarks show that they struggle to achieve satisfactory performance.

Copied to clipboard

Shubham Gandhi, Atharva Naik, Yiqing Xie, Carolyn Rose

Towards Universal Dialogue State Tracking (D18-1)

Challenge:	Recent advances in large language models (LLMs) have demonstrated impressive capabilities across complex reasoning and generation tasks.
Approach:	They evaluate a broad spectrum of collaboration strategies for repository-level code generation where the weak model handles simpler tasks at lower cost and the most challenging tasks are delegated to the strong model.
Outcome:	The proposed model achieves equivalent performance to the strong model while reducing the cost by 40%.

Copied to clipboard

Liliang Ren, Kaige Xie, Lu Chen, Kai Yu

A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction (2022.naacl-main)

Challenge:	Existing approaches to dialogue state tracking are difficult to scale to large dialogue domains.
Approach:	They propose a universal dialogue state tracker that is independent of the number of values and shares parameters across all slots.
Outcome:	The proposed system significantly outperforms state-of-the-art approaches on two datasets.

Copied to clipboard

Yong Xie, Dakuo Wang, Pin-Yu Chen, Jinjun Xiong, Sijia Liu, Oluwasanmi Koyejo

Recall, Expand, and Multi-Candidate Cross-Encode: Fast and Accurate Ultra-Fine Entity Typing (2023.acl-long)

Challenge:	Existing models are vulnerable to adversarial attacks, but their vulnerability is underexplored.
Approach:	They propose to concatenate a perturbed but semantically similar tweet into a model that fools stock prediction models.
Outcome:	The proposed method achieves consistent success rates and causes significant monetary loss in trading simulation by simply concatenating a perturbed but semantically similar tweet.

Copied to clipboard

Chengyue Jiang, Wenyang Hui, Yong Jiang, Xiaobin Wang, Pengjun Xie, Kewei Tu

Towards Robustness of Text-to-SQL Models against Synonym Substitution (2021.acl-long)

Challenge:	State-of-the-art (SOTA) methods use the cross-encoder architecture to concatenate a mention (and its context) with each type and feed it into a pretrained language model (PLM) to score their relevance.
Approach:	They propose to perform entity typing in a recall-expand-filter manner and use a novel model to encode and score all these K candidates in one forward pass.
Outcome:	The proposed method is thousands of times faster than the CE-based architecture and is very efficient in fine-grained (130 types) and coarse-grain (9 types) entity typing.

Copied to clipboard

Yujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver, John R. Woodward, Jinxia Xie, Pengsheng Huang

Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers (2025.emnlp-main)

Challenge:	Existing text-to-SQL models rely on lexical matching between words in NL questions and tokens in table schemas, which may break the schema linking mechanism.
Approach:	They propose a human-curated dataset for text-to-SQL translation . they replace schema-related words with manually selected synonyms .
Outcome:	The proposed model outperforms its counterparts without the defense.

Copied to clipboard

Juncheng Wang, Chao Xu, Cheng Yu, Zhe Hu, Haoyu Xie, Guoqi Yu, Lei Shang, Shujun Wang

Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models (2025.coling-main)

Challenge:	Autoregressive language models excel in text-to-audio generation, but lag behind diffusion models by a non-trivial margin.
Approach:	They propose a framework that integrates multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning.
Outcome:	The proposed framework outperforms existing LM-based and diffusion-based systems in audio synthesis.

Copied to clipboard

Chengkai Huang, Yu Xia, Rui Wang, Kaige Xie, Tong Yu, Julian McAuley, Lina Yao

Context and POS in Action: A Comparative Study of Chinese Homonym Disambiguation in Human and Language Models (2025.emnlp-main)

Challenge:	Retrieval-augmented large language models excel in various NLP tasks but are not always helpful when the knowledge required is absent in the model.
Approach:	They propose to determine whether the model is knowledgeable on a query via inspecting the (contextualized) pre-trained token embeddings of LLMs.
Outcome:	Experiments show that the proposed approach performs better than previous approaches on various benchmarks.

Copied to clipboard

Xie Chenwei, Matthew King-Hang Ma, Wenbo Wang, William Shiyuan Wang

HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapy (2024.acl-long)

Challenge:	Ambiguity is pervasive in language, yet we resolve it effortlessly and unconsciously . ambiguity is common because languages allow words to take on multiple meanings .
Approach:	They build a sentence-pair dataset to examine how context and POS influence homonym resolution in humans and large language models.
Outcome:	The proposed dataset compared humans and large language models to determine how POS and context influence homonym resolution in humans.

Copied to clipboard

Mengxi Xiao, Qianqian Xie, Ziyan Kuang, Zhicheng Liu, Kailai Yang, Min Peng, Weiguang Han, Jimin Huang

ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL (2026.acl-long)

Challenge:	Large Language Models (LLMs) can be used in psychotherapy to overcome challenges such as shame, distrust, and resource scarcity.
Approach:	They propose a cognitive reframing therapy method that uses empathetic dialogue to address deep-rooted negative thoughts and fosters rational, balanced perspectives.
Outcome:	The proposed model outperforms other models in terms of empathy, guidance, and logical coherence, demonstrating its effectiveness and potential positive impact on psychotherapy.

Copied to clipboard

Yaxun Dai, Wenxuan Xie, Xialie Zhuang, Tianyu Yang, Ziyi Liu, Haiqin Yang, Yiying Yang, Yuhang Zhao, Pingfu Chao, Wenhao Jiang

Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment (2024.acl-long)

Challenge:	Current Text-to-SQL reasoning models lack integrated execution feedback during generation.
Approach:	They propose a text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback.
Outcome:	The proposed framework achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale.

Copied to clipboard

Qiming Xie, Zengzhi Wang, Yi Feng, Rui Xia

Personalized Abstractive Summarization by Tri-agent Generation Pipeline (2024.findings-eacl)

Challenge:	Existing large language models often waver in their judgments when faced with follow-up questions . this is a challenge for generating reliable responses and building user trust .
Approach:	They propose a Follow-up Questioning Mechanism and two metrics to quantify this inconsistency . they also develop a framework that teaches large language models to maintain original correct judgments .
Outcome:	The proposed framework improves the general capabilities of large language models by allowing them to maintain original correct judgments.

Copied to clipboard

Wen Xiao, Yujia Xie, Giuseppe Carenini, Pengcheng He

Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation (2022.findings-emnlp)

Challenge:	Existing research shows that large language models do not consistently satisfy users' preferences or expectations.
Approach:	They propose a tri-agent generation pipeline that includes a generator, an instructor, and an editor to enhance output personalization.
Outcome:	The proposed pipeline generates outputs that better meet user expectations on two abstractive summarization datasets.

Copied to clipboard

Jinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun, Xing Xie

Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation (2023.acl-long)

Challenge:	Variational Auto-Encoder (VAE) has been widely adopted in text generation due to its ability to learn flexible representations.
Approach:	They propose a Transformer-based recurrent VAE structure that imposes recurrence on segment-wise latent variables with arbitrarily separated text segments and constructs the posterior distribution with residual parameterization.
Outcome:	The proposed structure can deduce a non-zero lower bound of the KL term and enhance the entanglement of each segment and preceding latent variables, providing a theoretical guarantee of generation diversity.

Copied to clipboard

Zhiwei Cao, Baosong Yang, Huan Lin, Suhang Wu, Xiangpeng Wei, Dayiheng Liu, Jun Xie, Min Zhang, Jinsong Su

An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic Parsing (2023.findings-acl)

Challenge:	Existing methods to improve k-Nearest neighbor machine translation (kNN-MT) are based on the ability to non-parametrically adapt to new domains.
Approach:	They propose a method to boost the datastore retrieval of k-Nearest neighbor machine translation by reconstructing the original datastore.
Outcome:	The proposed method boosts the retrieval and translation quality of k-Nearest neighbor machine translation by reconstructing the original datastore.

Copied to clipboard

Mayank Kulkarni, Aoxiao Zhong, Nicolas Guenon des mesnards, Sahar Movaghati, Mukund Sridhar, He Xie, Jianhua Lu

Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction (2026.findings-eacl)

Challenge:	Task-oriented semantic parsing is a new approach to represent the meaning of user requests with arbitrarily nested semantics.
Approach:	They propose to use knowledge-enhanced encoders to parse user requests with arbitrarily nested semantics.
Outcome:	The proposed model improves performance in low-resource and low-compute settings.

Copied to clipboard

Chong Zhang, Yixi Zhao, Yulu Xie, Chenshu Yuan, Yi Tu, Ya Guo, Mingxu Chai, Ziyu Shen, Yue Zhang, Qi Zhang

Cognitive Analysis Graph-Guided Multi-Turn Safety Enhancement for Large Language Models (2026.findings-acl)

Challenge:	PTLMs have shown remarkable success in multiple information extraction tasks . however, their performance in real-world scenarios falls short of expectations .
Approach:	They propose to use an entity-centric dataset to evaluate PTLMs' performance . they find that inadequate annotations in benchmark datasets lead to spurious correlations .
Outcome:	The proposed dataset disentangles the falsely-coupled segment and entity annotations that arises from the block-level annotation of FUNSD.

Copied to clipboard

Lanxue Zhang, Yuqiang Xie, Fang Fang, Yubing Ren, Xuebin Wang, Yanan Cao

Text Representation Distillation via Information Bottleneck Principle (2023.emnlp-main)

Challenge:	Existing methods to align large language models with human preferences lack relationship consideration between question and response.
Approach:	They propose an inference-time safety alignment framework that explicitly models the cognitive process of problem solving through a structured cognitive analysis graph.
Outcome:	The proposed framework enables transparent, controllable reasoning while maintaining strong safety guarantees.

Copied to clipboard

Yanzhao Zhang, Dingkun Long, Zehan Li, Pengjun Xie

Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers (2023.acl-long)

Challenge:	Pre-trained language models (PLMs) have recently shown great success in text representation field, however, the high computational cost and high-dimensional representation of PLMs pose significant challenges for practical applications.
Approach:	They propose a Knowledge Distillation method that distills large models into smaller representation models to reduce performance degradation after distillation.
Outcome:	Empirical results on two main downstream applications of the proposed method show that it reduces the risk of over-fitting and maximizes the mutual information between the model and the input data.

Copied to clipboard

Linyuan Gong, Chenyan Xiong, Xiaodong Liu, Payal Bajaj, Yiqing Xie, Alvin Cheung, Jianfeng Gao, Xia Song

WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Challenge:	Recent work in NLP has shown that pretrained language models have made notable progress toward generalization to unseen tasks.
Approach:	They propose to pretrain T5 using an auxiliary model to construct more challenging token replacements for the main model to denoise.
Outcome:	The proposed model outperforms similar-sized baseline models on prompted NLP benchmarks and rivals the state-of-the-art model with only 8% of its parameters.

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Influence-based Online Experience Selection for Effective RLHF (2026.acl-long)

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

Copied to clipboard

Yifan Gong, Jing Yao, Xiting Wang, Xunlong Wang, Xiaoyuan Yi, Xing Xie

DPDV: Dual-Pathway and Dual-View Representation Learning for Bridging Information Asymmetry in Text-Video Retrieval (2026.acl-long)

Challenge:	Existing methods for RL fail to establish an interpretable connection between data and optimization objectives.
Approach:	They propose a data selection method that dynamically estimates the influence of individual training samples on policy optimization.
Outcome:	The proposed method significantly improves training effectiveness with fewer optimization steps.

Copied to clipboard

Zequn Xie, Xin Liu, Fangming Feng, Boyun Zhang, Tao Jin

Targeted Distillation for Sentiment Analysis (2025.emnlp-main)

Challenge:	Existing methods for text-based person anomaly search fail to address the pose-semantic gap . asymmetric cross-modal information poses a challenge to accurately establishing retrieval relationships .
Approach:	They propose a video retrieval framework that partitions visual features into two categories based on relevance to the text query and performs effective interaction.
Outcome:	The proposed framework achieves leading retrieval performance on five benchmark datasets.

Copied to clipboard

Yice Zhang, Guangyu Xie, Jingjie Lin, Jianzhu Bao, Qianlong Wang, Xi Zeng, Ruifeng Xu

Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning (2022.coling-1)

Challenge:	Recent studies demonstrate that large language models exhibit remarkable capabilities and achieve state-of-the-art performance in diverse sentiment analysis tasks.
Approach:	They propose a distillation framework that decouples knowledge from alignment and introduces a sentiment analysis benchmark that covers a diverse set of tasks.
Outcome:	The proposed framework improves models' generalization to unseen tasks and their generalization is strong against existing small-scale models.

Copied to clipboard

Xuantao Lu, Jingping Liu, Zhouhong Gu, Hanwen Tong, Chenhao Xie, Junyang Huang, Yanghua Xiao, Wenguang Wang

Challenge:	Existing methods to parse natural language into structured logical expressions have limitations due to paucity of labeled data.
Approach:	They propose a scoring model to automatically learn a model-based reward . they also propose introducing a Chinese-PL/FOL dataset to compensate for paucity of labeled data .
Outcome:	The proposed model outperforms competitors on several datasets.

Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models (2024.naacl-short)

Copied to clipboard

Tingyu Xie, Qi Li, Yan Zhang, Zuozhu Liu, Hongwei Wang

Exploiting Pseudo Image Captions for Multimodal Summarization (2023.findings-acl)

Challenge:	Existing studies exploring the performance of large language models on named entity recognition tasks have focused on training task-specific LLMs for NER.
Approach:	They propose a training-free self-improving framework that utilizes an unlabeled corpus to stimulate the self-learning ability of LLMs.
Outcome:	The proposed framework improves performance on the named entity recognition task by using an unlabeled corpus.

Copied to clipboard

Chaoya Jiang, Rui Xie, Wei Ye, Jinan Sun, Shikun Zhang

The Security Threat of Compressed Projectors in Large Vision-Language Models (2025.findings-emnlp)

Challenge:	Existing approaches to multimodal summarization with multimodal output (MSMO) lack reference images for training, and exposure of image captions during training is inconsistent with MSMO’s task settings.
Approach:	They propose a coarse-to-fine image-text alignment mechanism to identify the most relevant sentence of each image in a document, resembling the role of image captions in capturing visual knowledge.
Outcome:	The proposed method sets up state-of-the-art on all intermodality and intramodality metrics and improves on image recommendation precision.

Copied to clipboard

Yudong Zhang, Ruobing Xie, Xingwu Sun, Jiansheng Chen, Zhanhui Kang, Di Wang, Yu Wang

Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning (2024.naacl-long)

Challenge:	Mainstream VLPs have significant security implications, but their security implications have not been thoroughly examined.
Approach:	a study evaluates the security of visual language projectors by comparing them to uncompressed projector.
Outcome:	The evaluation reveals significant differences in security profiles between compressed and uncompressed projectors.

Copied to clipboard

Yunchao Zhang, Zonglin Di, Kaiwen Zhou, Cihang Xie, Xin Wang

See or Say Graphs: Agent-Driven Scalable Graph Understanding with Vision-Language Models (2026.findings-acl)

Challenge:	Towards Byzantine-robust federated embodied agent learning, we study the attack and defense for the task of vision-and-language navigation (VLN)
Approach:	They propose a new method to defend against a navigation-and-language navigation attack using navigation as wish (NAW) the method provides the server with a 'prompt' of the vision-and language alignment variance between benign and malicious clients so they can be distinguished during training.
Outcome:	The proposed method outperforms other state-of-the-art defense methods on two VLN datasets.

Copied to clipboard

Shuo Han, Yukun Cao, Zezhong Ding, Zengyi Gao, S Kevin Zhou, Xike Xie

ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions (2025.emnlp-industry)

Challenge:	Existing studies have explored textual graph descriptions and visual modalities for VLMs to understand graphs.
Approach:	They propose a unified framework that enhances both scalability and modality coordination in graph understanding by integrating textual and visual modalities.
Outcome:	GraphVista scales to large graphs, 200 larger than those used in existing benchmarks, and consistently outperforms existing textual, visual, and fusion-based methods.

Copied to clipboard

Jingheng Ye, Yong Jiang, Xiaobin Wang, Yinghui Li, Yangning Li, Pengjun Xie, Fei Huang

Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction (2021.findings-acl)

Challenge:	Recent advances in conversational information seeking (CIS) suggest a remedy for the lack of interactive clarification when people face unfamiliar domains.
Approach:	They propose a fully autonomous conversational information-seeking agent that couples large language models with a set of domain-specific tools to provide product demand clarification.
Outcome:	The proposed agent can iterate over 2,000 automatically generated sessions and score high on real-world evaluations without human annotation.

Copied to clipboard

Tianyu Gao, Xu Han, Yuzhuo Bai, Keyue Qiu, Zhiyu Xie, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Selective Preference Optimization via Token-Level Reward Function Estimation (2025.emnlp-main)

Challenge:	Distantly supervised relation extraction (RE) has attracted much attention in the past few years . previous methods to evaluate models manually or directly on autolabeled data have produced inaccurate evaluations .
Approach:	They propose to use distant supervision to generate large-scale autolabeled data . they build manually-annotated test sets for two DS-RE datasets and evaluate models .
Outcome:	The proposed method produces 53% wrong labels at the entity pair level in the popular NYT10 dataset.

Copied to clipboard

Kailai Yang, Zhiwei Liu, Qianqian Xie, Jimin Huang, Erxue Min, Sophia Ananiadou

MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI (2026.findings-acl)

Challenge:	Existing methods for maximizing preference optimization on all available tokens are noisy and inefficient.
Approach:	They propose a selective alignment strategy that centers on efficient key token selection without strong, fine-grained supervision signals.
Outcome:	The proposed strategy outperforms baseline methods on three benchmarks with up to 60% reduction in training hours.

Copied to clipboard

Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, Meng Han

Graph Propagation based Data Augmentation for Named Entity Recognition (2023.acl-short)

Challenge:	Large Language Models (LLMs) are vulnerable to jailbreak, authors say . authors propose a robust, layered defense architecture designed for LLM–tool interactions .
Approach:	They propose a robust, layered defense architecture designed for LLM–tool interactions . they propose XCP-Guard, which employs a three-stage detection pipeline .
Outcome:	The proposed model achieves 96.01% accuracy in identifying adversarial prompts . the model is based on a three-stage detection pipeline that balances efficiency with accuracy .

Copied to clipboard

Jiong Cai, Shen Huang, Yong Jiang, Zeqi Tan, Pengjun Xie, Kewei Tu

Adaptive Textual Label Noise Learning based on Pre-trained Models (2023.findings-emnlp)

Challenge:	Synthetic data suffer from poor diversity, which leads to performance limitations.
Approach:	They propose a graph-propagated data augmentation framework for named entity recognition that uses graph propagation to build relationships between labeled data and unlabeled natural texts.
Outcome:	The proposed framework improves on a low-resource named entity recognition dataset.

Copied to clipboard

Shaohuan Cheng, Wenyu Chen, Fu Mingsheng, Xuanting Xie, Hong Qu

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Challenge:	Existing approaches to learning with noisy labels are limited due to the time and labor costs involved.
Approach:	They propose an adaptive warm-up and hybrid training frameworks to learn with noisy labels based on pre-trained models.
Outcome:	The proposed approach performs comparable or even surpasses state-of-the-art methods in various noise scenarios, including scenarios with the mixture of multiple types of noise.

Copied to clipboard

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation (2026.findings-acl)

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Copied to clipboard

Hanwen Gu, Chao Guo, Junle Wang, Wenda Xie, Yisheng Lv

PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision (2020.findings-emnlp)

Challenge:	Existing methods for long-form complex narrative generation struggle to maintain global narrative coherence and logical consistency.
Approach:	They propose a framework that performs narrative planning on structural graph representations instead of direct sequential text representations.
Outcome:	The proposed model outperforms representative baselines across diverse scenarios.

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Tao Qi, Jianxun Lian, Yongfeng Huang, Xing Xie

OASIS: Mitigating Harmful Fine-tuning Attacks on LLMs via Orthogonal and Adaptive Safety Alignment Strategy (2026.acl-long)

Challenge:	Existing methods for user modeling cannot exploit useful information in unlabeled data . Existing models only model task-specific user information and do not exploit universal user information encoded in user behaviors.
Approach:	They propose to pre-train user models from large-scale unlabeled user behavior data.
Outcome:	The proposed method can model relatedness between historical and future behaviors on two real-world datasets.

