Papers by Cheng Liu

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models (2024.findings-emnlp)

Challenge:	Existing studies attribute object hallucinations to linguistic priors and data biases . MFCD method removes hallucinian distribution in the original output distribution .
Approach:	They propose a method that removes the hallucination distribution in the original output distribution . they propose MFCD to mitigate hallucinism in large visual-language models .
Outcome:	The proposed method reduces hallucination distributions without training or external tools . the proposed method can be applied to various LVLMs without modifying model architecture or training .

Copied to clipboard

Bozhong Tian, Xiaozhuan Liang, Siyuan Cheng, Qingbin Liu, Mengru Wang, Dianbo Sui, Xi Chen, Huajun Chen, Ningyu Zhang

Recyclable Tuning for Continual Pre-training (2023.findings-acl)

Challenge:	Existing unlearning paradigms are mired in vague forgetting boundaries, erasing knowledge indiscriminately.
Approach:	They propose a benchmark to evaluate if unlearning erases essential knowledge . they propose 'knowUnDo' which uses copyrighted content and privacy domains .
Outcome:	The proposed method is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs.

Copied to clipboard

Yujia Qin, Cheng Qian, Xu Han, Yankai Lin, Huadong Wang, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

Snapshot-Guided Domain Adaptation for ELECTRA (2022.findings-emnlp)

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

Daixuan Cheng, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Furu Wei, Denvy Deng, Qi Zhang

Towards Explainable Computerized Adaptive Testing with Large Language Model (2024.findings-emnlp)

Challenge:	Existing domain-specific knowledge of domain-related tasks is lacking in pre-trained language models.
Approach:	They propose a domain-adaptation method which can dynamically select domain-specific tokens and guide the discriminator to emphasize them, without introducing new training parameters.
Outcome:	The proposed method can capture domain-specific knowledge of domain-related tasks without introducing new training parameters.

Copied to clipboard

Cheng Cheng, GuanHao Zhao, Zhenya Huang, Yan Zhuang, Zhaoyuan Pan, Qi Liu, Xin Li, Enhong Chen

Generation-Augmented Retrieval: Rethinking the Role of Large Language Models in Zero-Shot Relation Extraction (2025.findings-emnlp)

Challenge:	Existing methods focus on minimizing the number of questions required to assess ability, lacking clear and reliable explanations for the question selection process.
Approach:	They propose to use large language models to enhance computer adaptive testing (CAT) by providing human-like interpretability and explanations.
Outcome:	The proposed agent-based CAT performs comparably or superior to traditional CAT methods in accuracy and significantly improves student trust and satisfaction.

Copied to clipboard

Zehan Li, Fu Zhang, Tianyue Peng, He Liu, Jingwei Cheng

SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems (2026.acl-long)

Challenge:	Recent advances in Relation Extraction (RE) emphasize Zero-Shot methodologies, aiming to recognize unseen relations between entities with no annotated data.
Approach:	They propose a plug-in retrieval adjuster that allows rapid fine-tuning without accessing LLMs’ parameters.
Outcome:	The proposed model demonstrates comparable performance on multiple benchmarks.

Copied to clipboard

Yuzhe Zhang, Feiran Liu, Yi Shan, Xinyi Huang, Xin Yang, Yueqi Zhu, Xuxin Cheng, Cao Liu, Ke Zeng, Terry Jingchen Zhang, Wenyuan Jiang

Challenge:	Existing benchmarks conflate coordination ability with role-based priors.
Approach:	They propose a role-free benchmark for evaluating free-form collaboration under information silos.
Outcome:	The proposed benchmark systematically probes coordination capabilities under information silos using 54 configurations and 3 frontier LLMs.

VoxpopuliTTS: a large-scale multilingual TTS corpus for zero-shot speech generation (2025.coling-main)

Copied to clipboard

Wenrui Liu, Jionghao Bai, Xize Cheng, Jialong Zuo, Ziyue Jiang, Shengpeng Ji, Minghui Fang, Xiaoda Yang, Qian Yang, Zhou Zhao

Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models (2026.acl-long)

Challenge:	Existing multilingual TTS datasets are limited in speech generation fields due to lack of quality data.
Approach:	They propose to use 30,000 hours of high-quality speech data across 3 languages . they filter out low-quality text-text pairs and concatenate short transcripts .
Outcome:	The proposed dataset comprises 30,000 hours of high-quality speech data, across 3 languages with multiple speakers and styles, suitable for various speech tasks such as TTS and ASR.

Copied to clipboard

Tianle Chen, Pengyu Cheng, Qiyuan Zhu, Jiacheng Wang, Bei Liu, Hao Gu, Ruijie Shen, Xiaofeng Hou, Sirui Han, Jiacheng Liu

Neural Machine Translation with Contrastive Translation Memories (2022.emnlp-main)

Challenge:	Existing research to improve CoT efficiency falls into three categories, each with distinct limitations.
Approach:	They propose a training-free framework that addresses both dimensions of CoT reasoning by applying a progressive precision reduction strategy coupled with an entropy-based confidence mechanism for adaptive termination.
Outcome:	Empirical results show that the proposed framework achieves 11.3 efficiency gain without compromising accuracy.