Copied to clipboard

Jiayu Tang, Guowei Peng, Qiuhao Xie, Yuning Yang, Xiurui Xie, Guisong Liu

Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates (2021.acl-long)

Challenge:	Existing methods to decouple safety enforcement from harmful feature acquisition rely on perturbation directions that conflict with harmful gradients . harmful fine-tuning attacks pose a significant challenge for service providers aiming to uphold rigorous safety standards.
Approach:	They propose an orthogonal and ad hoc safety alignment strategy to decouple safety enforcement from harmful feature acquisition.
Outcome:	Experiments on four large language models show that OASIS reduces the Harmful Score by 60% compared to baselines while maintaining stable task utility.

Copied to clipboard

Yuqing Xie, Yi-An Lai, Yuanjun Xiong, Yi Zhang, Stefano Soatto

NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks (2026.acl-long)

Challenge:	Using negative flips, we quantify, reduce and analyze regression errors in deep neural networks.
Approach:	They propose to quantify, reduce and analyze regression errors in NLP models by negative flips.
Outcome:	The proposed model update regression has a prevalent presence across tasks in the GLUE benchmark.

Copied to clipboard

Zhihao Luo, Wentao Yan, Jingyu Gong, Min Wang, Zhizhong Zhang, Xuhong Wang, Yuan Xie, Xin Tan

Challenge:	Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and training paradigms.
Approach:	They propose a visual-target trajectory collection pipeline that generates trajectories for GUI and embodied tasks using a single formulation.
Outcome:	The proposed agent outperforms state-of-the-art agents in GUI navigation, spatial affordance prediction, and embodied navigation.

Collective Human Opinions in Semantic Textual Similarity (2023.tacl-1)

Copied to clipboard

Yuxia Wang, Shimin Tao, Ning Xie, Hao Yang, Timothy Baldwin, Karin Verspoor

Experiential Co-Learning of Software-Developing Agents (2024.acl-long)

Challenge:	Existing benchmarks for semantic textual similarity (STS) use averaged human ratings as gold standard.
Approach:	They propose to use a Chinese sentence-to-sentence dataset to study collective human opinions in semantic textual similarity (STS) neither a scalar nor a single Gaussian fits a set of observed judgments adequately, they argue .
Outcome:	The proposed dataset does not capture disagreements on individual instances, but rather the confidence over the aggregate dataset.

Copied to clipboard

Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

ViLBench: A Suite for Vision-Language Process Reward Modeling (2025.emnlp-main)

Challenge:	Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents.
Approach:	They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution.
Outcome:	The proposed framework enables agents to tackle unseen software-developing tasks more effectively.

Copied to clipboard

Haoqin Tu, Weitao Feng, Hardy Chen, Hui Liu, Xianfeng Tang, Cihang Xie

Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations (2021.findings-emnlp)

Challenge:	Despite its advantages, evaluation on PRMs remains less explored, especially in the multimodal domain.
Approach:	They propose to benchmark vision large language models as output reward models and process reward models as process-supervised reward models.
Outcome:	The proposed model outperforms both ORM and PRM on vision-language benchmarks and achieves an average improvement of 3.3% over standard CoT and up to 2.5% over its untrained counterpart on ViLBench.

Copied to clipboard

Yunhe Xie, Kailai Yang, Chengjie Sun, Bingquan Liu, Zhenzhou Ji

CodeRAG-Bench: Can Retrieval Augment Code Generation? (2025.findings-naacl)

Challenge:	Emotion Recognition in Conversation models neglect direct utterance-knowledge interaction and use emotion-indirect auxiliary tasks to augment semantic information.
Approach:	They propose a Knowledge-Interactive Network with sentiment polarity intensity-aware multi-task learning which leverages both commonsense knowledge and sentiment lexicon to augment semantic information.
Outcome:	The proposed model shows 1.04% performance improvement over the state-of-the-art model on the IEMOCAP dataset.

Copied to clipboard

Zora Zhiruo Wang, Akari Asai, Xinyan Velocity Yu, Frank F. Xu, Yiqing Xie, Graham Neubig, Daniel Fried

Shorten After You’re Right: Lazy Length Penalties for Reasoning RL (2026.findings-acl)

Challenge:	Language models excel at generating code, but many programs are difficult to generate using only parametric knowledge.
Approach:	They propose a retrieval-augmented code generation benchmark that provides reproducible evaluations on retrieval and end-to-end code generation performance.
Outcome:	The proposed benchmark covers programming, open-domain, and repository-level tasks and provides reproducible evaluations on retrieval and end-to-end code generation performance.

Copied to clipboard

Danlong Yuan, Tian Xie, Shaohan Huang, Huishuai Zhang, Zhuocheng Gong, Chong Luo, Furu Wei, Dongyan Zhao

LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning (2026.findings-acl)

Challenge:	Existing shortening methods for long reasoning models rely on additional supervision or multi-stage post-training.
Approach:	They propose a lazy length penalty that imposes length pressure on models without extra training stages.
Outcome:	The proposed method significantly reduces response length without extra training stages while maintaining or improving performance.

Copied to clipboard

Zhengjun Huang, Zhoujin Tian, Qintian Guo, Fangyuan Zhang, Yingli Zhou, Di Jiang, Zeying Xie, Xiaofang Zhou

Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion (2023.findings-eacl)

Challenge:	Large Language Models are constrained by limited context windows and lack of persistent memory . recent efforts address these limitations via external memory architectures .
Approach:	They propose an end-to-end agentic memory framework for real-time updating and retrieval that integrates hierarchical and temporal indexing layers.
Outcome:	The proposed framework outperforms established benchmarks in temporal reasoning, multi-session consistency, and retrieval efficiency.

Copied to clipboard

Yi-An Lai, Elman Mansimov, Yuqing Xie, Yi Zhang

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (2024.findings-acl)

Challenge:	a regression error during model upgrade often outweighs the benefits of accuracy gain . a novel method that promotes backward compatibility during model upgrades is proposed .
Approach:	They propose a method that promotes backward compatibility via learning to mix predictions between old and new models.
Outcome:	The proposed method outperforms existing methods and achieves negative flip rate reductions by 73.2% on two model upgrade scenarios.

Copied to clipboard

Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Zheng Li, Ruirui Li, Xianfeng Tang, Suhang Wang, Yu Meng, Jiawei Han

Chat-Driven Text Generation and Interaction for Person Retrieval (2025.emnlp-main)

Challenge:	Existing studies suggest augmenting LLMs with external text corpora to alleviate hallucination problems.
Approach:	They propose to augment large language models with text units retrieved from external knowledge corpora to alleviate the issue.
Outcome:	The proposed framework outperforms baselines on GRBench with three LLMs and shows that iterative reasoning outperformed the baselines.

Copied to clipboard

Zequn Xie, Chuxin Wang, Yeqiang Wang, Sihang Cai, Shulei Wang, Tao Jin

Automatic Song Translation for Tonal Languages (2022.findings-acl)

Challenge:	Text-based person search (TBPS) aims to retrieve images of a target individual from large-scale databases using natural language descriptions.
Approach:	They propose two modules to improve retrieval accuracy and usability . they generate rich pseudo-labels through simulated dialogues with MLLMs .
Outcome:	The proposed method achieves competitive or superior results while eliminating the need for manual captions.

Copied to clipboard

Fenfei Guo, Chen Zhang, Zhirui Zhang, Qixin He, Kejun Zhang, Jun Xie, Jordan Boyd-Graber

Enhancing In-Context Learning via Implicit Demonstration Augmentation (2024.acl-long)

Challenge:	Existing automatic song translation systems for tonal languages do not match the number of notes and beat the original rhythm of the song.
Approach:	They propose three criteria for effective AST: preserving meaning, singability and intelligibility.
Outcome:	The proposed system balances semantics and singability with human evaluations.

Copied to clipboard

Xiaoling Zhou, Wei Ye, Yidong Wang, Chaoya Jiang, Zhemg Lee, Rui Xie, Shikun Zhang

Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns (2023.eacl-main)

Challenge:	In-context learning (ICL) is a new paradigm for pre-trained language models that can make predictions for unseen inputs without updating parameters.
Approach:	They propose a method that enables a model to augmented copies of a demonstration by leveraging their deep feature distribution and a logit calibration mechanism.
Outcome:	The proposed method significantly improves the average and worst-case accuracy across diverse PLMs and tasks.

Copied to clipboard

Zhongbin Xie, Vid Kocijan, Thomas Lukasiewicz, Oana-Maria Camburu

Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation (2026.findings-acl)

Challenge:	a number of studies have focused on gender bias in language models, but these methods fail to detect it.
Approach:	They propose to use gender bias in coreference resolution to evaluate gender bias . they propose to construct an annotated quadruple-level dataset with 4008 instances .
Outcome:	The proposed method is able to detect gender bias in a quadruple dataset . previous methods failed to detect bias or cancel it, the authors argue .

Copied to clipboard

Yubo Jiang, Xin Yang, Abudukelimu Wuerkaixi, Zheming Yuan, Xuxin Cheng, Cao Liu, Ke Zeng, Fengying Xie, Zhiguo Jiang, Haopeng Zhang

AutoFigure-Edit: Generating Editable Scientific Illustrations via Reference-Guided Styling (2026.acl-demo)

Challenge:	Large vision–language models suffer from object-existence hallucinations when multi-step deliberation decouples from visual evidence.
Approach:	They propose a framework that allocates visual computation by uncertainty . they propose highlighting retains global context, while selective zoom-in performs local verification.
Outcome:	The proposed framework reduces the complexity of multimodal reasoning by minimizing the operator trade-off.

Copied to clipboard

Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li, QiYao Sun, Enhao Gu, Yiran Ding, Ke Sun, Fang Guo, Panzhong Lu, Zhiyuan Ning, Yixuan Weng, Yue Zhang

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025.acl-long)

Challenge:	Existing automated systems for scientific illustrations are limited in editability, stylistic controllability, and efficiency.
Approach:	They propose an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images.
Outcome:	The proposed system generates fully editable scientific illustrations from long-form scientific texts while enabling flexible style adaptation through user-provided reference images.

Copied to clipboard

Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, Yuxing Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng

League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models (2026.acl-long)

Challenge:	Long-context modeling is crucial for next-generation language models, but high computational cost of standard attention mechanisms poses significant computational challenges.
Approach:	They propose a natively trained Sparse Attention mechanism that integrates algorithms with hardware-aligned optimizations to achieve efficient long-context modeling.
Outcome:	The proposed model maintains or exceeds Full Attention models across general benchmarks, long-context tasks, and instruction-based reasoning.

Copied to clipboard

Qianhong Guo, Wei Xie, Xiaofang Cai, Enze Wang, Shuoyoucheng Ma, Xiaobing Sun, Tian Xia, Kai Chen, Xiaofeng Wang, Baosheng Wang

MMNMT: Modularizing Multilingual Neural Machine Translation with Flexibly Assembled MoE and Dense Blocks (2023.emnlp-main)

Challenge:	Large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, but reliable evaluation remains a challenge due to data contamination, opaque operation, and subjective preferences.
Approach:	They propose a benchmark-free evaluation paradigm that organizes multiple LLMs into a self-governed league for multi-round mutual evaluation.
Outcome:	Experiments on eight mainstream LLMs in mathematics and programming show that the proposed model can distinguish capabilities while maintaining high internal ranking stability.

Copied to clipboard

Shangjie Li, Xiangpeng Wei, Shaolin Zhu, Jun Xie, Baosong Yang, Deyi Xiong

Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation (2022.findings-naacl)

Challenge:	Mixture-of-Experts (MoE) based sparse architectures are prone to overfitting on low-resource language translation.
Approach:	They propose a modularized MNMT framework that flexibly assembles dense and MoE-based sparse modules to achieve the best of both worlds.
Outcome:	The proposed framework outperforms existing models on low-resource language translation and zero-shot translation on benchmark datasets.

Copied to clipboard

Huan Lin, Baosong Yang, Liang Yao, Dayiheng Liu, Haibo Zhang, Jun Xie, Min Zhang, Jinsong Su

CROSSAGENTIE: Cross-Type and Cross-Task Multi-Agent LLM Collaboration for Zero-Shot Information Extraction (2025.findings-acl)

Challenge:	Existing diverse NMT models lack translation diversity due to a discrepancy between training and inference . despite the success of diverse NTM, there is still a lack of translation diversity .
Approach:	They propose a multi-candidate optimization framework for diverse NMT to deal with this defect.
Outcome:	The proposed framework is transparent to basic diverse NMT models, and universally makes better trade-off between diversity and quality.

Copied to clipboard

Meng Lu, Yuzhang Xie, Zhenyu Bi, Shuxiang Cao, Xuan Wang

Causality-aware Concept Extraction based on Knowledge-guided Prompting (2023.acl-long)

Challenge:	Large language models struggle with producing structured output while maintaining accuracy in zero-shot information extraction (IE)
Approach:	They propose a multi-agent framework that enhances zero-shot IE through multi-task collaboration.
Outcome:	CROSSAGENTIE outperforms state-of-the-art models in structured prediction . the framework significantly reduces inference cost while preserving accuracy .

Copied to clipboard

Siyu Yuan, Deqing Yang, Jinxi Liu, Shuyu Tian, Jiaqing Liang, Yanghua Xiao, Rui Xie

Domain-Specific Data Generation Framework for RAG Adaptation (2026.findings-acl)

Challenge:	Concepts in knowledge graphs (KGs) are far from complete in existing knowledge graph models.
Approach:	They propose to equip a PLM-based extractor with a knowledge-guided prompt to alleviate concept bias by removing spurious co-occurrence correlations from existing knowledge.
Outcome:	The proposed prompt can alleviate concept bias and improve the performance of existing models.

Copied to clipboard

Chris Xing Tian, Weihao Xie, Zhen Chen, Hui Liu, Zhengyuan Yi, Haoliang Li, Shiqi Wang, Siwei Ma

WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning (2026.findings-acl)

Challenge:	Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning capabilities of large language models (LLMs) with external retrieval to produce domain-grounded responses.
Approach:	They propose a scalable and modular data-centric framework for generating domain-grounded question–answer–context triples tailored to diverse RAG adaptation strategies.
Outcome:	The proposed framework generates domain-grounded question–answer–context triples for multiple RAG adaptation strategies.

Copied to clipboard

Xinmiao Yu, Liwen Zhang, Xiaocheng Feng, Pengjun Xie, Jingren Zhou, Bing Qin, Yong Jiang

Altogether: Image Captioning via Re-aligning Alt-text (2024.emnlp-main)

Challenge:	Existing methods for reinforcement learning (RL)-based agents struggle with long-horizon planning and strategy coherence.
Approach:	They propose a reinforcement learning framework that decouples planning and execution.
Outcome:	The proposed framework outperforms baseline and first-step RL frameworks on four benchmarks.

Copied to clipboard

Hu Xu, Po-Yao Huang, Xiaoqing Tan, Ching-Feng Yeh, Jacob Kahn, Christine Jou, Gargi Ghosh, Omer Levy, Luke Zettlemoyer, Wen-tau Yih, Shang-Wen Li, Saining Xie, Christoph Feichtenhofer

Can AI Revise Research Papers with Human Review Feedback? An Empirical Study and Benchmark (2026.findings-acl)

Challenge:	Existing captioning models ignore existing alt-text metadata and lack transparency if training data is unknown.
Approach:	They propose an approach to edit and re-align alt-texts associated with images using human annotation.
Outcome:	The proposed approach improves image captions and improves text-to-image generation and zero-shot image classification tasks.

Copied to clipboard

Zihan Luo, Hong Huang, Jianxun Lian, Yu Chang, Xing Xie, Hai Jin

GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling (2021.acl-long)

Challenge:	Large Language Models (LLMs) are fundamentally reshaping the scientific landscape, transitioning the role of AI from passive tools to active partners within a new paradigm of Human-AI collaboration.
Approach:	They propose a benchmark to evaluate the ability of Large Language Models to improve papers with human feedback.
Outcome:	The proposed benchmark tests the skills of Large Language Models (LLMs) on paper interpretation, experimental implementation, and paper formulation, using authors’ camera-ready versions as natural human baselines.

Copied to clipboard

Libo Qin, Fuxuan Wei, Tianbao Xie, Xiao Xu, Wanxiang Che, Ting Liu

Retrieved In-Context Principles from Previous Mistakes (2024.emnlp-main)

Challenge:	Existing joint models for multi-intent SLU only consider intent detection while ignoring slot filling task.
Approach:	They propose a non-autoregressive model for joint multiple intent detection and slot filling . their framework is 11.5 times faster than existing joint models .
Outcome:	The proposed model is 11.5 times faster than existing models and is faster than current models.

Copied to clipboard

Hao Sun, Yong Jiang, Bo Wang, Yingyan Hou, Yan Zhang, Pengjun Xie, Fei Huang

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)

Challenge:	Recent advances in in-context learning (ICL) have limited customization and inadequate error coverage.
Approach:	They propose a method to retrieve in-context principles from mistakes to improve model performance.
Outcome:	The proposed framework enhances model performance when applied to various prompting strategies.

Copied to clipboard

Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie

Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation (2025.emnlp-main)

Challenge:	Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach:	They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome:	The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.

Copied to clipboard

Li Zhou, Lutong Yu, Dongchu Xie, Shaohuan Cheng, Wenyan Li, Haizhou Li

Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion (2026.acl-long)

Challenge:	Existing studies on cultural understanding with vision-language models primarily emphasize geographic diversity, often overlooking the critical temporal dimensions.
Approach:	They propose a multimodal vision-language model that examines temporal features and cultural image transcreation.
Outcome:	The novel model performs better than non-experts on visual cutural understanding but falls short to human experts on cultural image transcreation task.

Copied to clipboard

Shunian Chen, Xinyuan Xie, Zheshu Chen, Owen Lee, Liyan Zhao, Zhan Su, Qilin Sun, Benyou Wang

Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk (2023.acl-long)

Challenge:	Existing methods for audio captioning lack fine-grained detail and contextual accuracy due to limited unimodal or superficial information.
Approach:	They propose a two-stage automated pipeline that uses pretrained models to extract contextual cues from video . a large language model synthesizes these inputs to generate detailed and context-aware captions .
Outcome:	The proposed method is scalable and generates detailed and context-aware captions on large-scale audio datasets.

Copied to clipboard

Jianquan Li, XiangBo Wu, Xiaokang Liu, Qianqian Xie, Prayag Tiwari, Benyou Wang

Envisioning Future from the Past: Hierarchical Duality Learning for Multi-Turn Dialogue Generation (2023.acl-long)

Challenge:	Pre-trained language models have been widely used in NLP, but their social or cultural impact is under-explored.
Approach:	They build a dataset consisting of numerous Chinese *Comical C*rosstalk scripts, which is for a popular Chinese performing art called ‘Xiangsheng’ or ‘’ since 1800s.
Outcome:	The proposed approach can generate humor as humans do, but it is still in its infancy.

Copied to clipboard

Ang Lv, Jinpeng Li, Shufang Xie, Rui Yan

LoReFact: Bridging the Logic Gap in Fact-Checking (2026.findings-acl)

Challenge:	Existing approaches to generate high quality responses rely on future text .
Approach:	They propose a hierarchical duality learning for dialogue to simulate human cognitive ability . they utilize hierarchically dualities at token hierarchy and utterance hierarchy to simulate duality .
Outcome:	The proposed model can generate high quality responses that connect both previous and follow-up dialogues.

Copied to clipboard

Qiming Xie, Wenjie Zheng, Xiangqing Shen, Rui Xia

Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules (2023.findings-emnlp)

Challenge:	Existing fact-checking methods focus on verification of individual facts, overlooking logical dependencies . a recent study shows that text containing logical errors may still be misjudged as factual .
Approach:	They propose a content–logic coupled factuality evaluation paradigm that conceptualizes factual dimension along two complementary dimensions: content factualism and logic factuity.
Outcome:	The proposed paradigm bridges the gap between factual verification and content factuality . it incorporates the logical dimension and a logic-aware metric to expose and penalize logical fallacies.

Copied to clipboard

Chaojun Xiao, Yuqi Luo, Wenbin Zhang, Pengle Zhang, Xu Han, Yankai Lin, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

DCMKC: A Dual Consistency Matching Approach for Multi-hop Question Answering in LLMs (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have been successful on NLP tasks but require huge parameter sizes and computational resources.
Approach:	They propose a parameter-efficient acceleration method that enhances computational efficiency through plug-and-play compression plugins.
Outcome:	The proposed method saves 53% computational costs using only 0.9% additional parameters with a performance drop of less than 2%.

Copied to clipboard

Xinyi Wang, Yiping Song, Chang Liu, Tingjin Luo, Bo Liu, Zheng Xie, Minlie Huang

Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism (2020.coling-main)

Challenge:	Existing reasoning based on chains of thought (CoTs) fails to find logical connections between reasoning steps .
Approach:	They propose a method to match KG reasoning chains with CoTs based on semantic similarity . they use a knowledge graph to find relevant information "within" each reasoning step .
Outcome:	The proposed method outperforms baselines on multi-answer questions with 5.1% improvement over baselines.

Copied to clipboard

Pan Xie, Zhi Cui, Xiuying Chen, XiaoHui Hu, Jianwei Cui, Bin Wang

Exploring Layer-wise Representations of English and Chinese Homonymy in Pre-trained Language Models (2025.findings-acl)

Challenge:	Existing non-autoregressive models generate target words in parallel, but with a large latency due to the left-to-right dependency.
Approach:	They propose to train a conditional masked translation model and refine results within several iterations to remedy a flawed translation by non-autoregressive models.
Outcome:	The proposed model outperforms state-of-the-art models by over 1 BLEU while using less training computations.

Copied to clipboard

Matthew King-Hang Ma, Xie Chenwei, Wenbo Wang, William Shiyuan Wang

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026.acl-long)

Challenge:	lexical ambiguity can arise due to the misunderstanding of its multiple senses.
Approach:	They propose to use part of speech to examine homonyms in Chinese and English . they find no universal layer depth excels in differentiating homnomial representations .
Outcome:	The proposed model improves contextualization of homonym representations in Chinese . the results challenge the simplistic understanding of their inner workings, the authors say .

Copied to clipboard

Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong

Challenge:	Existing methods for detecting unsafe mobile GUI agents are underexplored.
Approach:	They propose a mobile agent safety detection framework that integrates a formal verifier and a VLM-based contextual judge to detect system-level violations.
Outcome:	The proposed framework achieves 10%–30% improvements over existing approaches across multiple metrics.

On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)

Copied to clipboard

Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie

Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization (2022.findings-emnlp)

Challenge:	under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors.
Approach:	They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients .
Outcome:	The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets.

Copied to clipboard

Dongmin Hyun, Xiting Wang, Chayoung Park, Xing Xie, Hwanjo Yu

Prompt-learning for Fine-grained Entity Typing (2022.findings-emnlp)

Challenge:	Existing models to summarize texts without ground-truth summaries are extractive, which remove words from texts and thus are less flexible than abstractive models.
Approach:	They propose an unsupervised model that extracts words from texts and makes them mutually enhance each other.
Outcome:	The proposed model outperforms both abstractive and extractive models, while generating new words not contained in input texts.

Copied to clipboard

Ning Ding, Yulin Chen, Xu Han, Guangwei Xu, Xiaobin Wang, Pengjun Xie, Haitao Zheng, Zhiyuan Liu, Juanzi Li, Hong-Gee Kim

Fine-Grained Features-based Code Search for Precise Query-Code Matching (2025.coling-main)

Challenge:	Extensive experiments on fine-grained entity typing under fully supervised, few-shot, and zero-shot settings show the effectiveness of prompt-learning.
Approach:	They propose a prompt-learning pipeline that stimulates versatile knowledge of pre-trained language models (PLMs) by constructing entity-oriented verbalizers and templates and conducting masked language modeling.
Outcome:	The proposed approach can be applied to fine-grained entity typing in fully supervised, few-shot, and zero-shot scenarios.

Copied to clipboard

Xinting Zhang, Mengqiu Cheng, Mengzhen Wang, Songwen Gong, Jiayuan Xie, Yi Cai, Qing Li

Denoising Relation Extraction from Document-level Distant Supervision (2020.emnlp-main)

Challenge:	Existing methods to locate code snippets from databases represent the semantics of code and query by averaging the features of each token and word.
Approach:	They propose a fine-grained code search model that consists of a cross-modal encoder, mapping layer and classification layer to capture fine-granular interactions between code and query.
Outcome:	The proposed model significantly outperforms existing methods across multiple programming language datasets.

Copied to clipboard

Chaojun Xiao, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Maosong Sun, Fen Lin, Leyu Lin

On the Automatic Generation of Medical Imaging Reports (P18-1)

Challenge:	Existing methods to generate auto-labeled sentences for relation extraction (RE) are difficult to extend to document-level relation extraction as noise from DS may be even multiplied in documents.
Approach:	They propose a pre-trained model which de-emphasizes noisy DS data via multiple pre-training tasks.
Outcome:	The proposed model can capture useful information from noisy data and achieve promising results on the large-scale DocRE benchmark.

Copied to clipboard

Baoyu Jing, Pengtao Xie, Eric Xing

Challenge:	a complete medical imaging report contains multiple heterogeneous forms of information, including findings and tags . abnormal regions in medical images are difficult to identify and the reports are typically long, containing multiple sentences.
Approach:	They propose a multi-task learning framework which predicts tags and generates paragraphs for abnormal regions in medical images.
Outcome:	The proposed framework can generate long paragraphs on two publicly available datasets.

RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information (2025.acl-long)

Copied to clipboard

Zhiwei Liu, Kailai Yang, Qianqian Xie, Christine de Kock, Sophia Ananiadou, Eduard Hovy

GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding (2026.acl-long)

Challenge:	Current methods for cross-domain misinformation detection focus on in-domain tasks and do not incorporate significant sentiment and emotion features.
Approach:	They propose a retrieval augmented (RAG) LLM framework that incorporates affective information into retrieval databases.
Outcome:	The proposed framework improves on three misinformation benchmarks.

Copied to clipboard

Weicai Long, Yusen Hou, Junning Feng, Houcheng su, Shuo Yang, Donglin Xie, Yanlin Zhang

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models (2026.findings-acl)

Challenge:	Existing benchmarks focus on specialized DNA models trained for sequence prediction or evaluate biological knowledge using text-only questions.
Approach:	They propose a benchmark to evaluate general-purpose LLMs on sequence-based genome inference tasks.
Outcome:	The proposed benchmark outperforms baseline models on sequence-based genome inference tasks.

Copied to clipboard

He Xiao, Qingyao Yang, Dirui Xie, Wendong XU, Zunhai Su, Runming Yang, Haobo Liu, Wenyong Zhou, Zhengwu Liu, Ngai Wong

Can LLMs Automate Fact-Checking Article Writing? (2026.tacl-1)

Challenge:	Large language models with billions of parameters are often over-provisioned . smaller models exhibit lower robustness under extreme low-bit quantization .
Approach:	They propose a hardware-native, metric-driven post-training quantization framework that keeps uniform bit-width within each layer while mixing precision across layers.
Outcome:	LieQ reduces large accuracy gap observed for large language models with billions of parameters while preserving standard multiplication kernels.

Copied to clipboard

Dhruv Sahnan, David Corney, Irene Larraz, Giovanni Zagni, Ruben Miguez, Zhuohan Xie, Iryna Gurevych, Elizabeth Churchill, Tanmoy Chakraborty, Preslav Nakov

TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling (2021.findings-emnlp)

Challenge:	Existing tools for automatic fact-checking produce little or no justification for their assessments . 80% of american adults on major social media platforms regularly encounter news-related content .
Approach:	They propose to extend automatic fact-checking pipeline with automatic generation of full fact- checking articles.
Outcome:	The proposed framework outperforms existing frameworks but lags behind expert-written articles.

Copied to clipboard

Huiyuan Xie, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu, Ann Copestake

RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)

Challenge:	Existing dialog models can generate on-topic utterances but struggle to proactively switch topics.
Approach:	They propose a topic-shift aware dialog benchmark based on human topic shift annotations.
Outcome:	The proposed benchmark enables chatbots to generate topic-shift responses while still struggling to decide when to change topic.

Copied to clipboard

Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie

Dynamic Voting for Efficient Reasoning in Large Language Models (2023.findings-emnlp)

Challenge:	Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates.
Approach:	They propose a ranking-oriented induction model to learn personalized mapping function for each word.
Outcome:	The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages.

Copied to clipboard

Mingfeng Xue, Dayiheng Liu, Wenqiang Lei, Xingzhang Ren, Baosong Yang, Jun Xie, Yidan Zhang, Dezhong Peng, Jiancheng Lv

Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations (2022.emnlp-main)

Challenge:	Multi-path voting methods generate multiple reasoning paths for each problem, causing factual errors and illusion generation.
Approach:	They propose a multi-path voting technique that effectively reduces the number of reasoning paths during multi-path voting while preserving accuracies.
Outcome:	The proposed method outperforms Self-consistency using 24.7% of the number of paths on the LetterConcat task.

Copied to clipboard

Zhihui Xie, Handong Zhao, Tong Yu, Shuai Li

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning (2025.acl-long)

Challenge:	Existing studies show that pre-trained ML-LMs can achieve zero-shot cross-lingual transfer without explicit cross-linguistic supervision.
Approach:	They propose a method to remove language-specific factors from multilingual embedding spaces by using a single value decomposition method with multiple monolingual corpora as input.
Outcome:	The proposed method can boost language agnosticism without finetuning . Empirical results show that it consistently leads to improvements over existing models.

Copied to clipboard

Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, Chen Shen, Jieping Ye

WorldTree V2: A Corpus of Science-Domain Structured Explanations and Inference Patterns supporting Multi-Hop Inference (2020.lrec-1)

Challenge:	Representation Fine-tuning (ReFT) is a proposed method for improving parameter efficiency . however, it yields suboptimal performance, as fixed-position representations have uncertain impact on outputs .
Approach:	They propose a method that fine-tunes critical representations in a low-rank linear subspace while freezing the base model.
Outcome:	The proposed method improves accuracy of LLaMA-2-7B and ReFT by 18.2 and 3.8 on GSM8K.

Copied to clipboard

Zhengnan Xie, Sebastian Thiem, Jaycie Martin, Elizabeth Wainwright, Steven Marmorstein, Peter Jansen

Neural News Recommendation with Multi-Head Self-Attention (D19-1)

Challenge:	Standardized science questions require combining an average of 6 facts and as many as 16 facts to answer and explain.
Approach:	They propose to combine an average of 6 facts and as many as 16 facts to produce an answer for complex questions.
Outcome:	The proposed model is based on a corpus of 5,114 standardized science exam questions . it uses multi-fact explanations that combine science knowledge and world knowledge .

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Suyu Ge, Tao Qi, Yongfeng Huang, Xing Xie

Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service (2025.naacl-industry)

Challenge:	Precisely modeling news and users is critical for news recommendation, and capturing the contexts of words and news is important to learn news and user representations.
Approach:	They propose a neural news recommendation approach with multi-head self-attention to model the interactions between words and news and use multi-headed self- attention to capture relatedness between the news.
Outcome:	The proposed approach can learn representations from news titles by modeling the interactions between words and users and capture relatedness between the news.

Copied to clipboard

Song Wang, Xun Wang, Jie Mei, Yujia Xie, Si-Qing Chen, Wayne Xiong

Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning (2024.lrec-main)

Challenge:	Hallucination is a problem in large language models that produce incorrect output . authors propose a reliable and high-speed production system to detect and rectify hallucinations .
Approach:	They propose a high-speed production system that detects hallucinations in LLMs . they propose NER, natural language inference, span-based detection and a rewriting mechanism .
Outcome:	The proposed system detects a wide range of hallucinations in LLM responses.

Copied to clipboard

Jun Cheng Yang, Zuchao Li, Shuai Xie, Wei Yu, Shijun Li, Bo Du

Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark (2025.coling-main)

Challenge:	Existing approaches to learn multi-modal tasks are based on chain-of-thought . however, human thought processes are non-linear and employ dynamic adjustment and updating mechanisms.
Approach:	They propose a chain-of-thought technique that adjusts the length of the chain to improve the performance of generated prompts.
Outcome:	The proposed model improves multi-modal representation learning in visual, visual, and audio-visual tasks and also has good domain generalization performance due to better reasoning.

Copied to clipboard

Zhikun Xu, Yinghui Li, Ruixue Ding, Xinyu Wang, Boli Chen, Yong Jiang, Haitao Zheng, Wenlian Lu, Pengjun Xie, Fei Huang

To Paraphrase or Not: Efficient Comment Detoxification with Unsupervised Detoxifiability Discrimination (2026.eacl-short)

Challenge:	Recent work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer dynamic questions well.
Approach:	They propose a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest dynamic questions on the Chinese Internet.
Outcome:	The proposed benchmark will be one of the key data resources for improving LLMs’ Chinese question-answering ability in the future.

Copied to clipboard

Jing Ke, Zheyong Xie, Shaosheng Cao, Tong Xu, Enhong Chen

Towards Preference Following in Tool Calling Language Agents (2026.findings-acl)

Challenge:	Existing methods for detoxification of toxic comments are limited by overcorrection and data scarcity . experimental results show that DID outperforms existing methods on academic data and an industrial platform .
Approach:	They propose a paradigm that adaptively conducts filtering or paraphrasing for each toxic comment based on its detoxifiability . they propose 'detoxifiabilities-aware detoxification' that can be trained to filter or paraphrase toxic comments based upon their detoxifikatability based only on detoxificable comments .
Outcome:	Experimental results show that DID outperforms existing methods on academic and industrial data.

Copied to clipboard

Zhi-Yuan Chen, Siyu Lu, Qianlong Xie, Xingxing Wang, Yankai Lin

Better Modeling of Incomplete Annotations for Named Entity Recognition (N19-1)

Challenge:	Currently, large language model (LLM)-based agents can't follow user preferences when calling tools.
Approach:	They propose a benchmark to evaluate agents' ability to identify personalized user preferences from interaction histories and to adhere to these preferences when calling tools.
Outcome:	The proposed model achieves 51.16% accuracy on the APOLLO benchmark, while GPT-4o achieves only 51.13% accuracy.

Copied to clipboard

Zhanming Jie, Pengjun Xie, Wei Lu, Ruixue Ding, Linlin Li

TREA: Tree-Structure Reasoning Schema for Conversational Recommendation (2023.acl-long)

Challenge:	Existing approaches to named entity recognition (NER) assume that the training data is fully annotated with named entity information.
Approach:	They propose a supervised setup for named entity recognition where annotated data is assumed to be available during training.
Outcome:	The proposed approach is able to recognize named entities with incomplete annotations.

Copied to clipboard

Wendi Li, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Ye Yuan, Wenfeng Xie, Dangyang Chen

Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality? (2022.emnlp-main)

Challenge:	Recent reasoning-based models cannot fully figure out complex causal relationships between mentioned entities with external knowledge.
Approach:	They propose a Tree structure Reasoning schEmA that constructs a multi-hierarchical scalable tree as the reasoning structure to clarify the causal relationships between mentioned entities.
Outcome:	Extensive experiments on two public CRS datasets show the proposed model works.

Copied to clipboard

Pei Zhang, Baosong Yang, Hao-Ran Wei, Dayiheng Liu, Kai Fan, Luo Si, Jun Xie

Importance-based Neuron Allocation for Multilingual Neural Machine Translation (2021.acl-long)

Challenge:	Neural machine translation models are often criticized for failures that happen without competency awareness.
Approach:	They propose a method that extends conventional NMT with a self-estimator to translate a source sentence and estimate its competency.
Outcome:	The proposed method performs on translation tasks intact and on quality estimation tasks better than existing methods.

Copied to clipboard

Wanying Xie, Yang Feng, Shuhao Gu, Dong Yu

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration (2025.findings-acl)

Challenge:	Existing approaches to multilingual neural machine translation tend to preserve general knowledge, but ignore language-specific knowledge.
Approach:	They propose to divide model neurons into general and language-specific parts based on their importance across languages.
Outcome:	The proposed model can preserve general knowledge but ignore language-specific knowledge on several languages, and is universal and cost-effective.

Copied to clipboard

Jiahui Geng, Qing Li, Zongxiong Chen, Yuxia Wang, Derui Zhu, Zhuohan Xie, Chenyang Lyu, Xiuying Chen, Preslav Nakov, Fakhri Karray

RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services (2025.emnlp-industry)

Challenge:	Existing safety calibration methods focus on model undersafety, where the model responds to hazardous queries, while neglecting oversafetiness, where models refuse to answer safe queries.
Approach:	They propose safety calibration which addresses both undersafety and oversafetiness by comparing model responses to a novel dataset of 3,600 image-text pairs.
Outcome:	The proposed methods have been used to evaluate safety calibration across image-centric and text-centric scenarios.

Copied to clipboard

Fei Zhao, Chonggang Lu, null Wangyue, Zheyong Xie, Ziyan Liu, Haofu Qian, Jianzhao Huang, Fangcheng Shi, Zijie Meng, Hongcheng Guo, Mingqian He, Xinze Lyu, Zheyu Ye, Weiting Liu, Boyang Wang, Shaosheng Cao

PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models (2026.findings-acl)

Challenge:	Social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement.
Approach:	They propose a domain-specific LLM to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for social networking services.
Outcome:	The proposed model achieves an average improvement of 14.02% across 8 major tasks and 7.56% in bilingual evaluation benchmark, compared with baseline models.

Copied to clipboard

Wenlong Shi, Jianxun Lian, Mingqi Wu, Haiming Qin, Mingyang Zhou, Xing Xie, Naipeng Chao, Hao Liao

Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Challenge:	Existing research focuses on character-level settings and static evaluation formats fail to capture the complexity of everyday social interactions.
Approach:	They propose a dynamic simulation framework for evaluating and improving persona-level role-playing in large language models (LLMs).
Outcome:	The proposed framework leverages user-generated social content to construct a nuanced persona bank and elicits multi-turn, context-rich interactions within simulated social environments.

Copied to clipboard

Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

Speech & Audio in NLP

Challenge:	Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach:	They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome:	The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022.emnlp-main)

Copied to clipboard

Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu

InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning (2025.acl-long)

Challenge:	Structured knowledge grounding (SKG) uses structured knowledge to complete user requests . since inputs and outputs of SKG tasks are heterogeneous, they have been studied separately .
Approach:	They propose a framework that unifies 21 SKG tasks into a text-to-text format . they use unifiedSKG to benchmark T5 with different sizes .
Outcome:	The proposed framework unifies 21 SKG tasks into a text-to-text format . it achieves state-of-the-art performance on almost all of the 21 tasks, the authors show .

Copied to clipboard

Zifu Wan, Yaqi Xie, Ce Zhang, Zhiqiu Lin, Zihan Wang, Simon Stepputtis, Deva Ramanan, Katia P. Sycara

IAPT: Instance-Aware Prompt Tuning for Large Language Models (2024.acl-long)

Challenge:	Large multimodal foundation models perceive objects as indivisible, overlooking the components that constitute them.
Approach:	They propose a novel benchmark for large multimodal foundation models comprising hand-labeled part segmentation annotations and task-oriented instructions to evaluate their performance.
Outcome:	The proposed benchmark improves performance of current models in understanding and executing part-level tasks within everyday contexts.

Copied to clipboard

Wei Zhu, Aaron Tian, Congrui Yin, Yuan Ni, Xiaoling Wang, Guotong Xie

MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language Models (2026.findings-acl)

Challenge:	Existing methods for prompt tuning require many soft tokens to guarantee performance . large language models still require a large amount of GPU memory and computations to fine-tune .
Approach:	They propose to use a parameter-efficient soft prompt generator to generate idiosyncratic soft prompts for each input instruction.
Outcome:	The proposed method outperforms the baselines with comparable tunable parameters and is more efficient than LoRA under the single-backbone multi-tenant setting.

Copied to clipboard

Zhiwen Xie, Xin Wang, Guangyou Zhou, Derek F. Wong

GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding (2025.acl-long)

Challenge:	Existing knowledge graph completion methods struggle to capture structural information in knowledge graphs (KGs) Existing approaches for KGC focus on learning representations of entities and relations through observed structural patterns.
Approach:	They propose a multi-layer Aligned Knowledge Injection model that tightly integrates structured KG information into LLMs through multi-layered alignment.
Outcome:	The proposed method outperforms state-of-the-art methods on benchmark datasets.