Copied to clipboard

Xin Cheng, Shen Gao, Lemao Liu, Dongyan Zhao, Rui Yan

Machine Translation

Challenge:	Experimental results show that retrieval-augmented NMT model obtains substantial improvements over strong baselines in the benchmark dataset.
Approach:	They propose a retrieval-augmented NMT model that is holistically similar to the source sentence while individually contrastive to each other.
Outcome:	The proposed model improves on baselines in the translation task.

CE-DA: Custom Embedding and Dynamic Aggregation for Zero-Shot Relation Extraction (2025.coling-main)

Copied to clipboard

Fu Zhang, He Liu, Zehan Li, Jingwei Cheng

Language Models as Inductive Reasoners (2024.eacl-long)

Challenge:	Existing methods to predict relationships with given entity pairs are lacking in supervised methods.
Approach:	They propose a framework for zero-shot Relation Extraction that includes two modules: Custom Embedding and Dynamic Aggregation.
Outcome:	The proposed framework shows competitive performance on two ZSRE datasets.

Copied to clipboard

Zonglin Yang, Li Dong, Xinya Du, Hao Cheng, Erik Cambria, Xiaodong Liu, Jianfeng Gao, Furu Wei

CART: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling (2025.acl-long)

Challenge:	Inductive reasoning is a core component of human intelligence.
Approach:	They propose a task to induce natural language rules from natural language facts using natural language as representation for knowledge instead of formal language.
Outcome:	The proposed task surpasses baselines in both automatic and human evaluations.

Copied to clipboard

Minghui Fang, Shengpeng Ji, Jialong Zuo, Hai Huang, Yan Xia, Jieming Zhu, Xize Cheng, Xiaoda Yang, Wenrui Liu, Gang Wang, Zhenhua Dong, Zhou Zhao

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models (2024.emnlp-main)

Challenge:	Cross-modal retrieval tasks are used to retrieve data from one modality or another based on a query from another modality.
Approach:	They propose a generative cross-modal retrieval framework based on coarse-to-fine semantic modeling . they propose combining K-Means and RQ-VAE to discretize multimodal data into token sequences that support autoregressive generation.
Outcome:	The proposed framework achieves excellent performance and efficiency in multimodal retrieval tasks.

Copied to clipboard

Yifei Liu, Jicheng Wen, Yang Wang, Shengyu Ye, Li Lyna Zhang, Ting Cao, Cheng Li, Mao Yang

Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction (2024.findings-acl)

Challenge:	Recent research has focused on pushing weight-only quantization to extremely low-bit due to numerical representation limitations.
Approach:	They propose a vector-based quantization approach that pushes LLMs to extremely low-bit . they propose scalar-based weight quantization that reduces memory requirements and optimizes storage costs .
Outcome:	The proposed method reduces model quantization perplexity by 0.01-0.34 on LLaMA-2, 0.38-0.68 on mistral-7B, 4.41-7.34, on llaMA-3 on QA tasks on average.

Copied to clipboard

Wanlong Liu, Li Zhou, DingYi Zeng, Yichen Xiao, Shaohuan Cheng, Chen Zhang, Grandee Lee, Malu Zhang, Wenyu Chen

On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation (2021.acl-long)

Challenge:	mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring correlations among multiple events.
Approach:	They propose a multi-event argument argument extraction model which extracts arguments from all events simultaneously.
Outcome:	The proposed model performs better on four public datasets while saving time.

Copied to clipboard

Ruidan He, Linlin Liu, Hai Ye, Qingyu Tan, Bosheng Ding, Liying Cheng, Jiawei Low, Lidong Bing, Luo Si

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)

Challenge:	Existing studies have shown that adapter-based tuning is more parameter-efficient than fine-tuning.
Approach:	They propose to add adapter modules to a pretrained language model and update the parameters of adapter module when learning on a downstream task.
Outcome:	The proposed method outperforms fine-tuning on low-resource and cross-lingual tasks and settings.

Copied to clipboard

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li

Logit Space Constrained Fine-Tuning for Mitigating Hallucinations in LLM-Based Recommender Systems (2025.emnlp-main)

Challenge:	Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach:	They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome:	The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.

Copied to clipboard

Jianfeng Deng, Qingfeng Chen, Debo Cheng, Jiuyong Li, Lin Liu

Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot (2025.findings-emnlp)

Challenge:	Existing LLM-based recommender systems rely on standard fine-tuning methodologies, often ignoring hallucination issues during the fine-uning process.
Approach:	They propose a logit space constraint-based fine-tuning framework to mitigate hallucination in LLM-based recommenders by incorporating Kullback–Leibler divergence into the training objective.
Outcome:	Experiments on two recommendation models with distinct LLM backbones and four real-world datasets show that LCFT reduces hallucination and enhances recommendation performance.