Copied to clipboard

Yukun Cao, Shuo Han, Zengyi Gao, Zezhong Ding, Xike Xie, S Kevin Zhou

Semantic Graphs for Generating Deep Questions (2020.acl-main)

Challenge:	Large language models struggle with comprehending graphical structure information through prompts of graph description sequences, especially as the graph size increases.
Approach:	They propose a framework to improve LLMs’ comprehension of both macro- and micro-level graphical information by placing critical graphical data in positions where LLM's exhibit stronger memory performance.
Outcome:	The proposed framework outperforms all other graph description methods in understanding graph structures of varying sizes.

Copied to clipboard

Liangming Pan, Yuxi Xie, Yansong Feng, Tat-Seng Chua, Min-Yen Kan

Counterfactual Inference for Text Classification Debiasing (2021.acl-long)

Challenge:	Existing research has focused on generating factoid questions relevant to one fact obtainable from a single sentence.
Approach:	They propose a framework that first constructs a semantic-level graph and then encodes it by introducing an attention-based GGNN.
Outcome:	The proposed framework captures the global structure of the document and facilitates reasoning over multiple facts.

Copied to clipboard

Chen Qian, Fuli Feng, Lijie Wen, Chunping Ma, Pengjun Xie

Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data (P19-1)

Challenge:	Existing methods to capture unintended dataset biases are expensive and require elaborate balancing strategies.
Approach:	They propose a model-agnostic text classification debiasing framework which can effectively avoid employing data manipulations or designing balancing mechanisms.
Outcome:	The proposed framework can effectively avoid data manipulations or designing balancing mechanisms to capture unintended dataset biases.

Copied to clipboard

Wei Ye, Bo Li, Rui Xie, Zhonghao Sheng, Long Chen, Shikun Zhang

End-to-End Open-Domain Question Answering with BERTserini (N19-4)

Challenge:	Existing methods to perform relation extraction are feature-based or kernel-based, but the results of our study show that they can improve the performance of a baseline model with more than 10% absolute increase in F1-score.
Approach:	They propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss.
Outcome:	The proposed model outperforms the state-of-the-art models on ACE 2005 Chinese and English corpus and significantly improves the performance of a baseline model with more than 10% increase in F1-score.

Copied to clipboard

Wei Yang, Yuqing Xie, Aileen Lin, Xingyu Li, Luchen Tan, Kun Xiong, Ming Li, Jimmy Lin

Question Answering

Challenge:	a new open-domain question answering system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles.
Approach:	They propose an end-to-end question answering system that integrates BERT with an IR reader.
Outcome:	The proposed system improves on a standard benchmark test collection.

A Class-Rebalancing Self-Training Framework for Distantly-Supervised Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Qi Li, Tingyu Xie, Peng Peng, Hongwei Wang, Gaoang Wang

PENS: A Dataset and Generic Framework for Personalized News Headline Generation (2021.acl-long)

Challenge:	Distant supervision reduces the reliance on human annotation in named entity recognition tasks.
Approach:	They propose a class-rebalancing self-training framework for improving distantly-supervised named entity recognition by using a flexible threshold and a hybrid pseudo label.
Outcome:	The proposed model achieves state-of-the-art on five flat and two nested datasets and compares with other methods on the same dataset.

Copied to clipboard

Xiang Ao, Xiting Wang, Ling Luo, Ying Qiao, Qing He, Xing Xie

Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications (2024.findings-acl)

Challenge:	Using a dataset of Microsoft News, we propose a generic framework to personalize a text generator and establish personalized headlines.
Approach:	They propose a generic framework to personalize a news headline generator and establish personalized headlines by leveraging user behavioral data.
Outcome:	The proposed framework is based on user preference data and user preference injections to personalize a text generator and establish personalized headlines.

Copied to clipboard

Junlin Wang, Tianyi Yang, Roy Xie, Bhuwan Dhingra

Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards (2026.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have markedly shifted the landscape of AI, enabling these models to tackle complex, real-world tasks through natural language instructions.
Approach:	They propose a benchmark which evaluates a model's susceptibility to prompt extraction attacks by employing a dual approach to evaluate the effectiveness of existing defenses and the resilience of the models.
Outcome:	The proposed benchmark assesses models under both defenseless and defended scenarios, employing a dual approach to evaluate the effectiveness of existing defenses and the resilience of the models.

Copied to clipboard

Shaoan Xie, Lingjing Kong, Xiangchen Song, Xinshuai Dong, Guangyi Chen, Eric P. Xing, Kun Zhang

Syntax Matters: Towards Spoken Language Understanding via Syntax-Aware Attention (2023.findings-emnlp)

Challenge:	Existing methods for improving reasoning in diffusion language models rely on outcome-based rewards that provide no direct supervision over the denoising process.
Approach:	They propose a method that provides a process-level reinforcement signal over denoising trajectory of diffusion language models.
Outcome:	Experiments on challenging reasoning benchmarks show that the proposed model improves reasoning stability, interpretability and overall performance.

Copied to clipboard

Yifeng Xie, Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Dongsheng Chen

Noisy Parallel Data Alignment (2023.findings-eacl)

Challenge:	Existing studies on SLU systems have focused on integrating syntactic information into language models.
Approach:	They propose a model where attention scopes are constrained based on syntactic relationships.
Outcome:	The proposed model improves on three datasets and can be integrated into other language models to further boost their performance.

Copied to clipboard

Ruoyu Xie, Antonios Anastasopoulos

Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents (2026.findings-acl)

Challenge:	Optical character recognition (OCR) is used to convert endangered language documents into machine-readable data, but its noisy outputs are a challenge for many under-resourced languages.
Approach:	They propose to use optical character recognition (OCR) to convert endangered language documents into machine-readable data by using noisy alignment models.
Outcome:	The proposed model reduces alignment error rate on a state-of-the-art neural-based alignment model up to 59.6%.

Copied to clipboard

Jianming Chen, Yawen Wang, Junjie Wang, Xiaofei Xie, Shoubin Li, Qing Wang, Fanjiang Xu

Investigating Multi-layer Representations for Dense Passage Retrieval (2025.findings-emnlp)

Challenge:	Existing testing methods are system-level and provide limited insight into which capability deficiencies cause task failures.
Approach:	They propose a capability-oriented testing approach that enables failure detection and attribution by seed selection and mutation.
Outcome:	The proposed method detects more failure cases and pinpoints capability-level deficiencies than state-of-the-art baselines, providing more interpretable and actionable guidance for improving embodied agents.

Copied to clipboard

Zhongbin Xie, Thomas Lukasiewicz

Towards Realistic Single-Task Continuous Learning Research for NER (2021.findings-emnlp)

Challenge:	Dense retrieval models adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model contain different kinds of linguistic knowledge and behave differently during fine-tuning.
Approach:	They propose to utilize representations from multiple encoder layers to make up the representation of a document, which they denote Multi-layer Representations (MLR).
Outcome:	The proposed model outperforms dual encoder, ME-BERT and ColBERT in the single-vector retrieval setting and with other advanced training techniques.

Copied to clipboard

Justin Payan, Yuval Merhav, He Xie, Satyapriya Krishna, Anil Ramakrishna, Mukund Sridhar, Rahul Gupta

Named Entity Recognition

Challenge:	Academic datasets are often static and contain data that is annotated all at once based on fixed annotation guidelines.
Approach:	They propose to build a single-task continuous learning dataset from an existing dataset and release it along with the code to the research community.
Outcome:	The proposed model is based on an existing dataset and released to the research community.

Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4 (2026.acl-long)

Copied to clipboard

Chengwu Liu, Yichun Yin, Ye Yuan, Jiaxuan Xie, Botao Li, Siqi Li, Jianhao Shen, Yan Xu, Lifeng Shang, Ming Zhang

ELAINE-medLLM: Lightweight English Japanese Chinese Trilingual Large Language Model for Bio-medical Domain (2025.coling-main)

Challenge:	Existing approaches to solving mathematical problems fall into two broad categories: informal methods and formal methods.
Approach:	They propose to use LLM natural-language reasoning to discover answers . they introduce Discover And Prove framework that rewrites Hard Mode statements into Easy Mode ones for existing ATP provers.
Outcome:	The proposed framework can be used to prove hard mode statements on ATP benchmarks.

Copied to clipboard

Ken Yano, Zheheng Luo, Jimin Huang, Qianqian Xie, Masaki Asada, Chenhan Yuan, Kailai Yang, Makoto Miwa, Sophia Ananiadou, Jun’ichi Tsujii

U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents (2026.findings-acl)

Challenge:	Existing bilingual or multilingual medical LLMs are limited in multilingual data and therefore perform poorly in non-English languages such as Japanese and Chinese.
Approach:	They propose to use a trilingual (English, Japanese, Chinese) large language model adapted for the bio-medical domain to harness the knowledge and abilities of the base model.
Outcome:	The proposed model can support English, Japanese, and Chinese and is adapted for a bio-medical domain.

Copied to clipboard

Jin Su, Runnan Fang, Yeqiu Li, Xiaobin Wang, Shihao Cai, Pengjun Xie, Ningyu Zhang, Fajie Yuan

Measuring Human Contribution in AI-Assisted Content Generation (2026.acl-long)

Challenge:	Existing context-folding methods are designed for single-query or single-intent scenarios.
Approach:	They propose a dynamic context-folding framework tailored to user-centric tasks that preserves fine-grained information through dynamic context folding.
Outcome:	The proposed framework outperforms ReAct and previous folding frameworks on long, noisy tasks.

Copied to clipboard

Yueqi Xie, Tao Qi, Jingwei Yi, Xiyuan Yang, Ryan Whalen, Junming Huang, Qian Ding, Yu Xie, Xing Xie, Fangzhao Wu

MANNER: A Variational Memory-Augmented Model for Cross Domain Few-Shot Named Entity Recognition (2023.acl-long)

Challenge:	generative AI has created a new way to generate content with humans . varying degrees of human contribution in content generation poses significant challenges for the delineation of originality .
Approach:	They propose a framework to measure human contribution in AI-assisted content generation by calculating mutual information between human input and AI-aided output relative to self-information of AI-assist output.
Outcome:	The proposed measure discriminates between varying degrees of human contribution across multiple creative domains and is validated in real-world applications.

Copied to clipboard

Jinyuan Fang, Xiaobin Wang, Zaiqiao Meng, Pengjun Xie, Fei Huang, Yong Jiang

Tool learning via Inference-time Scaling and Cycle Verifier (2025.findings-acl)

Challenge:	Named Entity Recognition (NER) is a fundamental NLP task that aims at classifying mention spans into entity types.
Approach:	They propose a variational memory-augmented few-shot named entity recognition model that uses a memory module to store information from source domain and retrieve relevant information from the memory to augment few-shot task in target domain.
Outcome:	The proposed model can adapt the learned knowledge from source domain to target domain and achieve superior performance on English and Chinese cross domain few-shot NER datasets.

Copied to clipboard

Xiaobo Liang, Wenjin Xie, Juntao Li, Wanfu Wang, Yibin Chen, Kehai Chen, Min Zhang

Challenge:	In inference-time scaling, Chain-of-Thought (CoT) data is scarce or even unavailable.
Approach:	They propose a method which establishes an inference cycle to synthesize user queries and CoT data.
Outcome:	The proposed method achieves a 75.4% pass rate and a 79.6% win rate using small models in StableToolBench.

Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations (2026.findings-acl)

Copied to clipboard

Nanxu Gong, Zixin Chen, Haotian Li, Zishu Zhao, Jianxun Lian, Huamin Qu, Yanjie Fu, Xing Xie

Linguistics & Cognitive NLP

Challenge:	Existing benchmarks measure ToM capability improvement through story-reading, multiple-choice questions from a third-person perspective, while ignoring the first-person, dynamic nature of human-AI interactions.
Approach:	They propose a new paradigm of interactive ToM evaluation with both perspective and metric shifts.
Outcome:	The proposed approach improves the performance of four representative LLM enhancement techniques using real-world datasets and a user study.

Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning (2025.emnlp-main)

Copied to clipboard

Deng Linger, Linghao Zhu, Yuliang Liu, Yu Wang, Qunyi Xie, Jingjing Wu, Gang Zhang, Yingying Zhu, Xiang Bai

Enhancing Automatic Readability Assessment with Pre-training and Soft Labels for Ordinal Regression (2022.findings-emnlp)

Challenge:	Existing methods for generating geometric reasoning data through Chain-of-Thought (CoT) frameworks face three fundamental limitations: 1) lack of high-quality annotations and domain-specific expertise to ensure theorem-grounded diagrams. 2) lack of a coherent model; 3) lack of coherent model.
Approach:	They propose a two-stage Theorem-Validated Reverse Chain-of-Thought Reasoning Synthesis framework that synthesizes theorematic diagrams with structured descriptions and properties.
Outcome:	The proposed framework expands theorem-type coverage, corrects misunderstandings, and enhances geometric reasoning.

Copied to clipboard

Jinshan Zeng, Yudong Xie, Xianglong Yu, John Lee, Ding-Xuan Zhou

TAGS: A Test-Time Generalist–Specialist Framework with Retrieval-Augmented Reasoning and Verification (2026.findings-acl)

Challenge:	Existing models do not exploit ordinal nature of difficulty grades and make little effort for initialization to facilitate fine-tuning.
Approach:	They propose a readability assessment task that assigns a difficulty grade to a text . they use ordinal regression and pairwise relative text difficulty to train the model .
Outcome:	The proposed model outperforms competitive neural models and statistical classifiers on most datasets.

Copied to clipboard

Jianghao Wu, Feilong Tang, Yulong Li, Ming Hu, Haochen Xue, Shoaib Jameel, Zongyuan Ge, Yutong Xie, Imran Razzak

Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval (2022.findings-emnlp)

Challenge:	Existing efforts to improve medical question answering performance follow two directions.
Approach:	They propose a framework that combines a generalist with a domain-specific specialist without any model fine-tuning or parameter updates.
Outcome:	The proposed framework boosts GPT-4o accuracy by 13.8%, deepseek-R1 by 16.8%, and improves a vanilla 7B model from 14.1% to 23.9%.

Copied to clipboard

Wei Zhong, Jheng-Hong Yang, Yuqing Xie, Jimmy Lin

EntSUMv2: Dataset, Models and Evaluation for More Abstractive Entity-Centric Summarization (2023.emnlp-main)

Challenge:	a recent study has shown that dense retrieval methods are suboptimal for capturing contextual similarities in complex data.
Approach:	They propose to combine a structure search method and efficient bi-encoder dense retrieval models to capture contextual similarities.
Outcome:	The proposed model improves on token-level and passage-level dense retrieval tasks.

Copied to clipboard

Dhruv Mehra, Lingjue Xie, Ella Hofmann-Coyle, Mayank Kulkarni, Daniel Preotiuc-Pietro

Neural Cross-Lingual Named Entity Recognition with Minimal Resources (D18-1)

Challenge:	Entity-centric summarization is a form of controllable summarizing that aims to generate a summary for a specific entity given a document.
Approach:	They propose to use a more abstract version of the original entity-centric ENTSUM summarization dataset to generate a shorter annotated summary for downstream users.
Outcome:	The proposed method is more abstract and uses supervised fine-tuning and large-scale instruction tuning to provide more specific and useful summaries for downstream users.

Copied to clipboard

Jiateng Xie, Zhilin Yang, Graham Neubig, Noah A. Smith, Jaime Carbonell

Min Peng, Qianqian Xie, Yanchun Zhang, Hua Wang, Xiuzhen Zhang, Jimin Huang, Gang Tian

Challenge:	Named-entity recognition (NER) models are highly dependent on large amounts of labeled data.
Approach:	They propose a method that finds translations based on bilingual word embeddings . they also propose 'self-attention' which allows for a degree of flexibility with respect to word order .
Outcome:	The proposed method achieves state-of-the-art or competitive performance on common languages with lower resource requirements than previous approaches.

Neural Sparse Topical Coding (P18-1)

Copied to clipboard

Topic Modeling

Challenge:	Topic models with sparsity enhancement are effective at learning discriminative and coherent latent topics of short texts.
Approach:	They propose a novel sparsity-enhanced topic model with back propagation that replaces the inference process with the back propagations, making it easy to explore extensions.
Outcome:	The proposed model outperforms existing methods on Web Snippet and 20Newsgroups datasets.

UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost (2021.naacl-main)

Copied to clipboard

Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai, Tie-Yan Liu

Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision (2025.naacl-long)

Challenge:	Existing approaches to improve the performance of natural language processing models are over-parameterized and overfitted.
Approach:	They propose an approach to integrate dropout techniques into the training of Transformer models.
Outcome:	The proposed approach can achieve 1.5 BLEU improvement on IWSLT14 translation tasks and better accuracy for the classification even using strong pre-trained RoBERTa as backbone.

Copied to clipboard

Zhouhang Xie, Tushar Khot, Bhavana Dalvi Mishra, Harshit Surana, Julian McAuley, Peter Clark, Bodhisattwa Prasad Majumder

Game on Tree: Visual Hallucination Mitigation via Coarse-to-Fine View Tree and Game Theory (2024.emnlp-main)

Challenge:	Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purpose of the discovery (i.e., goal).
Approach:	They propose a goal-oriented latent factor discovery system that integrates LLM’s instruction-following ability with statistical models to handle large, noisy datasets where LLM reasoning alone falls short.
Outcome:	The proposed system improves task performance by 5-52% over baselines and 1.8 times as often as the best alternative, on average, in human evaluation.

Copied to clipboard

Xianwei Zhuang, Zhihong Zhu, Zhanpeng Chen, Yuxin Xie, Liming Liang, Yuexian Zou

A Little Annotation does a Lot of Good: A Study in Bootstrapping Low-resource Named Entity Recognizers (D19-1)

Challenge:	Large vision-language models produce unfaithful visual hallucinations, also known as visual halluinations, which hinders their application in multimodal understanding and decision-making.
Approach:	They propose a plug-and-play train-free decoding algorithm for mitigating visual hallucinations . they leverage visual information to construct a coarse-to-fine visual view tree .
Outcome:	The proposed algorithm reduces visual hallucinations (VH) by leveraging visual information to construct a coarse-to-fine visual view tree (CFTree)

Copied to clipboard

Aditi Chaudhary, Jiateng Xie, Zaid Sheikh, Graham Neubig, Jaime Carbonell

What Have We Achieved on Text Summarization? (2020.emnlp-main)

Challenge:	Named entity recognition models rely on large amounts of labeled data, making them challenging to extend to new, lower-resource languages.
Approach:	They propose a method for bootstrapping named entity recognition models in under-resourced languages . they use cross-lingual transfer learning and targeted annotation of only uncertain entities .
Outcome:	The proposed method achieves competitive accuracy with just one-tenth of training data.

Copied to clipboard

Dandan Huang, Leyang Cui, Sen Yang, Guangsheng Bao, Kun Wang, Jun Xie, Yue Zhang

CCEval: A Representative Evaluation Benchmark for the Chinese-centric Multilingual Machine Translation (2023.findings-emnlp)

Challenge:	Existing methods for text summarization have been investigated, but there are still gaps between them and human professionals.
Approach:	They analyze 8 major sources of errors on 10 representative summarization models manually.
Outcome:	Aiming to gain more understanding of summarization systems with respect to their strengths and limitations on a fine-grained syntactic and semantic level, we use 8 major sources of errors on 10 representative summarizing models.

Copied to clipboard

Lianzhang Lou, Xi Yin, Yutao Xie, Yang Xiang

A Neural Multi-digraph Model for Chinese NER with Gazetteers (P19-1)

Challenge:	Multilingual machine translation (MMT) has gained more importance due to international business development and cross-cultural exchanges.
Approach:	They propose to use Chinese-centric MMT evaluation dataset to build an impartial and representative evaluation benchmark.
Outcome:	The proposed dataset covers more diverse linguistic features than other benchmarks and is highly representative and humancorrelated.

Copied to clipboard

Ruixue Ding, Pengjun Xie, Xiaoyan Zhang, Wei Lu, Linlin Li, Luo Si

From Discourse to Narrative: Knowledge Projection for Event Relation Extraction (2021.acl-long)

Challenge:	Existing approaches to incorporating gazetteers into NER systems rely on manually defined selection strategies or handcrafted templates, which may not lead to optimal effectiveness.
Approach:	They propose to use graph neural networks to automatically learn how to incorporate multiple gazetteers into an NER system by capturing the information that the gazetteer offers.
Outcome:	The proposed model outperforms existing methods on Chinese NER datasets while incorporating rich gazetteer information while resolving ambiguities.