Copied to clipboard

Xiang Cheng, Chengyan Pan, Minjun Zhao, Deyang Li, Fangchao Liu, Xinyu Zhang, Xiao Zhang, Yong Liu

PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks (2025.emnlp-main)

Challenge:	In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs).
Approach:	They introduce CoT to exemplars of ICL to enhance the reasoning capability . however, it remains unclear whether CoT exemplar is still beneficial for recent, stronger models in such tasks.
Outcome:	The enhanced exemplars fail to improve the model’s reasoning performance, despite being constructed using answers from advanced models such as Qwen2.5-Max and DeepSeek-R1.

Copied to clipboard

Yunuo Liu, Dawei Zhu, Zena Al-Khalili, Dai Cheng, Yanjun Chen, Dietrich Klakow, Wei Zhang, Xiaoyu Shen

Neuron-Level Differentiation of Memorization and Generalization in Large Language Models (2025.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, such as code generation, mathematical problem-solving, and general-purpose human instruction following.
Approach:	They propose to use large language models to process questions expressed in natural language to automate tourism-booking prices when multiple, overlapping farerules apply.
Outcome:	The proposed model can automate tourism-booking prices when multiple, overlapping farerules apply.

Copied to clipboard

Ko-Wei Huang, Yi-Fu Fu, Ching-Yu Tsai, Yu-Chieh Tu, Tzu-ling Cheng, Cheng-Yu Lin, Yi-Ting Yang, Heng-Yi Liu, Keng-Te Liao, Da-Cheng Juan, Shou-De Lin

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Challenge:	Existing models exhibit memorization and generalization behaviors in ways that are not easily interpretable or controllable.
Approach:	They propose to use a GPT-2 and LLaMA-3.2 model to identify distinct neuron subsets responsible for each behavior to steer the model toward memorization or generalization.
Outcome:	The proposed models show that inference-time interventions on these neurons can steer the model’s behavior toward memorization or generalization.

Copied to clipboard

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin

Challenge:	a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach:	They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome:	The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.

On the Universal Truthfulness Hyperplane Inside LLMs (2024.emnlp-main)

Copied to clipboard

Junteng Liu, Shiqi Chen, Yu Cheng, Junxian He

Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding (2023.findings-emnlp)

Challenge:	Recent studies have explored hallucinations through the lens of internal representations, proposing mechanisms to decipher LLMs’ adherence to facts.
Approach:	They propose to train a universal truthfulness hyperplane that distinguishes the model’s factually correct and incorrect outputs on a diverse collection of over 40 datasets and examine its cross-task, cross-domain, and in-domain generalization.
Outcome:	The proposed model is able to distinguish factual outputs from incorrect outputs on a diverse collection of over 40 datasets.

Copied to clipboard

Xiang Fang, Daizong Liu, Wanlong Fang, Pan Zhou, Yu Cheng, Keke Tang, Kai Zou

Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding (2023.findings-emnlp)

Challenge:	Existing work on temporal sentence grounding rely on expensive video-query paired annotations . despite this, there are no ground-truth annotations in the current work .
Approach:	They propose to use paired video-query and segment boundary annotations to generate temporal sentence grounding without training.
Outcome:	The proposed model outperforms existing unsupervised methods and beats supervised ones on two challenging datasets.

Copied to clipboard

Yu Zhang, Hao Cheng, Zhihong Shen, Xiaodong Liu, Ye-Yi Wang, Jianfeng Gao

Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training (2025.acl-long)

Challenge:	Pre-trained language models (LMs) have shown effectiveness in literature understanding tasks, especially when tuned via contrastive learning.
Approach:	They propose a multi-task contrastive learning framework that enables common knowledge sharing across different scientific literature understanding tasks while preventing task-specific skills from interfering with each other.
Outcome:	The proposed framework outperforms state-of-the-art pre-trained language models on a comprehensive dataset.

Copied to clipboard

Zheheng Luo, Xin Zhang, Xiao Liu, Haoling Li, Yeyun Gong, Qi Chen, Peng Cheng

EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets (2021.acl-long)

Challenge:	Existing methods to optimise pretraining performance have not addressed the complexities of domain-adaptive continual pretraining.
Approach:	They propose a framework that dynamically assesses learning velocity and adjusts data proportions accordingly, favouring slower learning domains while de-emphasising faster learning ones.
Outcome:	The proposed framework achieves performance gains in math and code reasoning tasks and command-line generation benchmarks.

Copied to clipboard

Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Zhangyang Wang, Jingjing Liu

RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models (2025.findings-emnlp)

Challenge:	Large-scale pre-trained language models require enormous computational resources and long training time.
Approach:	They propose an algorithm to reduce inference time and train large NLP models by slimming the self-attention and fully-connected sub-layers inside a transformer.
Outcome:	The proposed algorithm achieves comparable performance to standard BERT with 35 45% less training time.

Copied to clipboard

Jingjing Liu, Zeming Liu, Zihao Cheng, Mengliang He, Xiaoming Shi, Yuhang Guo, Xiangrong Zhu, Yuanfang Guo, Yunhong Wang, Haifeng Wang

Commonsense Subgraph for Inductive Relation Reasoning with Meta-learning (2025.coling-main)

Challenge:	Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair.
Approach:	They propose a repository-level code debugging dataset with 22 subtypes of errors that supports 8 commonly used programming languages and 3 debug tasks.
Outcome:	The proposed dataset supports 8 commonly used programming languages and 3 debugging tasks.

Copied to clipboard

Feng Zhao, Zhilu Zhang, Cheng Yan, Xianggan Liu

CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions (2024.emnlp-main)

Challenge:	Existing subgraph-based models focus on predicting missing relations in knowledge graphs . a new meta-learning model extracts concepts from entities to construct commonsense subgraphs based on semantic information .
Approach:	They propose a commonsense subgraph meta-learning model that extracts concepts from entities to construct commonsensible subgraphs.
Outcome:	The proposed model outperforms existing models in inductive reasoning tasks and in few-shot scenarios.

Copied to clipboard

Jun Rao, Xuebo Liu, Lian Lian, Shengjun Cheng, Yunjie Liao, Min Zhang

Simple but Challenging: Natural Language Inference Models Fail on Simple Sentences (2022.findings-emnlp)

Challenge:	Current studies have focused on fine-tuning, but the use of instruction tuning is not as effective as fine-cuning.
Approach:	They propose a commonality-aware instruction tuning strategy to cluster instruction datasets into distinct groups with three proposed metrics Task, Embedding and Length.
Outcome:	The proposed strategy boosts an average improvement of 2.1% on the general domain and 5.2% on the special domain.

Copied to clipboard

Cheng Luo, Wei Liu, Jieyu Lin, Jiajie Zou, Ming Xiang, Nai Ding

Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective (2025.naacl-long)

Challenge:	Natural language inference (NLI) tasks are difficult to perform on large datasets . a small number of simple sentences can improve model performance, authors say .
Approach:	They propose to use syntactically simple sentences to test the inference ability of NLI models.
Outcome:	The proposed set of simple sentences shows that the models fine-tuned on MNLI and SNLI perform poorly on Simple Pair.

Copied to clipboard

Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Hui Liu, Yue Xing, Monica Xiao Cheng, Jiliang Tang

Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs (2025.findings-emnlp)

Challenge:	Existing studies have shown that LLMs struggle to identify the boundaries of their own knowledge and tend to prioritize external information over internal knowledge learned during pre-training.
Approach:	They conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking.
Outcome:	The proposed classifiers improve performance even when dealing with noisy knowledge databases.

Copied to clipboard

Che Liu, Cheng Ouyang, Zhongwei Wan, Haozhe Wang, Wenjia Bai, Rossella Arcucci

Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts (2025.acl-long)

Challenge:	Current methods for multimodal representation learning for electrocardiograms often result in suboptimal alignment of ECG signals with their corresponding text reports.
Approach:	They propose a framework to learn ECG representations by aligning ECG signals with paired free-text reports.
Outcome:	The proposed framework outperforms existing methods in zero-shot classification and linear probing tasks using 12 leads.

Copied to clipboard

Baolong Bi, Shenghua Liu, Lingrui Mei, Yiwei Wang, Junfeng Fang, Pengliang Ji, Xueqi Cheng

Neutralizing Bias in LLM Reasoning using Entailment Graphs (2025.findings-acl)

Challenge:	In-context knowledge editing (ICE) is currently the most effective method for knowledge editing, but it is constrained by the black-box modeling of LLMs and lacks interpretability.
Approach:	They propose a method to decode new knowledge by comparing logits with unedited knowledge to improve the accuracy of LLMs.
Outcome:	The proposed method improves the performance of LLaMA3-8B-instruct on MQuAKE by up to 219%.

Copied to clipboard

Liang Cheng, Tianyi Li, Zhaowei Wang, Tianyang Liu, Mark Steedman

One Cognitive Loop Is Enough: SODA unlocks Pure-Text Spatial Reasoning in Large Language Models (2026.acl-long)

Challenge:	Natural Language Inference (NLI) is a foundational understanding task in language understanding.
Approach:	They propose a framework to construct counterfactual reasoning data and fine-tune LLMs to reduce attestation bias.
Outcome:	The proposed framework reduces hallucinations from attestation bias on original and bias-neutralized datasets while keeping hypotheses unchanged.

Copied to clipboard

Shunwen Bai, Jiahuan Zhang, Haoran Huang, Yurun Wang, Jiale Liu, Yanxi Wu, Ningzhe Yu, Yudong Gao, Mingjun Cheng

HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications (2021.findings-acl)

Challenge:	Existing large language models (LLMs) lack visual input, leading to errors in basic numerical comparisons.
Approach:	They propose a spatial OODA framework that integrates the OODAC cognitive loop into multiple control tasks and integrates it into LLMs.
Outcome:	The proposed model significantly improves the spatial reasoning capabilities of large language models across multiple scenarios including SPOD-Bench, SPACE and applications.