Copied to clipboard

Jialong Tang, Hongyu Lin, Meng Liao, Yaojie Lu, Xianpei Han, Le Sun, Weijian Xie, Jin Xu

Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation (2026.acl-long)

Challenge:	Existing event-centric knowledge graphs rely on explicit connectives to extract relations between events.
Approach:	They propose a knowledge projection paradigm for event relation extraction using commonalities between events.
Outcome:	The proposed method achieves state-of-the-art performance and extrinsic results verify the extracted event relations.

Copied to clipboard

Fangda Ye, Kuicai Dong, Xie Zhifei, Yuxin Hu, Yihang Yin, Shurui Huang, Shikai Dong, Chen Zhang, Jianzhu Bao, Shuicheng Yan

LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search (2025.naacl-long)

Challenge:	Recent agentic search frameworks are text-centric, overlooking multimodal evidence . a pressing task is multimodal long-form generation, a new paper argues .
Approach:	They propose a unified agentic framework for grounded multimodal long-form generation.
Outcome:	The proposed framework is based on a unified agentic framework for grounded multimodal long-form generation.

Copied to clipboard

Di Zhang, Jianbo Wu, Jingdi Lei, Tong Che, Jiatong Li, Tong Xie, Xiaoshui Huang, Shufei Zhang, Marco Pavone, Yuqiang Li, Wanli Ouyang, Dongzhan Zhou

GUI Agents: A Survey (2025.findings-acl)

Challenge:	LLaMA-Berry is an advanced mathematical reasoning framework to enhance the problem-solving ability of large language models (LLMs).
Approach:	They propose a Monte Carlo Tree Search and Self-Refine framework to optimize reasoning paths and a pairwise reward model to evaluate different paths globally.
Outcome:	The proposed framework overcomes inefficiencies and limitations of step-wise and greedy search algorithms, enabling more efficient exploration of solution spaces.

Copied to clipboard

Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, Nesreen K. Ahmed, Puneet Mathur, Seunghyun Yoon, Lina Yao, Branislav Kveton, Jihyung Kil, Thien Huu Nguyen, Trung Bui, Tianyi Zhou, Ryan A. Rossi, Franck Dernoncourt

Challenge:	Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life.
Approach:	They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities.
Outcome:	The proposed framework delineates their perception, reasoning, planning, and acting capabilities.

Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework (2025.findings-naacl)

Copied to clipboard

Qi Zhao, Qi Song, Tian Xie, Haiyue Zhang, Hongyu Yang, Xiangyang Li

EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving (2026.findings-acl)

Challenge:	Existing knowledge enhancement techniques for pre-trained language models (PLMs) introduce noisy entity representations.
Approach:	They propose a knowledge enhancement filter that integrates external knowledge bases to enhance PLMs' ability to capture entity knowledge.
Outcome:	The proposed method achieves the highest F1-score and accuracy while reducing the computational cost by 1.7-2.5x.

Copied to clipboard

Xiyuan Zhou, Xinlei Wang, Yirui He, Ruixi Zou, Yang Wu, Yuheng Cheng, Yulu Xie, Wenxuan Liu, Huan Zhao, Yan Xu, Jinjin Gu, Junhua Zhao

UCS-SQL: Uniting Content and Structure for Enhanced Semantic Bridging In Text-to-SQL (2025.findings-acl)

Challenge:	Existing benchmarks focus on well-defined or abstract reasoning and fail to capture real-world engineering problems.
Approach:	They propose a hierarchical benchmark to evaluate large language models on engineering problems.
Outcome:	The proposed model performs well under well-defined conditions and is based on three levels of difficulty and covers diverse engineering subfields.

Copied to clipboard

Zhenhe Wu, Zhongqiu Li, JieZhangChinaTele JieZhangChinaTele, Zhongjiang He, Jian Yang, Yu Zhao, Ruiyu Fang, Bing Wang, Hongyan Xie, Shuangyong Song, Zhoujun Li

An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism (2022.acl-long)

Challenge:	Existing methods overlook the challenge of effectively transforming structure information from NL to SQL.
Approach:	They propose a text-to-SQL framework that unites content and structure pipes to bridge the gap between NL and SQL.
Outcome:	The proposed framework bridges the gap between natural language questions and SQL by combining content and structure pipes.

Copied to clipboard

Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan

DroidCall: A Dataset for LLM-powered Android Intent Invocation (2025.findings-emnlp)

Challenge:	Existing methods focus on graph representation learning, but decoding is a key part of the process.
Approach:	They propose an EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI) they combine two sets of isomorphic equations to enhance the decoding process .
Outcome:	The proposed algorithm can deliver significant performance improvements even on the most advanced methods while the extra required time is less than 3 seconds.

Copied to clipboard

Weikai Xie, Li Zhang, Shihe Wang, Rongjie Yi, Mengwei Xu

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem (2026.findings-acl)

Challenge:	We present DroidCall, the first training and testing dataset for accurate Android intent invocation.
Approach:	We introduce DroidCall, the first training and testing dataset for accurate Android intent invocation.
Outcome:	The proposed dataset provides a training and testing pipeline for Android intent invocation.

Copied to clipboard

Chengyou Wang, Mingchen Shao, Jingbin Hu, Zeyu Zhu, Hongfei Xue, Bingshen Mu, Xin Xu, Xingyi Duan, Binbin Zhang, Zhu Pengcheng, Chuang Ding, Xiaojun Zhang, Hui Bu, Lei Xie

Parallel Instance Query Network for Named Entity Recognition (2022.acl-long)

Challenge:	despite its linguistic significance, the Wu dialect of Chinese has long been hindered by the lack of large-scale speech data, standardized evaluation benchmarks, and publicly available models.
Approach:	They propose to use WenetSpeech-Wu as a large-scale, multi-dimensionally annotated open-source speech corpus for the Wu dialect of Chinese.
Outcome:	The proposed dataset includes 8,000 hours of speech data and strong open-source models . the proposed dataset is competitive and empirically validated .

Copied to clipboard

Yongliang Shen, Xiaobin Wang, Zeqi Tan, Guangwei Xu, Pengjun Xie, Fei Huang, Weiming Lu, Yueting Zhuang

Knowledge Representation

Challenge:	Named entity recognition is a fundamental task in natural language processing.
Approach:	They propose a method that sets up global and learnable instance queries to extract entities from a sentence in a parallel manner.
Outcome:	The proposed method outperforms existing state-of-the-art models on nested and flat datasets.

ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding (2020.acl-main)

Copied to clipboard

Zhiwen Xie, Guangyou Zhou, Jin Liu, Jimmy Xiangji Huang

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning (2026.findings-acl)

Challenge:	Existing knowledge graph embedding methods are limited in their expressiveness and lack structural information in the embeddable space.
Approach:	They propose to use a relation-aware network to learn query embedding . they first explore the Inception network to further increase interactions between head and relation embedders .
Outcome:	The proposed network improves performance on WN18RR and FB15k-237 datasets.

Copied to clipboard

Yongcan Yu, Lingxiao He, Jian Liang, Kuangpu Guo, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He

Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling (2025.acl-long)

Challenge:	a framework to mitigate spurious optimization signals is proposed for test-time reinforcement learning (TTRL) Reinforcement learning with verifiable rewards (RLVR) is an effective paradigm for improving large language models on structured challenging reasoning tasks.
Approach:	They propose a framework to mitigate spurious optimization signals from label noise . they propose to use a frequency-based sampling strategy to exclude ambiguous samples .
Outcome:	The proposed framework outperforms existing TTRL baselines on three large language models across multiple mathematical reasoning benchmarks.

Copied to clipboard

Yang Yuguang, Yu Pan, Jixun Yao, Xiang Zhang, Jianhao Ye, Hongbin Zhou, Lei Xie, Lei Ma, Jianjun Zhao

Non-Parametric Domain Adaptation for End-to-End Speech Translation (2022.emnlp-main)

Challenge:	Expressive zero-shot voice conversion (VC) aims to modify source timbre to match unseen speaker . existing zero- shot VC systems struggle to reproduce paralinguistic information in highly expressive speech .
Approach:	They propose a framework for expressive zero-shot voice conversion that uses hybrid content encoding and memory-augmented context-aware timbre modeling.
Outcome:	The proposed framework surpasses state-of-the-art VC systems in speech naturalness, speaker similarity, and speaker similarness.

Copied to clipboard

Yichao Du, Weizhi Wang, Zhirui Zhang, Boxing Chen, Tong Xu, Jun Xie, Enhong Chen

Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning (2026.findings-acl)

Challenge:	End-to-end speech translation (E2E-ST) systems have received increasing attention due to its less error propagation, lower latency and fewer parameters.
Approach:	They propose a non-parametric method that leverages in-domain text translation corpus to achieve domain adaptation for E2E-ST systems.
Outcome:	The proposed method outperforms the existing in-domain fine-tuning strategies on the Europarl-ST benchmark.

Copied to clipboard

Can Xie, Ruotong Pan, Xiangyu Wu, Zhang Yunfei, Jiayi Fu, Tingting Gao, Guorui Zhou

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm (2022.acl-long)

Challenge:	Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs).
Approach:	They propose a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals.
Outcome:	Extensive experiments on five mathematical reasoning benchmarks show that the proposed method outperforms strong RLVR baselines on multiple model scales, including 1.5B and 7B.

Copied to clipboard

Shaoyi Huang, Dongkuan Xu, Ian Yen, Yijue Wang, Sung-En Chang, Bingbing Li, Shiyang Chen, Mimi Xie, Sanguthevar Rajasekaran, Hang Liu, Caiwen Ding

SLIM: Subtrajectory-Level Elimination for More Effective Reasoning (2025.findings-emnlp)

Challenge:	Conventional wisdom in pruning Transformer-based language models is that it reduces model expressiveness, but new research shows pruning increases risk of overfitting when performed at the fine-tuning phase.
Approach:	They propose to reduce pruning risk under pretrain-and-finetune paradigm . they propose to use knowledge distillation to improve pruning performance .
Outcome:	The proposed method outperforms the leading competitors on the GLUE benchmark.

Copied to clipboard

Xifeng Yao, Chengyuan Ma, Dongyu Lang, Yinhao Ni, Zhiwei Xu, Huarui Xie, Zihao Chen, Guang Shen, Dandan Tu, Yi Bai, Changzheng Zhang

Aligning Large Language Models for Controllable Recommendations (2024.acl-long)

Challenge:	Notable examples include OpenAI’s o1/o3/o4 series and DeepSeek-R1 .
Approach:	They develop a framework to identify suboptimal subtrajectories based on human-established criteria . they also use a sampling algorithm to select data whose reasoning process is free from suboptimally subtravertories to the highest degree .
Outcome:	The proposed method reduces the number of suboptimal subtrajectories by 25.9% during the inference process.

Copied to clipboard

Wensheng Lu, Jianxun Lian, Wei Zhang, Guanghua Li, Mingyang Zhou, Hao Liao, Xing Xie

ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors (2025.acl-long)

Challenge:	Existing literature focuses on integrating domain-specific knowledge into LLMs to enhance accuracy using a fixed task template.
Approach:	They propose a collection of supervised learning tasks augmented with labels derived from a conventional recommender model to improve LLMs’ proficiency in adhering to recommendation-specific instructions.
Outcome:	The proposed approach significantly improves the capability of LLMs to respond to instructions within recommender systems, reducing formatting errors while maintaining a high level of accuracy.

Copied to clipboard

Yuguo Yin, Yuxin Xie, Wenyuan Yang, Dongchao Yang, Jinghan Ru, Xianwei Zhuang, Liming Liang, Yuexian Zou

HookMoE: A learnable performance compensation strategy of Mixture-of-Experts for LLM inference acceleration (2025.emnlp-main)

Challenge:	Existing multilingual audio-text retrieval schemes suffer from inconsistencies for instance similarity matching across languages.
Approach:	They propose a multilingual audio-text retrieval scheme that mitigates the impact of data distribution error on recall and consistency.
Outcome:	The proposed scheme achieves state-of-the-art performance on recall and consistency metrics for eight mainstream languages, including English.

Copied to clipboard

Cheng Longkai, Along He, Mulin Li, Xie Xueshuo, Tao Li

Neural News Recommendation with Topic-Aware News Representation (P19-1)

Challenge:	Mixture of Experts (MoE) models have been a promising paradigm for scaling model capacity through top-k routing mechanisms.
Approach:	They propose a plug-and-play single-layer compensation framework that strategically inserts a lightweight trainable Hook module immediately preceding selected transformer blocks.
Outcome:	The proposed framework reduces the number of activated experts by more than 50% and achieves a 1.42 inference speed-up during the prefill stage.

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Mingxiao An, Yongfeng Huang, Xing Xie

Language Modeling with Sparse Product of Sememe Experts (D18-1)

Challenge:	Existing methods for learning accurate news representations do not consider topic information in news.
Approach:	They propose a neural news recommendation approach with topic-aware news representations using CNN networks and attention networks to select important words.
Outcome:	The proposed approach is based on a topic-aware news encoder and user encoder.

Copied to clipboard

Yihong Gu, Jun Yan, Hao Zhu, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin

Can Large Language Models Translate Spoken-Only Languages through International Phonetic Transcription? (2025.emnlp-main)

Challenge:	Existing language modeling methods rely on large-scale text data to learn the sequential patterns of words.
Approach:	They propose to use sememes to represent the implicit semantics behind words for language modeling . they propose to employ sememe-driven language models to fine-grained semem-level semantics .
Outcome:	Experiments on language modeling and the downstream application of headline generation show the effectiveness of SDLM.

Copied to clipboard

Jiale Chen, Xuelian Dong, Qihao Yang, Wenxiu Xie, Tianyong Hao

WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics (2026.acl-long)

Challenge:	Existing research on spoken-only languages has focused on low-resource languages . spoken- only languages are among the most vulnerable to extinction .
Approach:	They propose a unified language understanding framework that learns to translate spoken-only languages via in-context learning.
Outcome:	The proposed framework can translate spoken-only languages into high-resource languages using phonetic transcription and automatic dictionary construction and knowledge retrieval.

Copied to clipboard

Chenxu Liu, Yingjie Fu, Wei Yang, Ying Zhang, Tao Xie

MIND: A Large-scale Dataset for News Recommendation (2020.acl-main)

Challenge:	Web applications (web apps) are a key arena for large language models to demonstrate their code generation capabilities and commercial potential.
Approach:	a new benchmark for large language models (LLMs) is designed to provide real-world user requirements and generalizable evaluation metrics.
Outcome:	a new benchmark for large language models (LLMs) provides a real-world, generalizable, and interpretable evaluation score . the benchmark measures user requirements, expression styles and human-preference-aligned weights . a web application can be used to demonstrate its commercial potential, authors say .

Copied to clipboard

Fangzhao Wu, Ying Qiao, Jiun-Hung Chen, Chuhan Wu, Tao Qi, Jianxun Lian, Danyang Liu, Xing Xie, Jianfeng Gao, Winnie Wu, Ming Zhou

Context-Value-Action Architecture for Value-Driven Large Language Model Agents (2026.findings-acl)

Challenge:	Personalized news recommendation is an important technique for personalized news service.
Approach:	They propose to build a large-scale news recommendation dataset from Microsoft News . they demonstrate that news recommendation relies on the quality of news content understanding .
Outcome:	The proposed dataset contains 1 million users and more than 160k English news articles, each of which has rich textual content such as title, abstract and body.

Copied to clipboard

TianZe Zhang, Sirui Sun, Yuhang Xie, Xin Zhang, Zhiqiang Wu, Guojie Song

QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models (2025.naacl-long)

Challenge:	Existing LLMs exhibit behavioral rigidity, a flaw often masked by the self-referential bias of current "LLM-as-a-judge" evaluations.
Approach:	They propose a Context-Value-Action architecture that decouples action generation from cognitive reasoning via a Value Verifier trained on authentic human data to explicitly model dynamic value activation.
Outcome:	The proposed architecture significantly outperforms baseline models on 1.1 million real-world interaction traces on CVABench.

Copied to clipboard

Yudong Zhang, Ruobing Xie, Jiansheng Chen, Xingwu Sun, Zhanhui Kang, Yu Wang

INT: Establishing Information Transfer for Multilingual Intent Detection and Slot Filling (2025.findings-acl)

Challenge:	Currently, large vision-language models are limited in their ability to provide correct answers for multimodal tasks . however, they can still provide correct responses for multiple images associated with a single image . a query-agnostic visual attack (QAVA) provides robust adversarial examples that generate incorrect responses to unspecified and unknown questions.
Approach:	They propose a query-agnostic visual attack to create adversarial examples that generate incorrect answers to unspecified and unknown questions.
Outcome:	The proposed model improves performance on images when the question is unknown compared to known target questions .

Copied to clipboard

Di Wu, Liting Jiang, Bohui Mao, Hongyan Xie, Haoxiang Su, Zhongjiang He, Ruiyu Fang, Shuangyong Song, Hao Huang, Xuelong Li

LEDOM: Reverse Language Model (2026.acl-long)

Challenge:	Existing studies struggle to achieve performance comparable to that on high-resource languages due to inherent linguistic diversity of multilingual SLU tasks.
Approach:	They propose a multilingual information transfer network to solve these challenges . they propose to reformulate SF as a span prediction problem and introduce a slot-matching attention mechanism to achieve slot alignment across languages.
Outcome:	The proposed model outperforms baseline models on the MASSIVE and MASSIV-UG datasets in overall accuracy across all languages.

Copied to clipboard

Xunjian Yin, Sitao Cheng, Yuxi Xie, Xinyu Hu, Li Lin, Xinyi Wang, Liangming Pan, William Yang Wang, Xiaojun Wan

Do PLMs Know and Understand Ontological Knowledge? (2023.acl-long)

Challenge:	Autoregressive language models are trained exclusively left-to-right, yet they are limited in their ability to factorize text.
Approach:	They propose a purely reverse autoregressive language model that factorizes text as a product of left-to-right conditionals.
Outcome:	The proposed model can be used to score forward outputs using reverse posterior estimates.

Copied to clipboard

Weiqi Wu, Chengyue Jiang, Yong Jiang, Pengjun Xie, Kewei Tu

Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation (2022.naacl-main)

Challenge:	Existing studies on pretrained language models focus mainly on factual knowledge, lacking a systematic probing of ontological knowledge.
Approach:	They investigate whether Pretrained Language Models store ontological knowledge and have a semantic un- derstanding of the knowledge rather than rote memorization of the surface form.
Outcome:	The proposed models can memorize certain ontological knowledge and perform logical reasoning with given knowledge according to ontological entailment rules.

Copied to clipboard

Jinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun, Xing Xie

Defense against Prompt Injection Attacks via Mixture of Encodings (2025.naacl-short)

Challenge:	Variational Auto-Encoders are often used for text generation tasks due to the sequential nature of the text.
Approach:	They propose a variational Transformer framework that learns a series of layer-wise latent variables with each inferred from those of lower layers and tightly coupled with the hidden states by low-rank tensor product.
Outcome:	The proposed framework can learn latent variables from lower layers and incorporate more information.

Copied to clipboard

Ruiyi Zhang, David Sullivan, Kyle Jackson, Pengtao Xie, Mei Chen

FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation (2026.acl-long)

Challenge:	Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, but external content embeds malicious instructions that manipulate the LLM’s output.
Approach:	They propose a mixture of encodings defense mechanism which utilizes multiple character encodes to degrade LLM performance on certain NLP tasks.
Outcome:	The proposed method achieves one of the lowest attack success rates under prompt injection attacks while maintaining high performance across all NLP tasks.

Copied to clipboard

Cy Xie

BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents (2026.findings-acl)

Challenge:	Existing approaches to writing formulas rely on static supervised data, which quickly saturates on limited annotations.
Approach:	They propose a self-play framework that breaks the ceiling of supervised fine-tuning by enabling iterative self-improvement without any additional data.
Outcome:	The proposed framework outperforms existing approaches to fine-tuning on static data while enabling iterative self-improvement without additional data.

Copied to clipboard

Litu Ou, Kuan Li, Huifeng Yin, Liwen Zhang, Zhongwang Zhang, Xixi Wu, Rui Ye, Zile Qiao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

Challenge:	Existing work on confidence in LLMs is limited.
Approach:	They propose to use confidence scores to determine model answer quality and encourage model to try again until it reaches satisfactory confidence level.
Outcome:	The proposed methods significantly reduce token consumption while demonstrating competitive performance compared to baseline fixed budget methods.

SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications (D18-1)

Copied to clipboard

Zexuan Zhong, Jiaqi Guo, Wei Yang, Jian Peng, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang

Mitigating Language Confusion through Inference-time Intervention (2025.coling-main)

Challenge:	Existing approaches to generate programs from natural language do not address program aliasing . semantically equivalent programs may have many syntactically different forms .
Approach:	They propose a semantics-based approach to generate regular expressions from natural language.
Outcome:	The proposed approach improves on three public datasets.

Copied to clipboard

Xie Yunfan, Lixin Zou, Dan Luo, Min Tang, Chenliang Li, Xiangyang Luo, Liming Dong

URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models (2025.findings-emnlp)

Challenge:	Existing methods to address the problem of language confusion are incontext learning and supervised fine-tuning (SFT) however, they consume context window space and require extensive data collection.
Approach:	They propose a language-sensitive intervention that detects and assesses language confusion without additional complex mechanisms.
Outcome:	The proposed method detects language confusion and assesses content quality without additional complex mechanisms.

Copied to clipboard

Ruiqi Yan, Xiquan Li, Wenxi Chen, Zhikang Niu, Chen Yang, Ziyang Ma, Kai Yu, Xie Chen

Speech & Audio in NLP

Challenge:	a lack of comprehensive evaluations for SDMs in speech-to-speech (S2S) scenarios is a major challenge for end-to end spoken dialogue models.
Approach:	They propose to provide an extensive evaluation framework for end-to-end spoken dialogue models (SDMs) that includes both cognitive dimensions and paralinguistic cues .
Outcome:	The proposed benchmark is divided into two difficulty levels: basic track and pro track, each comprising 20 test sets, evaluating the spoken dialogue model’s abilities in Understanding, Reasoning, and O**ral conversation.

Efficient Continual Pre-training for Building Domain Specific Large Language Models (2024.findings-acl)

Copied to clipboard

Yong Xie, Karan Aggarwal, Aitzaz Ahmad

Learning Query Adaptive Anchor Representation for Inductive Relation Prediction (2023.findings-acl)

Challenge:	Large language models (LLMs) are typically trained entirely on domain corpus to excel at handling domain-specific tasks.
Approach:	They propose a continual pre-training strategy to build domain-specific LLMs over existing open-domain LLM.
Outcome:	The proposed model outperforms existing LLMs with 10% of corpus size and cost without any degradation on open-domain tasks.

Copied to clipboard

Zhiwen Xie, Yi Zhang, Jin Liu, Guangyou Zhou, Jimmy Huang

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)

Challenge:	Existing methods to infer the missing links between entities are limited to the transductive setting . Query Adaptive Anchor Representation (QAAR) model is based on entity-independent features .
Approach:	They propose a query adaptive anchor representation model which extracts one opening subgraph and performs reasoning by one time for all candidate triples.
Outcome:	The proposed model outperforms state-of-the-art models in relation prediction task.

Copied to clipboard

Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang

Don’t be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System (2021.emnlp-main)

Challenge:	Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive.
Approach:	They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory .
Outcome:	The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient.

Copied to clipboard

Libo Qin, Tianbao Xie, Shijue Huang, Qiguang Chen, Xiao Xu, Wanxiang Che

Neural Machine Translation with Decoding History Enhanced Attention (C18-1)

Challenge:	Consistency Identification has been used for preventing inconsistent response generation, but few efforts have been made to task-oriented dialogue.
Approach:	They propose a dataset for Consistency Identification in task-oriented dialog system.
Outcome:	The proposed dataset is based on a single label and provides fine-grained labels to encourage model to know what inconsistent sources lead to it.

Copied to clipboard

Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Chao Bian

Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction (N18-1)

Challenge:	Neural machine translation with source-side attention has been criticized for its poor memory performance.
Approach:	They propose to use a Decoding History Enhanced Attention mechanism to render NMT models better at selecting both source-side and target-side information.
Outcome:	The proposed model improves by 0:9 BLEU on Chinese-English translation and the state-of-the-art on a larger task.

Copied to clipboard

Ziang Xie, Guillaume Genthial, Stanley Xie, Andrew Ng, Dan Jurafsky

Structured Self-Supervised Pretraining for Commonsense Knowledge Graph Completion (2021.tacl-1)

Challenge:	Existing grammar correction methods are limited in their ability to correct highly local errors . evaluators are unable to distinguish noisy examples from nonsynthesized ones .
Approach:	They propose to synthesize parallel data by noising a clean monolingual corpus . they propose to apply noise to the corpus to syntherize additional noisy examples .
Outcome:	The proposed method can produce almost as strong results as training with nonsynthesized data.

Copied to clipboard

Jiayuan Huang, Yangkai Du, Shuting Tao, Kun Xu, Pengtao Xie

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing (2025.acl-long)

Challenge:	Existing approaches focus on generating concepts that have direct and obvious relationships with existing concepts and lack an ability to generate unobvious concepts.
Approach:	They propose a general graph-to-paths pretraining framework that leverages high-order structures in CKGs to capture high-level relationships between concepts.
Outcome:	The proposed framework can capture high-order relationships between concepts in four special cases: long path, path-to-path, router, and graph-node-path.

Copied to clipboard

Jiakuan Xie, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Challenge:	Existing knowledge editing algorithms are prone to generating original knowledge . despite the fact that many models achieve near-perfect performance, superficial editing remains a challenge .
Approach:	They propose to use "superficial editing" to describe the phenomenon . they investigate the internal mechanisms of the attention module and their corresponding left singular vectors .
Outcome:	The proposed method can modify specific knowledge in a pretrained large language model while ensuring that unrelated knowledge remains unaffected.

The Model Agreed, But Didn’t Learn: Diagnosing Surface Compliance in Large Language Models (2026.findings-acl)

Copied to clipboard

Xiaojie Gu, Ziying Huang, Weicong Hong, Jian Xie, Renze Lou, Kai Zhang

Quantifying Context Overlap for Training Word Embeddings (D18-1)

Challenge:	Large Language Models internalize vast world knowledge as parametric memory, yet inherit the staleness and errors of their source corpora.
Approach:	They propose a framework that subjects models to discriminative self-assessment under diverse contextual pressures to scrutinize subtle behavioral nuances induced by memory modifications.
Outcome:	The proposed framework achieves high benchmarks without overwriting internal beliefs, while recursive modifications accumulate representational residues, triggering cognitive instability and permanently diminishing the reversibility of the model’s memory state.

Copied to clipboard

Yimeng Zhuang, Jinghui Xie, Yinhe Zheng, Xuan Zhu

Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process (2024.emnlp-main)

Challenge:	Experimental results show that word embeddings can be improved using word embeds . word embedings are a popular form of natural language processing .
Approach:	They propose to estimate second order co-occurrence relations based on context overlap . they use the augmented data to enhance word embeddings learning .
Outcome:	The proposed model improves word vectors for word similarity and downstream NLP tasks.

Copied to clipboard

Peng Wang, Xiaobin Wang, Chao Lou, Shengyu Mao, Pengjun Xie, Yong Jiang

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation (2026.acl-long)

Challenge:	Existing studies on large-scale labeled support sets are not feasible in practical scenarios.
Approach:	They introduce a language model-based determinant point process that considers uncertainty and diversity of unlabeled instances for optimal selection.
Outcome:	The proposed method can effectively select canonical examples on 9 NLU and 2 Generation datasets.

Copied to clipboard

Hengyuan Zhang, Shiping Yang, Xiao Liang, Chenming Shang, Yuxuan Jiang, Chaofan Tao, Jing Xiong, Hayden Kwok-Hay So, Ruobing Xie, Angel X. Chang, Ngai Wong

MetaWeighting: Learning to Weight Tasks in Multi-Task Learning (2022.findings-acl)

Challenge:	Existing studies show that stronger models are not always optimal teachers, suggesting a mismatch between the teacher’s output and the student’s learning ability.
Approach:	They propose a method that routes each prompt to its optimal teacher via a query-level router that jointly considers the student models’ learnability and teacher models’ response quality.
Outcome:	The proposed method outperforms baselines on six benchmarks including instruct tuning and math reasoning settings.

Copied to clipboard

Yuren Mao, Zekai Wang, Weiwei Liu, Xuemin Lin, Pengtao Xie

EviReport: From Reasoned Outlines to Evidence Tracked Long-Form Reports (2026.findings-acl)

Challenge:	Existing task weighting methods assign weights only based on training losses, while ignoring the gap between the training loss and generalization loss.
Approach:	They propose a task weighting algorithm which automatically weights the tasks via a learning-to-learn paradigm and a multi-task text classification paradigm.
Outcome:	Extensive experiments show that the proposed method outperforms existing methods in multi-task text classification.

Copied to clipboard

Zihan Liu, Jianhui li, Zexin Wang, Fei Sun, Jingjing LI, Zheyuan Li, Ke Xiang, Hang Cui, Houhua Gong, Changhua Pei, Gaogang Xie

Exploring the Choice Behavior of Large Language Models (2025.findings-acl)

Challenge:	Evidence-intensive reports often produce fluent but under-supported drafts . eviReport is an evidence-grounded workflow for automated long-form report generation .
Approach:	They propose an evidence-tracked workflow that organizes corpus evidence into compact, traceable units and retrieves query-relevant subgraphs into retrieval-ready packages.
Outcome:	The proposed workflow outperforms baselines in factual coverage, factual accuracy and visual evidence integration.

Copied to clipboard

Weidong Wu, Qinlin Zhao, Hao Chen, Lexin Zhou, Defu Lian, Hong Xie

AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are increasingly being adopted across various domains where they help to make choices.
Approach:	They construct a virtual QA platform that includes three different experimental conditions, with four models from GPT and Llama series participating in repeated experiments.
Outcome:	The proposed model includes three experimental conditions and four models from GPT and Llama series.

Copied to clipboard

Chengyou Jia, Minnan Luo, Zhuohang Dang, Qiushi Sun, Fangzhi Xu, Junlin Hu, Tianbao Xie, Zhiyong Wu

Challenge:	Existing agents lack generalization and specialization capabilities for open-ended tasks . specialized generalists are often underdeveloped in real-world environments .
Approach:	They propose a platform to dynamically integrate heterogeneous agents for automating computer tasks . they propose specialized generalist agent MetaAgent with the AgentToken strategy .
Outcome:	The proposed platform expands capabilities of existing agents in generalization and specialization . it can be used to automate open-ended tasks in real-world environments .

Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models (2025.findings-emnlp)

Copied to clipboard

Jian Jornbowrl Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Yi Li

APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation (2026.findings-acl)

Challenge:	Code Large Language Models have limited ability to reason about runtime behavior and understand functionality . authors present a generic framework to support integrating semantic information to code task-relevant prompts .
Approach:	a study examines the role of trace-based semantic information in boosting supervised fine-tuning and post-phase inference of Code LLMs.
Outcome:	a new framework integrates semantic information to code task-relevant prompts . the proposed framework shows that trace-based semantic information boosts reasoning ability .

Copied to clipboard

Dongliang Chen, Xinlin Zhuang, Junjie Xu, Luojian Xie, Zehui Wang, Jiaxi Zhuang, Haolin Yang, Liang Dou, Xiao He, Xingjiao Wu, Ying Qian

Token-level Adaptive Training for Neural Machine Translation (2020.emnlp-main)

Challenge:	APEX optimizes for text-to-image generation by combining learning potential, conflict penalty, and progress need.
Approach:	They propose an algorithm that stabilizes heterogeneous rewards and dynamically schedules objectives . they propose a method that achieves better Pareto trade-offs across four heterogenous objectives based on P3 Adaptive Priorities .
Outcome:	The proposed algorithm achieves better pareto trade-offs across four heterogeneous objectives while maintaining competitive OCR accuracy.

Copied to clipboard

Shuhao Gu, Jinchao Zhang, Fandong Meng, Yang Feng, Wanying Xie, Jie Zhou, Dong Yu

Task Calibration: Calibrating Large Language Models on Inference Tasks (2025.findings-acl)

Challenge:	Existing token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural machine translation (NMT).
Approach:	They propose to assign tokens with different frequencies to target tokens during training to encourage the model to pay more attention to low-frequency tokens.
Outcome:	The proposed model yields consistent improvements on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens.

Copied to clipboard

Yingjie Li, Yun Luo, Xiaotian Xie, Yue Zhang

Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers (2024.acl-long)

Challenge:	Large language models (LLMs) have shown impressive zero-shot performance on inference tasks, however, they may suffer from spurious correlations between input texts and output labels, which limits their ability to reason based purely on general language understanding.
Approach:	They propose a zero-shot and inference-only calibration method inspired by mutual information which recovers LLM performance through task reformulation.
Outcome:	The proposed calibration method improves on 13 benchmarks and prompt templates and can be integrated with other calibration methods.

Copied to clipboard

Jiawen Xie, Pengyu Cheng, Xiao Liang, Yong Dai, Nan Du

Rectifying the Emotional Flow: Aligning Priors and Dynamic Guidance for High-Arousal Text-to-Speech (2026.acl-long)

Challenge:	Existing transformer-based models struggle with long-sequence processing due to computational costs . a framework to enhance long-content processing of transformers is proposed .
Approach:	They propose a framework to enhance long-sequence processing of transformers by three steps . they demonstrate that the framework significantly outperforms prior long-quence processors .
Outcome:	The proposed framework outperforms baseline models on long-sequence summarization and reading comprehension tasks.

Copied to clipboard

Fangming Feng, Dongjie Fu, Zequn Xie, Yu Zhang, Yangyang Wu, Zhou Zhao, Tao Jin

Measuring and Mitigating Local Instability in Deep Neural Networks (2023.findings-acl)

Challenge:	Existing systems suffer from linguistic collapse when pursuing high intensity or fail to meet target emotional levels.
Approach:	They propose an inference framework that introduces a neutral prosody bias and a uniform Classifier-Free Guidance that distorts the acoustic manifold, leading to artifacts.
Outcome:	The proposed framework achieves superior linguistic accuracy and expressiveness without model retraining.

Copied to clipboard

Arghya Datta, Subhrangshu Nandi, Jingcheng Xu, Greg Ver Steeg, He Xie, Anoop Kumar, Aram Galstyan

Challenge:	Uncertain details like random initialization can change the outputs of a trained system with potentially disastrous consequences.
Approach:	They propose a model stability problem by studying how the predictions of a deep neural network change as a consequence of stochasticity in the training process.
Outcome:	The proposed method outperforms data-agnostic methods and is 90% cheaper than the gold standard.

GL-CLeF: A Global–Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding (2022.acl-long)

Copied to clipboard

Libo Qin, Qiguang Chen, Tianbao Xie, Qixin Li, Jian-Guang Lou, Wanxiang Che, Min-Yen Kan

Knowledge Mechanisms in Large Language Models: A Survey and Perspective (2024.findings-emnlp)

Challenge:	Existing approaches to zero-shot cross-lingual spoken language understanding rely on shared parameters, which can only perform implicit alignment across languages.
Approach:	They propose a global-local contrastive learning framework to achieve a fine-grained cross-lingual transfer . they employ bilingual dictionaries to construct multilingual views of the same utterance .
Outcome:	Experiments on MultiATIS++ show that GL-CLeF achieves the best performance . GL is based on dictionaries and encourages representations to be more similar than negative example pairs .

Copied to clipboard

Mengru Wang, Yunzhi Yao, Ziwen Xu, Shuofei Qiao, Shumin Deng, Peng Wang, Xiang Chen, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization (2025.findings-acl)

Challenge:	Using large language models, we can understand knowledge mechanisms in LLMs for learning, storage, utilization, and evolution.
Approach:	They propose to analyze knowledge mechanisms in Large Language Models (LLMs) they examine utilization, evolution, and the potential dark knowledge (hypothesis) they hope to help understand knowledge in LLMs and provide insights for future research .
Outcome:	The proposed model can be used to analyze the evolution of parametric knowledge in LLMs.

Copied to clipboard

Yuhan Fu, Ruobing Xie, Xingwu Sun, Zhanhui Kang, Xirong Li

Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage (2025.naacl-long)

Challenge:	Multimodal Large Language Models (MLLMs) are known to hallucinate, which limits their practical applications.
Approach:	They propose a method that uses three types of preference pairs to target hallucinations from their diverse forms and causes.
Outcome:	The proposed method surpasses most state-of-the-art methods and shows potential for further improvements.

Copied to clipboard

Kaige Xie, Philippe Laban, Prafulla Kumar Choubey, Caiming Xiong, Chien-Sheng Wu

RaFe: Ranking Feedback Improves Query Rewriting for RAG (2024.findings-emnlp)

Challenge:	Existing evaluations of retrieval-augmented generation systems are limited . sub-question coverage measures how well a RAG system addresses different facets of a question.
Approach:	They propose a framework for evaluation based on sub-question coverage . they propose to decompose questions into sub-questions and classify them into three types .
Outcome:	The proposed evaluation framework measures how well a RAG system addresses different facets of a question.

Copied to clipboard

Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion Cause (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved to enhance document retrieval by reformulating queries.
Approach:	They propose a framework for training query rewriting models that leverages a reranker framework.
Outcome:	The proposed framework provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models.

Copied to clipboard

Guimin Hu, Zhihong Zhu, Daniel Hershcovich, Lijie Hu, Hasti Seifi, Jiayuan Xie

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Challenge:	Existing studies treat emotion recognition and emotion cause extraction as two individual problems, ignoring their natural causality.
Approach:	They propose a Unified Multimodal Emotion recognition and Emotion-Cause analysis framework to explore the causality between emotion and emotion cause.
Outcome:	The proposed framework reformulates MERC and MECPE tasks as mask prediction problems and unifies them with a causal prompt template.

Copied to clipboard

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen

Challenge:	a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach:	They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome:	The proposed benchmarks show that the current models perform worse than the human ceiling.

Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing (2024.lrec-main)

Copied to clipboard

Zhenyu Qian, Yiming Qian, Yuting Song, Fei Gao, Hai Jin, Chen Yu, Xia Xie

iPET: An Interactive Emotional Companion Dialogue System with LLM-Powered Virtual Pet World Simulation (2025.acl-demo)

Challenge:	Existing methods for graph processing rely on assumptions about data relations that are inadequate when handling large and complex graph data.
Approach:	They propose a large language model enhanced by an uncertainty-aware module to provide a confidence score on the generated graph data.
Outcome:	The proposed approach surpasses state-of-the-art algorithms by a substantial margin on ten datasets.

Copied to clipboard

Zheyong Xie, Shaosheng Cao, Zuozhu Liu, Zheyu Ye, Zihan Niu, Chonggang Lu, Tong Xu, Enhong Chen, Zhe Xu, Yao Hu, Wei Lu

Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables (2021.findings-emnlp)

Challenge:	Existing approaches to role-playing emotional companion products lack sustained personalization and contextual adaptability, limiting their effectiveness in real-world settings.
Approach:	They propose a virtual pet agent that can enhance user engagement through rich, dynamic pet behaviors and interactions tailored to individual preferences.
Outcome:	The proposed system has been deployed in a real-world, non-commercial product for 200 days and has demonstrated its effectiveness in practical applications.

Copied to clipboard

Weizhi Wang, Zhirui Zhang, Yichao Du, Boxing Chen, Jun Xie, Weihua Luo

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)

Challenge:	Existing methods to achieve zero-shot translation suffer from spurious correlations between output language and language invariant semantics.
Approach:	They propose a method that denoizes the autoencoder objective based on pivot language into traditional training objective to improve translation accuracy on zero-shot directions.
Outcome:	The proposed method eliminates spurious correlations and outperforms state-of-the-art methods on two benchmark machine translation datasets.

Copied to clipboard

Haoyu Han, Yaochen Xie, Hui Liu, Xianfeng Tang, Sreyashi Nag, William Headden, Yang Li, Chen Luo, Shuiwang Ji, Qi He, Jiliang Tang

Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation (2020.acl-main)

Challenge:	Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences.
Approach:	They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks.
Outcome:	Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks.