Copied to clipboard

Qiao Cheng, Juntao Liu, Xiaoye Qu, Jin Zhao, Jiaqing Liang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Yanghua Xiao

Cooperative or Competitive? Understanding the Interaction between Attention Heads From A Game Theory Perspective (2025.acl-long)

Challenge:	Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention.
Approach:	They propose a case-oriented construction framework to build a hard case relation extraction dataset with 65,225 relational facts annotated from 9,231 documents.
Outcome:	The proposed model achieves a high 96% F1 score on data quality and is far lower than humans.

Copied to clipboard

Xiaoye Qu, Zengqi Yu, Dongrui Liu, Wei Wei, Daizong Liu, Jianfeng Dong, Yu Cheng

Linguistics & Cognitive NLP

Challenge:	a number of attention-based large language models (LLMs) focus on individual head contributions, but the precise interaction mechanisms between attention heads remain poorly understood.
Approach:	They propose a game-theoretic attention calibration method that uses the Harsanyi dividend . they selectively retain heads demonstrating significant cooperative gains and apply fine-grained adjustments to remaining heads .
Outcome:	The proposed framework is based on the Harsanyi dividend, a concept from cooperative game theory.

Gated Differentiable Working Memory for Long-Context Language Modeling (2026.acl-long)

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Yuyao Ge, Baolong Bi, Jiayu Yao, Jun Wan, Ziling Yin, Jiafeng Guo, Xueqi Cheng

Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing (2025.acl-long)

Challenge:	Long contexts break transformers, attention scores dilute, model cannot adapt to novel patterns at inference time.
Approach:	They propose a framework that gates the memory consolidation process by estimating Contextual Utility . they propose GDWM to maintain a form of working memory with constant contexts .
Outcome:	The proposed framework achieves comparable or superior performance on sparse-information tasks with 4 fewer gradient steps compared to uniform baselines.

Copied to clipboard

Kaishuai Xu, Tiezheng Yu, Wenjun Hou, Yi Cheng, Chak Tou Leong, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li

Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance (2023.findings-acl)

Challenge:	Existing studies to improve mathematical ability typically involve applying preference learning to step-wise solution pairs, but they overlook critical subtle errors.
Approach:	They propose a preference learning framework that injects predefined subtle errors into pivotal tokens to construct hard pairs for error mitigation.
Outcome:	Extensive experiments show that the proposed framework improves on Qwen2-7B-Instruct and MATH with 4.5K training samples.

Copied to clipboard

Wanlong Liu, Shaohuan Cheng, Dingyi Zeng, Qu Hong

Cluster-Former: Clustering-based Sparse Transformer for Question Answering (2021.findings-acl)

Challenge:	Document-level event argument extraction is a challenging task for cross-sentence inference . previous work focused on document-level EAE, but recent work focused more on documentlevel .
Approach:	They propose a document-level event argument extraction model that captures contextual clues and latent role information.
Outcome:	The proposed model outperforms existing methods on two public datasets with 1.13 F1 and 2.64 F1 improvements on RAMS and WikiEvents respectively.

Copied to clipboard

Shuohang Wang, Luowei Zhou, Zhe Gan, Yen-Chun Chen, Yuwei Fang, Siqi Sun, Yu Cheng, Jingjing Liu

Text Clustering

Challenge:	Existing models for encoding long sequences in deep learning suffer from high latency and memory demands.
Approach:	They propose a clustering-based sparse Transformer framework to perform attention across chunked sequences.
Outcome:	The proposed framework achieves state-of-the-art on several major QA benchmarks.

Exploring Mode Connectivity for Pre-trained Language Models (2022.emnlp-main)

Copied to clipboard

Yujia Qin, Cheng Qian, Jing Yi, Weize Chen, Yankai Lin, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

A Compressive Memory-based Retrieval Approach for Event Argument Extraction (2025.coling-main)

Challenge:	Recent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could be found.
Approach:	They investigate the geometric connections of different minima through the lens of mode connectivity, which measures whether two minima can be connected with a low-loss path.
Outcome:	The proposed model can be used to find low-loss paths between two minima, and to understand how their mode connectivity affects their task knowledge.

Copied to clipboard

Wanlong Liu, Enqi Zhang, Shaohuan Cheng, Dingyi Zeng, Li Zhou, Chen Zhang, Malu Zhang, Wenyu Chen

ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning (2023.acl-long)

Challenge:	Existing retrieval-based EAE methods have input length constraints and the gap between the retriever and the inference model.
Approach:	They propose a retrieval-based retrieval mechanism that overcomes input length constraints . they use compressive memory to cache retrieved information and support continuous updates .
Outcome:	The proposed method outperforms retrieval-based methods on three public datasets.