Copied to clipboard

Ning Ding, Dingkun Long, Guangwei Xu, Muhua Zhu, Pengjun Xie, Xiaobin Wang, Haitao Zheng

Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario (2024.findings-emnlp)

Challenge:	Fully supervised neural approaches have achieved significant progress in the task of Chinese word segmentation (CWS) however, they suffer from the cross-domain issue when they come to processing of out-of-domain data.
Approach:	They propose to use Chinese word as a target domain for distant annotation and adversarial training to reduce noise and maximize utilization of the source domain information.
Outcome:	The proposed method outperforms existing state-of-the-art methods on real-world datasets and significantly outperformed previous state- of-the art methods.

Copied to clipboard

Feiteng Mu, Yong Jiang, Liwen Zhang, Liuchu Liuchu, Wenjie Li, Pengjun Xie, Fei Huang

Challenge:	Existing tool learning methods focus on selecting the most effective tool from a wide array of options, often overlooking cost-effectiveness.
Approach:	They propose to predict query performance and cost required to accomplish a given task . they then assign queries to the optimal tools in a cost-effective manner .
Outcome:	The proposed method achieves higher performance at lower cost compared to baseline approaches.

DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting (2026.acl-industry)

Copied to clipboard

Md Mofijul Islam, Md Sirajus Salekin, Nivedha Balakrishnan, Vincil C. Bishop III, Niharika Jain, Spencer Romo, Bob Strahan, Boyi Xie, Diego A. Socolinsky

MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation (2025.acl-industry)

Challenge:	Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together.
Approach:	They propose to use document packet splitting to improve document understanding in real-world applications.
Outcome:	The proposed datasets and evaluation metrics provide a systematic framework for advancing document understanding capabilities essential for legal, financial, healthcare, and other document-intensive domains.

Copied to clipboard

Zhipeng Bian, Jieming Zhu, Xuyang Xie, Quanyu Dai, Zhou Zhao, Zhenhua Dong

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement (2025.acl-short)

Challenge:	generative AI is revolutionizing how users interact with smartphones, transforming how they interact with them.
Approach:	They propose a framework for task instruction recommendation that enables intuitive one-touch AI tasking on smartphones.
Outcome:	The proposed framework shows significant improvements in recommendation accuracy and coherence and intent alignment with predefined instruction candidates.

Copied to clipboard

Runnan Fang, Xiaobin Wang, Yuan Liang, Shuofei Qiao, Jialong Wu, Zekun Xi, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

Challenge:	Using Large Language Models (LLMs)-based agents can enhance their understanding of environments and tasks.
Approach:	They propose a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search exploration to refine their action knowledge in the current environment.
Outcome:	The proposed framework synthesizes possible scenarios with multi-step action invocation within the action space and performs Monte Carlo Tree Search exploration to refine action knowledge in the current environment.

MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval (2024.findings-naacl)

Copied to clipboard

Youbo Lei, Feifei He, Chen Chen, Yingbin Mo, Sijia Li, Defeng Xie, Haonan Lu

Natural SQL: Making SQL Easier to Infer from Natural Language Specifications (2021.findings-emnlp)

Challenge:	Large-scale visual-language pretraining models have shown remarkable capabilities in understanding both vision and language.
Approach:	They propose a multi-teacher cross-modality alignment distillation technique to integrate the advantages of single-stream and dual-stream models.
Outcome:	The proposed model is lightweight and has only 100M running memory and 8.0ms search latency.

Copied to clipboard

Yujian Gan, Xinyun Chen, Jinxia Xie, Matthew Purver, John R. Woodward, John Drake, Qiaofu Zhang

What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarization (2023.acl-long)

Challenge:	Existing models that do not support executable SQL generation can generate executable queries.
Approach:	They propose an SQL intermediate representation called Natural SQL (NatSQL) they propose to preserve the core functionalities of SQL while simplifying the queries .
Outcome:	The proposed model outperforms existing models on a text-to-SQL benchmark . it significantly improves the performance of previous models on the same dataset .

Copied to clipboard

Griffin Adams, Bichlien Nguyen, Jake Smith, Yingce Xia, Shufang Xie, Anna Ostropolets, Budhaditya Deb, Yuan-Jyue Chen, Tristan Naumann, Noémie Elhadad

Descriptive Prompt Paraphrasing for Target-Oriented Multimodal Sentiment Classification (2023.findings-emnlp)

Challenge:	Summarization models are trained to maximize the likelihood of a single reference (MLE) but little is known about why one setup is more effective than another .
Approach:	They add a calibration step which exposes a model to its own ranked outputs to improve relevance or contrasts positive and negative sets to improve faithfulness.
Outcome:	The proposed calibration step can unlock large gains in relevance or faithfulness.

Copied to clipboard

Dan Liu, Lin Li, Xiaohui Tao, Jian Cui, Qing Xie

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning (2025.emnlp-industry)

Challenge:	Current researches mainly work on either of two types of targets in a decentralized manner.
Approach:	They propose a model to perform sentiment polarity on a target jointly considering its corresponding multiple modalities including text, image, and others.
Outcome:	The proposed model performs well on four datasets spanning the above two target types and is prompt-based language modelling.

Copied to clipboard

Ruizhe Chen, Tianze Luo, Zhiting Fan, Heqing Zou, Zhaopeng Feng, Guiyang Xie, Hansheng Zhang, Zhuochen Wang, Zuozhu Liu, Zhang Huaijian

Your Stereotypical Mileage May Vary: Practical Challenges of Evaluating Biases in Multiple Languages and Cultural Contexts (2024.lrec-main)

Challenge:	Existing methods for video temporal grounding suffer from limited temporal awareness and poor generalization.
Approach:	They propose a two-stage training framework that integrates supervised fine-tuning with reinforcement learning to improve both the accuracy and robustness of VTG models.
Outcome:	The proposed training framework outperforms existing models on multiple benchmarks on open-domain and challenging scenarios.

Copied to clipboard

Karen Fort, Laura Alonso Alemany, Luciana Benotti, Julien Bezançon, Claudia Borg, Marthese Borg, Yongjian Chen, Fanny Ducel, Yoann Dupont, Guido Ivetta, Zhijian Li, Margot Mieskes, Marco Naguib, Yuyan Qian, Matteo Radaelli, Wolfgang S. Schmeisser-Nieto, Emma Raimundo Schulz, Thiziri Saci, Sarah Saidi, Javier Torroba Marchante, Shilin Xie, Sergio E. Zanotto, Aurélie Névéol

Making the Best Use of Review Summary for Sentiment Analysis (2020.coling-main)

Challenge:	Recent studies have identified a gap in the availability of tools and resources to study bias in languages other than English and social contexts outside the north of America.
Approach:	They use stereotypes to build a corpus of sentence pairs that cover biases in seven cultural contexts.
Outcome:	The proposed resource covers a wide range of languages and cultural settings . it favors sentences that express stereotypes in most bias categories .

Copied to clipboard

Sen Yang, Leyang Cui, Jun Xie, Yue Zhang

Evaluating Language Model Pluralism through In-the-wild Crowd Discussions (2026.acl-long)

Challenge:	Existing methods for sentiment analysis of user reviews are limited to a few examples.
Approach:	They propose a hierarchically-refined attention model that exploits the sentimental distribution of a review and its corresponding summary.
Outcome:	The proposed model can make better use of user-written summaries for review sentiment analysis and is more effective compared to existing methods when the user summary is replaced with summary generated by an automatic summarization system.

Copied to clipboard

Gagan Mundada, Rohan Surana, Nandhini Swaminathan, Bodhisattwa Prasad Majumder, Junda Wu, Julian McAuley, Zhouhang Xie

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game (2026.acl-long)

Challenge:	Existing evaluation methods focus predominantly on multiple-choice and question-answering tasks, leaving open-ended generation largely unaddressed.
Approach:	They propose an evaluation framework that assesses LLM pluralism in open-ended generation by comparing outputs against free-form crowd responses.
Outcome:	The proposed evaluation framework decomposes ground-truth responses into atomic, non-overlapping claims and evaluates whether LLMs adequately cover this diverse claim space.

Copied to clipboard

Yuanbo Xie, Yingjie Zhang, Yulin Li, Shouyou Song, Xiaokun Chen, Zhihan Liu, Liya Su, Tingwen Liu

A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment (2020.coling-main)

Challenge:	Retrieval-Augmented Generation (RAG) systems augment large language models with external knowledge, but introduce a critical security vulnerability: Knowledge Base Leakage.
Approach:	They propose a runtime defense mechanism inspired by stack canaries in software security . canaryRAG embeds carefully designed canary tokens into retrieved chunks and reformulates RAG extraction defense as a dual-path runtime integrity game.
Outcome:	The proposed system can detect and prevent RAG Knowledge Base Leakage in real time . it can be integrated into arbitrary RAG pipelines without retraining or structural modifications .

Copied to clipboard

Zhiwen Xie, Runjie Zhu, Kunsong Zhao, Jin Liu, Guangyou Zhou, Jimmy Xiangji Huang

SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context (2025.findings-emnlp)

Challenge:	Existing methods for cross-lingual entity alignment ignore useful pre-aligned links between two KGs.
Approach:	They propose a novel method that jointly learns embeddings in different KGs by propagating cross-KG information through pre-aligned seed alignments.
Outcome:	The proposed method achieves remarkable performance gains on three benchmark cross-lingual entity alignment datasets.

Copied to clipboard

Hairu Wang, Yuan Feng, Yukun Cao, Xike Xie, S Kevin Zhou

Constructing Word-Context-Coupled Space Aligned with Associative Knowledge Relations for Interpretable Language Modeling (2023.findings-acl)

Challenge:	Large language models incur high inference costs during deployment, causing hallucination . no dedicated routing methods exist for RAG, and existing training-based routers face challenges scaling to this domain .
Approach:	They propose a plug-and-play routing framework that optimizes performance and cost . the framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x .
Outcome:	The proposed framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x compared to existing methods.

Copied to clipboard

Fanyu Wang, Zhenping Xie

GECSum: Generative Evaluation-Driven Sequence Level Contrastive Learning for Abstractive Summarization (2024.lrec-main)

Challenge:	Existing methods to train language models have limitations in interpretability . a Word-Context-Coupled Space (W2CSpace) is proposed to improve the performance of pre-trained models .
Approach:	They propose a Word-Context-Coupled Space to replace pre-trained models with interpretable statistical logic.
Outcome:	The proposed language model can achieve better performance and highly credible interpretability compared to state-of-the-art methods.

Copied to clipboard

Jiawen Xie, Shaoting Zhang, Xiaofan Zhang

Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG (2025.acl-long)

Challenge:	Abstractive summarization is a technique in natural language processing that involves generating a summary of a source document by creating new sentences and phrases.
Approach:	They propose a sequence-level contrastive learning framework that leverages the semantic understanding capabilities of the abstractive model itself to evaluate summary in reference-based settings.
Outcome:	The proposed framework outperforms the state-of-the-art in four summarization datasets.

Copied to clipboard

Xin Sun, Jianan Xie, Zhongqi Chen, Qiang Liu, Shu Wu, Yuehe Chen, Bowen Song, Zilei Wang, Weiqiang Wang, Liang Wang

Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Field (2022.emnlp-main)

Challenge:	Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources.
Approach:	They propose a method that conditions large language models to generate answers even in the absence of reliable knowledge.
Outcome:	The proposed approach balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems.

Copied to clipboard

Chengyue Jiang, Yong Jiang, Weiqi Wu, Pengjun Xie, Kewei Tu

Adversarial Math Word Problem Generation (2024.findings-emnlp)

Challenge:	Entity typing assigns semantic types to entities mentioned in text.
Approach:	They propose to use an undirected graphical model to formulate the UFET problem by combining unary potentials with a pairwise conditional random field model.
Outcome:	The proposed model outperforms the existing model with little cost and is thousands of times faster than the existing neural network module.

Copied to clipboard

Roy Xie, Chengxuan Huang, Junlin Wang, Bhuwan Dhingra

LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases (2026.acl-long)

Challenge:	Large language models (LLMs) have revolutionized the educational landscape due to the great improvements in their natural language generation and problem-solving capabilities.
Approach:	They propose a cost-effective approach to attack large language models using abstract syntax trees to generate adversarial examples that preserve the structure and difficulty of the original questions aimed for assessment.
Outcome:	The proposed approach significantly degrades students' math problem-solving ability on open- and closed-source LLMs.

Copied to clipboard

Yida Cai, Ranjuexiao Hu, Huiyuan Xie, Chenyang Li, Yun Liu, Yuxiao Ye, Zhenghao Liu, Weixing Shen, Zhiyuan Liu

DAPE-BR: Distance-Aware Positional Encoding for Mitigating Object Hallucination in LVLMs (2025.findings-emnlp)

Challenge:	Legal relations are an important analytical framework for dispute resolution in civil cases.
Approach:	They propose a comprehensive schema for legal relations in civil cases with hierarchical taxonomy and definitions of arguments.
Outcome:	The proposed schema shows that existing LLMs lack the ability to identify civil legal relations and performance improves on downstream tasks.

Copied to clipboard

Mingrui Xie, Tianxiang Xu, Qianhai Tang, Shanming Yao, Xiaofeng Zhang, Junliang Du

Better Pre-Training by Reducing Representation Confusion (2023.findings-eacl)

Challenge:	Large Vision–Language Models (LVLMs) suffer from object hallucination, generating descriptions for objects that are absent from the image, which undermines reliability and hinders real-world deployment.
Approach:	They propose a positional-alignment scheme that preserves pretrained weight order while globally—- visual–text distances, embeds an isotropic fused patch-distance metric, and applies a patch-delay causal mask to enforce spatial causality.
Outcome:	Extensive experiments on POPE, MMStar and SQA show that DAPE-BR reduces hallucinations and boosts performance.

Copied to clipboard

Haojie Zhang, Mingfei Liang, Ruobing Xie, Zhenlong Sun, Bo Zhang, Leyu Lin

Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems (2023.findings-emnlp)

Challenge:	Existing methods to improve pre-trained language models address information confusion in position encoding and model representations.
Approach:	They propose two techniques to improve pre-trained language models by decoupling directions and auxiliary regularizers.
Outcome:	The proposed techniques can improve pre-trained language models on GLUE benchmarks.

Copied to clipboard

Lidiya Murakhovs’ka, Philippe Laban, Tian Xie, Caiming Xiong, Chien-Sheng Wu

Enhancing Incremental Summarization with Structured Representations (2024.findings-emnlp)

Challenge:	Existing conversational recommender systems focus on a single-shot approach to understand user preferences and provide recommendations.
Approach:	They propose a problem space for conversational agents that aim to provide both product recommendations and educational value through mixed-type mixed-initiative dialog.
Outcome:	The proposed framework can simulate salesbot and shopperbot agents and provide both product recommendations and educational value through mixed-type mixed-initiative dialog.

Copied to clipboard

EunJeong Hwang, Yichao Zhou, James Wendt, Beliz Gunel, Nguyen Vo, Jing Xie, Sandeep Tata

Extracting Space Situational Awareness Events from News Text (2022.lrec-1)

Challenge:	Large language models struggle with processing extensive input contexts, leading to redundancy or incoherency.
Approach:	They propose a chain-of-key update based on JSON structured memory representations to improve summarization performance by 40% and 14% on two public datasets.
Outcome:	The proposed method improves summarization performance by 40% and 14% on two datasets.

Copied to clipboard

Zhengnan Xie, Alice Saebom Kwak, Enfa George, Laura W. Dozal, Hoang Van, Moriba Jah, Roberto Furfaro, Peter Jansen

Concise and Organized Perception Facilitates Reasoning in Large Language Models (2025.findings-naacl)

Challenge:	Space situational awareness is the decisionmaking knowledge required to predict, avoid, operate through, or recover from the loss, disruption, or degradation of space services, capabilities, or activities.
Approach:	They construct a corpus of 48.5k news articles spanning all known active satellites between 2009 and 2020 that are annotated by humans with 15.9k labels for event slots.
Outcome:	The proposed system achieves an overall F1 between 53 and 91 per slot for event extraction in this low-resource, high-impact domain.

Copied to clipboard

Junjie Liu, Shaotian Yan, Chen Shen, Zhengdong Xiao, Liang Xie, Wenxiao Wang, Jieping Ye

A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making (2025.emnlp-main)

Challenge:	Extensive experimental results on several popular logical benchmarks (ProofWriter, PrOntoQA, PrONtoQA-OOD, and FOLIO) and mathematical benchmark (DI-GSM) show that COP significantly outperforms previous state-of-the-art methods.
Approach:	They propose a reasoning approach called Concise and Organized Perception (COP) that carefully analyzes the given statements to identify the most pertinent information while eliminating redundancy efficiently.
Outcome:	The proposed approach outperforms state-of-the-art methods on several popular logical benchmarks and mathematical benchmarks.

Copied to clipboard

Xiao Wu, Ting-Zhu Huang, Liang-Jian Deng, Yanyuan Qiao, Imran Razzak, Yutong Xie

Data Augmentation for Code Translation with Comparable Corpora and Multiple References (2023.findings-emnlp)

Challenge:	Medical decision-making often involves integrating knowledge from multiple clinical specialties. static, pre-assigned roles hinder adaptability and dynamic knowledge integration.
Approach:	They propose a Knowledge-driven Adaptive Multi-Agent Collaboration framework that emulates large language models to emulate expert teamwork.
Outcome:	The proposed framework outperforms single-agent and advanced multi-agend methods on two real-world medical scenarios.

Copied to clipboard

Yiqing Xie, Atharva Naik, Daniel Fried, Carolyn Rose

From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning (2025.findings-acl)

Challenge:	Existing methods for translating code between programming languages are limited by parallel training data.
Approach:	They propose a data augmentation technique that builds comparable corpora and augments existing parallel data with multiple reference translations.
Outcome:	The proposed techniques improve CodeT5 translation between Java, Python, and C++ by an average of 7.5% Computational Accuracy (CA@1) .

Copied to clipboard

Wenjing Xie, Xiaobo Liang, Juntao Li, Wanfu Wang, Kehai Chen, Qiaoming Zhu, Min Zhang

Differentially Private Instance Encoding against Privacy Attacks (2022.naacl-srw)

Challenge:	Existing approaches enhance reasoning through Chain-of-Thought, Program-ofThough, and Tool-Integration.
Approach:	They propose a tool-awareness training method that leverages both forward and backward data generation strategies to strengthen the model’s conscious and selective tool utilization in multi-step reasoning tasks.
Outcome:	The proposed method improves the model's tool utilization capabilities, including proactivity and execution success rates.

Copied to clipboard

Shangyu Xie, Yuan Hong

BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction (2024.acl-long)

Challenge:	TextHide is a proposed privacy-enhancing technology to protect the training data from privacy attacks.
Approach:	They propose to encode training data via instance encoding in natural language domain without theoretic privacy guarantee.
Outcome:	The proposed scheme can defend against privacy attacks while ensuring learning utility (as a trade-off).

Copied to clipboard

Yinhao Bai, Yalan Xie, Xiaoyi Liu, Yuhua Zhao, Zhixin Han, Mengting Hu, Hang Gao, Renhong Cheng

Siamese Network-Based Supervised Topic Modeling (D18-1)

Challenge:	Aspect sentiment quad prediction aims to predict aspects due to distinct data distribution.
Approach:	They propose a method that aggregates multiple templates with a broader view . they first construct a few-shot ASQP dataset that contains richer categories .
Outcome:	The proposed method outperforms the state-of-the-art methods under four few-shot settings and other public datasets.

Copied to clipboard

Minghui Huang, Yanghui Rao, Yuwei Liu, Haoran Xie, Fu Lee Wang

Dynamic Evaluation with Cognitive Reasoning for Multi-turn Safety of Large Language Models (2025.acl-long)

Challenge:	Label-specific topics are widely used for supporting personality psychology, aspectlevel sentiment analysis, and crossdomain sentiment classification.
Approach:	They propose a supervised topic model based on the Siamese network which trades off label-specific word distributions with document-specific label distributions in a uniform framework.
Outcome:	The proposed model can trade off label-specific word distributions with document-specific label distributions in a uniform framework.

Copied to clipboard

Lanxue Zhang, Yanan Cao, Yuqiang Xie, Fang Fang, Yangxi Li

KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models (2024.acl-long)

Challenge:	Existing safety evaluation methods rely on static assessments that use fixed harmful prompts or predefined prefixes as jailbreak templates.
Approach:	They propose a dynamic evaluation framework for multi-turn safety assessment of LLMs based on cognitive theories to simulate real chatting process and scenario simulation and strategy decision to guide dynamic generation.
Outcome:	The proposed framework has been applied to evaluate the safety of widely used LLMs.

Copied to clipboard

Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Wei Ye, Jindong Wang, Xing Xie, Yue Zhang, Shikun Zhang

Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance (2025.emnlp-main)

Challenge:	Existing methods to detect contaminated texts focus on quantifying contamination status instead of accurately gauging model performance.
Approach:	They propose a Knowledge-grounded Interactive Evaluation framework which incorporates an LLM-powered “interactor” role for the first time to accomplish a dynamic contamination-resilient evaluation.
Outcome:	The proposed framework is based on a question in a standard LLM benchmark and can be used to evaluate models in real-world conversations.

Copied to clipboard

Xueqing Peng, Triantafillos Papadopoulos, Efstathia Soufleri, Polydoros Giannouris, Ruoyu Xiang, Yan Wang, Lingfei Qian, Jimin Huang, Qianqian Xie, Sophia Ananiadou

From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment (2025.acl-long)

Challenge:	Greek is the dominant language of the world's merchant navy and is a key language for international trade.
Approach:	They propose to develop a Greek financial evaluation benchmark and a financial LLM fine-tuned on Greek-specific financial data to bridge this gap.
Outcome:	The proposed benchmarks surpass GPT-4 by 8.33%, GPT- 4o by 26.83%, and Deepseek-V3 by 67.74%.

Copied to clipboard

Bin Xie, Bingbing Xu, Yige Yuan, Shengmao Zhu, Huawei Shen

HL-EncDec: A Hybrid-Level Encoder-Decoder for Neural Response Generation (C18-1)

Challenge:	Existing approaches to align large language models with human preferences suffer from inconsistent scoring and suboptimal alignment.
Approach:	They propose a dual-consistency framework that aligns partial sequences with human preferences.
Outcome:	The proposed framework significantly reduces granularity discrepancies and improves GPT-4 evaluation scores.

Copied to clipboard

Sixing Wu, Dawei Zhang, Ying Li, Xing Xie, Zhonghai Wu

Extract and Attend: Improving Entity Translation in Neural Machine Translation (2023.findings-acl)

Challenge:	Existing models for conversation systems operate sentences at word-level . word-based models suffer from Unknown Words Issue and Preference Issue .
Approach:	They propose a hybrid-level Encoder-Decoder model which utilizes word-level features and character-level ones.
Outcome:	The proposed model outperforms non-word-level models in automatic metrics and human annotations on a Chinese corpus.

Copied to clipboard

Zixin Zeng, Rui Wang, Yichong Leng, Junliang Guo, Shufang Xie, Xu Tan, Tao Qin, Tie-Yan Liu

CoAlign: Uncertainty Calibration of LLM for Geospatial Repartition (2025.acl-industry)

Challenge:	Existing methods to improve entity translation in Neural machine translation still suffer from inaccurate translation of entities due to the lack of entity training instances.
Approach:	They propose an extract-and-tend approach to enhance entity translation in NMT by extracting entities from a dictionary and attending to them with a prefix.
Outcome:	Experiments on En-Zh and En-Ru show that the proposed approach improves translation accuracy and translation quality.

Copied to clipboard

Zejun Xie, Zhiqing Hong, Wenjun Lyu, Haotian Wang, Guang Wang, Desheng Zhang

HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)

Challenge:	Existing methods to optimize geospatial repartition rely on manual adjustments by experts or algorithmic optimization using limited offline operational metrics.
Approach:	They propose a framework that calibrates LLM uncertainty to enable robust geospatial repartition by integrating historical data with LLM-generated candidates.
Outcome:	The proposed framework calibrates LLM uncertainty to enable robust geospatial repartition by integrating historical data with LLM-generated candidates.

Copied to clipboard

Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang, Jun Gao, Shuai Huang, Yueping Kang, Yuanli Guo, Hongwei Feng, Yanghua Xiao

Linguistics & Cognitive NLP

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs).
Approach:	They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.
Outcome:	The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters.

ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents (2026.acl-long)

Copied to clipboard

Zhuofeng Li, Yi Lu, Dongfu Jiang, Haoxiang Zhang, Yuyang Bai, Chuan Li, Yu Wang, Shuiwang Ji, Jianwen Xie, Yu Zhang

LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)

Challenge:	Rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support.
Approach:	They propose a peer review benchmarking tool based on paper-specific rubrics and a rubric-guided framework that decomposes reviewing into drafting and grounding stages.
Outcome:	The proposed framework outperforms baselines with stronger/larger backbones in both alignment with human judgments and rubric-based review quality across 8 dimensions.

Copied to clipboard

Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang

Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework (2026.acl-long)

Challenge:	Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs.
Approach:	They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal .
Outcome:	The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts.

Copied to clipboard

Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian, Bowen Xing, Meishan Zhang, Libo Qin, Baotian Hu, Min Zhang

A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners (2024.emnlp-main)

Challenge:	Existing methods for cross-lingual chain-of-thought (XCoT) with self-consistency are costly due to extensive sampling of full trajectories across languages.
Approach:	They propose a cross-lingual chain-of-thought framework that minimizes redundancy in token usage and latency.
Outcome:	Experiments on polymath show that UL-XCoT reduces decoding token costs and latency by 50% . UL XCot also aggregates remaining high-quality reasoning paths via voting .

Copied to clipboard

Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao, Xiaomeng Wang, Tanwi Mallick, Weijie Su, Camillo Taylor, Dan Roth

LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation (2026.findings-acl)

Challenge:	a new hypothesis-testing framework is developed to assess whether large language models possess genuine reasoning abilities or primarily depend on token bias.
Approach:	They propose a framework to assess whether large language models have genuine reasoning abilities or primarily depend on token bias.
Outcome:	The proposed framework outlines a list of hypotheses where token biases are readily identifiable . the results suggest that most LLMs still struggle with logical reasoning .

Copied to clipboard

Yuxiao Ye, Yiming Zhang, Yiran Rex Ma, Huiyuan Xie, Huining Zhu, Zhiyuan Liu

BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have enabled Multi-Agent Systems (MASs) where agents interact through natural language to solve complex tasks or simulate multi-party dialogues.
Approach:	They propose a linguistically-grounded game-theoretic paradigm for multi-agent dialogue generation that uses a training-free equilibrium approximation algorithm to model dialogue over communicative intents and strategies.
Outcome:	The proposed framework improves agents’ communication efficiency by helping them convey their intended meaning more effectively through language.

Copied to clipboard

Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, Rui Yan

Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema (2025.coling-main)

Challenge:	BioT5+ is an extension of the BioT5, but lacked a nuanced understanding of molecular structures.
Approach:	They propose a new bio-entity modeling framework, BioT5+, which integrates IUPAC names and molecule data.
Outcome:	The proposed model bridges the gap between molecular representations and textual descriptions and improves the grounded reasoning of bio-text and bio-sequences.

Copied to clipboard

Jie Shi, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Chenhao Xie, Peng Wang, Wei Wang

TextBox: A Unified, Modularized, and Extensible Framework for Text Generation (2021.acl-demo)

Challenge:	Recent studies have shifted paradigms and leveraged Large Language Models (LLMs) to tackle the challenging task of Text-to-SQL.
Approach:	They propose a framework that leverages large language models to generate SQL queries . they exploit prior knowledge from the LLM to enhance embedding-based retriever .
Outcome:	The proposed method improves embedding-based retriever and reduces cost.

Copied to clipboard

Junyi Li, Tianyi Tang, Gaole He, Jinhao Jiang, Xiaoxuan Hu, Puzhao Xie, Zhipeng Chen, Zhuohao Yu, Wayne Xin Zhao, Ji-Rong Wen

Graph Neural News Recommendation with Unsupervised Preference Disentanglement (2020.acl-main)

Challenge:	TextBox is an open-source text generation framework that is modularized and extensible.
Approach:	They propose to provide a unified, modularized, and extensible text generation framework that implements 21 text generation models on 9 benchmark datasets.
Outcome:	The proposed framework implements 21 models on 9 benchmark datasets and is available under the Apache License 2.0 license.

Copied to clipboard

Linmei Hu, Siyong Xu, Chen Li, Cheng Yang, Chuan Shi, Nan Duan, Xing Xie, Ming Zhou

Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and Enhancement (2025.acl-long)

Challenge:	Existing methods to learn informative user and news representations fail to consider high-order connectivity underlying the user-news interactions.
Approach:	They propose a novel Graph Neural News Recommendation model with Unsupervised Preference Disentanglement which can encode high-order relationships into user and news representations by information propagation along the graph.
Outcome:	The proposed model can encode high-order relationships into user and news representations by information propagation along the graph and disentangle latent preference factors by a neighborhood routing algorithm.

Copied to clipboard

Bingbing Xu, Jing Yao, Xiaoyuan Yi, Aishan Maoliniyazi, Xing Xie, Xiaofeng Meng

Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization (2025.findings-naacl)

Challenge:	Large Language Models (LLMs) show remarkable performance across tasks . alignment with human values is critical for their responsible development.
Approach:	They propose a framework that evaluates value principles along three desirable properties . they propose supervised fine-tuning, reinforcement learning-based approaches .
Outcome:	The proposed framework improves value principles along the three desirable properties of LLMs.

Copied to clipboard

Weiqi Wu, Shen Huang, Yong Jiang, Pengjun Xie, Fei Huang, Hai Zhao

Large-scale Cloze Test Dataset Created by Teachers (D18-1)

Challenge:	a new approach to timeline summarization is proposed for open-domain news content . large language models (LLMs) can be used to extract and organize news events from multiple documents .
Approach:	They propose a method to integrate Large Language Models into news timeline summarization by iterating on how events are linked and posing new questions.
Outcome:	The proposed system is able to generate and refresh chronological summaries based on documents retrieved in each round.

Copied to clipboard

Qizhe Xie, Guokun Lai, Zihang Dai, Eduard Hovy

Challenge:	Existing cloze tests are used to evaluate language proficiency in language exams, but they are not yet available.
Approach:	They propose to create a large-scale human-created cloze test dataset CLOTH, which contains questions used in middle-school and high-school language exams.
Outcome:	The proposed dataset outperforms existing models and shows that humans outperformed existing models by a significant margin.

CoDA: Restoring Contextual Dominance via Copy-Encouraged Attention Intervention for Mitigating RAG Hallucinations (2026.findings-acl)

Copied to clipboard

JinWei Shi, Qizhuo Xie, Qianzi Hou, Zhipeng Wang, Wanting Su, Jianhua Zhao, Tao Zheng, Tieke He

Mitigating Hallucination in Fictional Character Role-Play (2024.findings-emnlp)

Challenge:	Retrieval-augmented generation reduces hallucination by grounding outputs in external evidence.
Approach:	They propose a lightweight inference-time attention intervention that amplifies evidence-aligned value states to enhance contextual faithfulness and reduce hallucination.
Outcome:	The proposed model reduces hallucination by grounding model outputs in external evidence.

Copied to clipboard

Nafis Sadeq, Zhouhang Xie, Byungkyu Kang, Prarit Lamba, Xiang Gao, Julian McAuley

Towards Text-Image Interleaved Retrieval (2025.acl-long)

Challenge:	Influence of parametric knowledge of large language models (LLMs) often causes role-playing characters to act out of character and hallucinate about things outside the scope of their knowledge.
Approach:	They propose a method that modulates the influence of parametric knowledge using a pre-calibrated confidence threshold to mitigate hallucination in fictional character role-play.
Outcome:	The proposed method reduces the factual accuracy of generated responses by 18% for adversarial questions and 44% in temporal hallucination for time-sensitive interviews.

Copied to clipboard

Xin Zhang, Ziqi Dai, Yongqi Li, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Meishan Zhang, Jun Yu, Wenjie Li, Min Zhang

Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling (2026.findings-acl)

Challenge:	Existing multimodal information retrieval models rely on single-image inputs . current models use a dense retrieval paradigm, but this approach is not effective .
Approach:	They propose a text-image interleaved retrieval task where query and document are interleaves . they adapt off-the-shelf retrievers and build a dense baseline by interleaded multimodal large language model .
Outcome:	The proposed model achieves significant improvements over the baseline by substantially fewer visual tokens.

Copied to clipboard

Wantong Xie, Yinghao Chen, Yi-Xiang Hu, Feng Wu, Jieyang Xu, Sijia Zhang, Xiangyang Li

Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues (2026.acl-long)

Challenge:	Existing retrieval-augmented strategies for large language models fail to capture dynamic reasoning required to resolve execution failures.
Approach:	They propose a framework that implements Experience Replay to transform transient rectification steps into persistent knowledge.
Outcome:	The proposed framework improves model accuracy by 8.45% on complex tasks while reducing token consumption by 28.65% and interaction turns by 25.82%.

Copied to clipboard

Muhammad Dehan Al Kautsar, Saeed Almheiri, Momina Ahsan, Bilal Elbouardi, Younes Samih, Sarfraz Ahmad, Amr Keleg, Omar El Herraoui, Kareem Elzeky, Abed Alhakim Freihat, Mohamed Anwar, Zhuohan Xie, Junhong Liang, Mohammad Rustom Al Nasar, Preslav Nakov, Fajri Koto

Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts (2024.findings-acl)

Challenge:	Most benchmarks focus on short text snippets in Modern Standard Arabic (MSA), overlooking cultural nuances that naturally arise in dialogues.
Approach:	They propose a culturally grounded conversational dataset covering 13 Arabic-speaking countries, in both Modern Standard Arabic (MSA) and each country’s respective dialect, spanning 12 daily-life topics and 54 fine-grained subtopics.
Outcome:	The proposed model performs worse on all three tasks than the MSA benchmark.

Copied to clipboard

Zhuo Chen, Xinyu Wang, Yong Jiang, Pengjun Xie, Fei Huang, Kewei Tu

LLEOT: A Privacy-Enhancing Offsite Tuning Framework via Loss Landscape Elevation (2026.findings-acl)

Challenge:	Retrieval Augmented Generation can be used to process long contexts in Open-Domain Question-Answering tasks.
Approach:	They propose a method to cover longer contexts in Open-Domain Question-Answering tasks by using a small encoder language model and cross-attention with origin inputs.
Outcome:	The proposed method can cover longer contexts while keeping the computing requirements close to the baseline.

Copied to clipboard

Jin Zhong, Jinglin Liang, Tongtong Yang, Zijian Xie, Shuangping Huang, Hanlin Gu

ECoK: Emotional Commonsense Knowledge Graph for Mining Emotional Gold (2024.findings-acl)

Challenge:	Existing approaches to fine-tune large language models are infeasible due to privacy regulations.
Approach:	They propose an offsite tuning framework that secures data privacy and model parameter and capability privacy.
Outcome:	The proposed framework secures data privacy and model parameter and capability privacy while preserving gradient alignment.

Copied to clipboard

Zhunheng Wang, Xiaoyi Liu, Mengting Hu, Rui Ying, Ming Jiang, Jianfeng Wu, Yalan Xie, Hang Gao, Renhong Cheng

A Sequential Flow Control Framework for Multi-hop Knowledge Base Question Answering (2022.emnlp-main)

Challenge:	Existing knowledge graphs focus on the representation and reasoning of general factual knowledge, while there are significant deficiencies in the understanding and reasoning for emotional knowledge.
Approach:	They propose a commonsense knowledge graph that can be used to represent emotional knowledge by combining theories from psychology, cognitive science, and linguistics.
Outcome:	The proposed model surpasses GPT-4-Turbo in the emotion-related tasks.

Copied to clipboard

Minghui Xie, Chuzhan Hao, Peng Zhang

BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks (2026.acl-long)

Challenge:	Existing methods for multi-hop reasoning in knowledge base question answering are coarse-grained and may bring information loss.
Approach:	They propose a sequential reasoning self-attention mechanism to capture the crucial reasoning information of each hop in a more fine-grained way.
Outcome:	The proposed model achieves new state-of-the-art Hits@1 of 76.8% on WebQSP and is also effective when KB is incomplete.

Copied to clipboard

Nishant Balepur, Bhavya Rajasekaran, Hyunjin Jane Oh, Michael Xie, Atrey Desai, Vipul Gupta, Steven James Moore, Eunsol Choi, Rachel Rudinger, Jordan Lee Boyd-Graber

Challenge:	Multiple-choice question answering (MCQ) is standard in NLP, but benchmarks lack rigorous quality control.
Approach:	They propose an education-inspired toolkit that uses LLM judges to flag flaws in MCQs . they validate the tool with annotations and run it to audit 12 benchmarks based on 19-rule education rubric .
Outcome:	The proposed toolkit flags three common MCQ flaws based on a 19-rule education rubric . contaminated MCqs tend to inflate accuracy, while writing errors lower it and change rankings .

Making Large Language Models into World Models with Precondition and Effect Knowledge (2025.coling-main)

Copied to clipboard

Kaige Xie, Ian Yang, John Gunerli, Mark Riedl

SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation (2025.acl-long)

Challenge:	Large Language Models (LLMs) are not inherently designed to model real-world dynamics, but can be induced to perform two critical world model functions: determining the applicability of an action based on a given world state and predicting the resulting world state upon action execution.
Approach:	They propose to use Large Language Models to model world states and preconditions . they validate that precondition and effect knowledge generated by LLMs aligns with human understanding of world dynamics .
Outcome:	The proposed model can predict valid actions and state transitions, thereby replicating existing models.

Copied to clipboard

Keqi Deng, Wenxi Chen, Xie Chen, Phil Woodland

Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts (2024.naacl-long)

Challenge:	Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency.
Approach:	They propose to train LLMs offline and employ a test-time policy to guide simultaneous inference by extracting boundary-aware speech prompts that allow it to be better matched with text input data.
Outcome:	The proposed model trains speech LLMs offline and employs a test-time policy to guide simultaneous inference.

Copied to clipboard

Sai Ashish Somayajula, Youwei Liang, Li Zhang, Abhishek Singh, Pengtao Xie

Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation (2021.findings-emnlp)

Challenge:	Pretrained language models have advanced natural language processing tasks significantly, but finetuning them on low-resource datasets presents significant challenges such as instability and overfitting.
Approach:	They propose a regularization method based on attention-guided weight mixup for finetuning PLMs on low-resource datasets.
Outcome:	The proposed method improves generalization and combats overfitting on two splits of the training dataset.

Copied to clipboard

Xin Zheng, Zhirui Zhang, Shujian Huang, Boxing Chen, Jun Xie, Weihua Luo, Jiajun Chen

Benchmarking Meaning Representations in Neural Semantic Parsing (2020.emnlp-main)

Challenge:	kNN-MT is a non-parametric method that uses nearest neighbor retrieval to translate out-of-domain sentences, rare words, etc.
Approach:	They propose a framework that directly uses in-domain monolingual sentences to build an effective datastore for k-nearest-neighbor retrieval.
Outcome:	The proposed framework improves translation accuracy with target-side monolingual data while achieving comparable performance with back-translation.

Copied to clipboard

Jiaqi Guo, Qian Liu, Jian-Guang Lou, Zhenwen Li, Xueqing Liu, Tao Xie, Ting Liu

Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation (2025.emnlp-main)

Challenge:	Existing work on meaning representations is not comprehensively evaluated due to the lack of readily-available execution engines.
Approach:	They propose a unified benchmark on meaning representations by integrating existing semantic parsing datasets, completing the missing logical forms, and implementing the missing execution engines.
Outcome:	The proposed benchmark combines existing parsing datasets, completes missing logical forms, and implements missing execution engines.

Copied to clipboard

Haijian Ma, Daizong Liu, Xiaowen Cai, Pan Zhou, Yulai Xie

Open-Vocabulary Argument Role Prediction For Event Extraction (2022.findings-emnlp)

Challenge:	Intrusion detection systems (IDS) are limited in labeled samples due to scarcity and lack of diversity in malicious samples.
Approach:	They propose a semi-supervised framework that integrates Generative Adversarial Networks with Large Language Models to enhance malicious code generation and SQL Injection detection capabilities.
Outcome:	The proposed framework enhances malicious code generation and detection capabilities in few-sample learning scenarios.

Copied to clipboard

Yizhu Jiao, Sha Li, Yiqing Xie, Ming Zhong, Heng Ji, Jiawei Han