Copied to clipboard

Wenjun Hou, Kaishuai Xu, Yi Cheng, Wenjie Li, Jiang Liu

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)

Challenge:	Existing methods to generate radiology reports only rely on high-level plans, but they lack important information.
Approach:	They propose an Observation-guided radiology Report Generation framework which generates free-text descriptions for a set of radiographs.
Outcome:	The proposed framework outperforms state-of-the-art methods regarding text quality and clinical efficacy.

Copied to clipboard

Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana

Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs (2026.acl-long)

Challenge:	Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100.
Approach:	They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth.
Outcome:	The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth.

Copied to clipboard

Shenglai Zeng, Tianqi Zheng, Chuan Tian, Dante Everaert, Yau-Shian Wang, Yupin Huang, Michael J. Morais, Rohit Patki, Jinjin Tian, Xinnan Dai, Kai Guo, Monica Xiao Cheng, Hui Liu

Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization (2026.findings-acl)

Challenge:	Existing approaches to personalize large language models (LLMs) rely on heuristic methods to compress user profiles but they ignore how LLMs process and prioritize different profile components.
Approach:	They propose an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences and guides a compression model to generate task-relevant compressed user contexts.
Outcome:	The proposed framework outperforms baselines across tasks, token limits, and settings while reducing token usage by 50 times.

Copied to clipboard

Rongjie Huang, Dongchao Yang, Wenxiang Guo, Huadai Liu, Xize Cheng, Zehan Wang, Zhou Zhao, Xixin Wu, Helen M. Meng

A Self-supervised Joint Training Framework for Document Reranking (2022.findings-naacl)

Challenge:	Experimental results show that Flow-matching generative models can scale training by increasing data, computational resources, and model size.
Approach:	They propose a flow-matching transformer with masked generative modeling for scaling text-to-audio inference-time prediction.
Outcome:	The proposed model scales inference-time computations by masking generation and re-predicting them through iterative decoding.

Copied to clipboard

Xiaozhi Zhu, Tianyong Hao, Sijie Cheng, Fu Lee Wang, Hai Liu

Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Challenge:	Pretrained language models have been successfully applied to a wide range of tasks . however, the pretraining tasks were based on the context of documents .
Approach:	They propose a self-supervised joint training framework with a method called Masked Query Prediction to establish semantic relations between given queries and positive documents.
Outcome:	The proposed framework outperforms existing models on document reranking tasks without further pre-training . it uses a self-supervised method to establish semantic relations between given queries and positive documents.

Copied to clipboard

Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu

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

Challenge:	Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach:	They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome:	The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.

Copied to clipboard

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

Distilling Knowledge Learned in BERT for Text Generation (2020.acl-main)

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

Yen-Chun Chen, Zhe Gan, Yu Cheng, Jingzhou Liu, Jingjing Liu

Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs (2026.findings-acl)

Challenge:	Large-scale pre-trained language models such as BERT have revolutionized the state of the art in many language understanding tasks.
Approach:	They propose a conditional masked language modeling approach to fine tune BERT on target generation tasks by imposing global sequence-level supervision on conventional Seq2Seq models.
Outcome:	The proposed model outperforms strong Transformer baselines on multiple language generation tasks such as machine translation and text summarization.

Copied to clipboard

Guangtao Lyu, Qi Liu, Chenghao Xu, Jiexi Yan, Muli Yang, Xueting Li, Fen Fang, Cheng Deng

Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation (P19-1)

Challenge:	Existing training-free methods are vulnerable to the attention sink phenomenon . Existing methods include contrastive decoding and auxiliary expert models .
Approach:	They propose a training-free attention intervention that constructs a PAD map to identify semantically core visual regions and applies per-head Median Absolute Deviation Scaling to adaptively control the intervention strength.
Outcome:	The proposed intervention improves visual grounding and reduces hallucinations on multiple LVLMs and benchmarks.

Copied to clipboard

Zhiqiang Liu, Zuohui Fu, Jie Cao, Gerard de Melo, Yik-Cheung Tam, Cheng Niu, Jie Zhou

Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training (2025.naacl-long)

Challenge:	Rhetoric is a vital element in modern Chinese poetry, and plays an essential role in improving its aesthetics. however, to date, it has not been considered in research on automatic poetry generation.
Approach:	They propose a rhetorically controlled encoder-decoder for modern Chinese poetry generation . their model captures various rhetorical patterns in an encoder and incorporates mixtures .
Outcome:	The proposed model outperforms state-of-the-art methods in terms of fluency, coherence, meaningfulness, and rhetorical aesthetics.

Copied to clipboard

Sun Ao, Weilin Zhao, Xu Han, Cheng Yang, Xinrong Zhang, Zhiyuan Liu, Chuan Shi, Maosong Sun

Formally Specifying the Intended Behavior of the Program: LLM-Driven Neuro-Symbolic Program Specification Synthesis (2026.acl-demo)

Challenge:	Current PP methods face severe bottlenecks, including pipeline bubbles and memory footprint.
Approach:	They propose a sequence-level one-forward-one-backward (1F1B) PP method for training LLMs on long sequences with high throughput and memory efficiency.
Outcome:	The proposed method achieves 1.14X training throughput with half memory footprint compared to baseline methods . it trains an LLM with 30B parameters on sequences up to 64k tokens using 64X NVIDIA A100 GPUs .

Copied to clipboard

Cheng Wen, Hu Junjie, YiKun Hu, Jie Su, Bin Yu, Dugang Liu, Zhiwu Xu, Weidi Sun, Shengchao Qin, Cong Tian

PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy (2025.acl-long)

Challenge:	Formal verification typically requires developers to write detailed formal specifications . a formal verification system that generates candidate specifications is costly and error-prone .
Approach:	They propose an LLM-driven neuro-symbolic demonstration system that reframes specification writing as constrained structured synthesis.
Outcome:	The proposed system reduces hallucinations and produces proof-ready annotations.

Copied to clipboard

Shuhao Guan, Moule Lin, Cheng Xu, Xinyi Liu, Jinman Zhao, Jiexin Fan, Qi Xu, Derek Greene

The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding (2020.acl-demos)

Challenge:	Existing pipelines that combine document image restoration with semantic-aware post-OCR correction can improve text extraction from degraded images.
Approach:	They propose a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency.
Outcome:	The proposed pipeline reduces character error rates by 63.9-70.3% on 13,831 pages of real historical documents in English, French, and Spanish compared to OCR on raw images.

Copied to clipboard

Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao

Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents (2024.acl-long)

Challenge:	MT-DNN is an open-source natural language understanding toolkit . it allows researchers and developers to train customized deep learning models .
Approach:	They present MT-DNN, an open-source natural language understanding toolkit . it is designed to facilitate rapid customization for a broad spectrum of NLU tasks . MT supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop.
Outcome:	The proposed model can significantly compress a large model without significant performance drop.

Copied to clipboard

Cheng Qian, Bingxiang He, Zhong Zhuang, Jia Deng, Yujia Qin, Xin Cong, Zhong Zhang, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)

Challenge:	Current language model-driven agents lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
Approach:	They propose a benchmark to inspect users’ implicit intentions through explicit queries and a model expert as the upstream in agent design to enhance user-agent interaction.
Outcome:	The proposed approach excels at identifying vague user tasks, recovering and summarizing critical missing information, setting precise and necessary agent execution goals, and minimizing redundant tool usage, thus boosting overall efficiency.

Copied to clipboard

Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks (2024.findings-naacl)

Challenge:	Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability.
Approach:	They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs .
Outcome:	The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks.

Copied to clipboard

Xiaodong Yu, Hao Cheng, Xiaodong Liu, Dan Roth, Jianfeng Gao

CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models (2024.findings-acl)

Challenge:	Existing static benchmarks do not guarantee that models can use the provided evidence for answering, which is essential to avoid hallucination when the required knowledge is new or private.
Approach:	They propose to automatically perturb existing static one for dynamic evaluation by using a chatGPT framework and a set of open-domain QA datasets.
Outcome:	The proposed framework generates new test cases on two open-domain QA datasets and is human-readable and useful to trigger hallucination in LLMs.

Copied to clipboard

Linhao Yu, Yongqi Leng, Yufei Huang, Shang Wu, Haixin Liu, Xinmeng Ji, Jiahui Zhao, Jinwang Song, Tingting Cui, Xiaoqing Cheng, Liutao Liutao, Deyi Xiong

Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026.acl-long)

Challenge:	Recent years have witnessed remarkable progress achieved by large language models in both natural language understanding and generation.
Approach:	They propose a large benchmark CMoralEval for moral evaluation of Chinese LLMs . they use a Chinese TV program discussing Chinese moral norms and Chinese moral anomies based on various sources .
Outcome:	The proposed dataset is characterized by diversity and authenticity.

Copied to clipboard

Kailai Yang, Xiao Liu, Lei Ji, Hao Li, Xiao Liang, Zhiwei Liu, Yeyun Gong, Peng Cheng, Mao Yang

LPNL: Scalable Link Prediction with Large Language Models (2024.findings-acl)

Challenge:	Existing methods for reweighting data mixtures rely on manual designation with certain heuristics based on intuition or empirical results.
Approach:	They propose a model-based framework that learns to re-weight domains by reinforcement learning on large quantities of data mixing trajectories with corresponding feedback from an evaluation environment.
Outcome:	The proposed framework outperforms baselines in achieving balanced performance across source and target fields and domain spaces without retraining.

Copied to clipboard

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Xueqi Cheng

Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making (2023.findings-acl)

Challenge:	Existing studies on graph learning with large language models have focused on the link prediction task on large graphs.
Approach:	They propose a framework for scalable link prediction on large-scale heterogeneous graphs based on large language models.
Outcome:	The proposed framework outperforms baselines in link prediction tasks on large graphs.

Copied to clipboard

Xuanjie Fang, Sijie Cheng, Yang Liu, Wei Wang

Uncertainty-Aware Test-Time Search for Optimization Problem Solving (2026.acl-long)

Challenge:	Pre-trained language models (PLMs) have shown strong potential in various downstream tasks.
Approach:	They propose to model adversarial attack task as a sequential decision-making problem where the whole attack process is sequential with two decision- making problems, i.e., word finder and word substitution.
Outcome:	The proposed approach achieves the highest attack success rate with a comparable modification rate and semantic similarity to attack fine-tuned BERT.

Copied to clipboard

Linlin Yu, Xujiang Zhao, Dong Li, Yanchi Liu, Wei Cheng, Zhengzhang Chen, Chen Zhao, Feng Chen, Haifeng Chen

ToolSpectrum: Towards Personalized Tool Utilization for Large Language Models (2025.findings-acl)

Challenge:	Language model hallucinations and limited availability of labeled datasets often result in misaligned formulations, code errors and feasibility failures.
Approach:	They propose a Monte Carlo Tree Search framework that automates optimization problems from natural language descriptions with efficiency and reliability.
Outcome:	The proposed framework achieves state-of-the-art solution accuracy and reduces token usage.

Copied to clipboard

Zihao Cheng, Hongru Wang, Zeming Liu, Yuhang Guo, Yuanfang Guo, Yunhong Wang, Haifeng Wang

KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion (2021.findings-acl)

Challenge:	Existing approaches focus on functional tool selection following user instructions while overlooking the critical role of context-aware personalization in tool selection.
Approach:	They propose a benchmark to evaluate LLMs’ capabilities in personalized tool utilization.
Outcome:	The proposed benchmark evaluates LLMs' capabilities in personalized tool utilization.

Copied to clipboard

Jie Zhou, Shengding Hu, Xin Lv, Cheng Yang, Zhiyuan Liu, Wei Xu, Jie Jiang, Juanzi Li, Maosong Sun

Textual Enhanced Contrastive Learning for Solving Math Word Problems (2022.findings-emnlp)

Challenge:	Existing studies focus on partial aspects of knowledge abstraction, concretization, and completion (KACC).
Approach:	They propose a unified knowledge graph benchmark to improve existing benchmarks . they collect new datasets that contain larger concept graphs and cross-view links .
Outcome:	The proposed benchmark improves existing benchmarks in terms of dataset scale, task coverage, and difficulty.

Copied to clipboard

Yibin Shen, Qianying Liu, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi

Novel Relation Detection: Discovering Unknown Relation Types via Multi-Strategy Self-Supervised Learning (2023.findings-emnlp)

Challenge:	Recent studies show that current models rely on shallow heuristics to predict solutions . a textual Enhanced Contrastive Learning framework enforces the models to distinguish semantically similar examples while holding different mathematical logic.
Approach:	They propose a textual Enhanced Contrastive Learning framework which enforces models to distinguish semantically similar examples while holding different mathematical logic.
Outcome:	The proposed framework improves on benchmark and challenge datasets in English and Chinese.

Copied to clipboard

Qingbin Liu, Yin Kung, Yanchao Hao, Dianbo Sui, Siyuan Cheng, Xi Chen, Ningyu Zhang, Jiaoyan Chen

Low-Resource NLP

Challenge:	Existing approaches to relation extraction can only recognize predefined relation types . new or out-of-scope relation types may continually emerge after the model is deployed .
Approach:	They propose a novel relation detection task that uses self-supervised learning to handle shallow semantic similarity problem.
Outcome:	The proposed method outperforms state-of-the-art methods on two datasets.

MasRouter: Learning to Route LLMs for Multi-Agent Systems (2025.acl-long)

Copied to clipboard

Yanwei Yue, Guibin Zhang, Boyang Liu, Guancheng Wan, Kun Wang, Dawei Cheng, Yiyan Qi

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

Challenge:	Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often face significant costs and challenges in dynamic LLM selection.
Approach:	They propose a multi-agent system routing solution that integrates all components of MAS into a unified routing framework.
Outcome:	The proposed solution is high-performing, cost-effective, and efficient . it reduces overhead by up to 52.07 compared to current methods on HumanEval .

Copied to clipboard

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

Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting (2021.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

Yi Cheng, Siyao Li, Bang Liu, Ruihui Zhao, Sujian Li, Chenghua Lin, Yefeng Zheng

From Model-centered to Human-Centered: Revision Distance as a Metric for Text Evaluation in LLMs-based Applications (2024.findings-acl)

Challenge:	Existing QG systems perform substantially worse in answering multi-hop questions than single-hop ones.
Approach:	They propose a framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.
Outcome:	The proposed framework increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.

Copied to clipboard

Yongqiang Ma, Lizhi Qing, Jiawei Liu, Yangyang Kang, Yue Zhang, Wei Lu, Xiaozhong Liu, Qikai Cheng

Efficient Sequence Learning with Group Recurrent Networks (N18-1)

Challenge:	Existing evaluation metrics for large language models yield numerical scores that ignore user experience.
Approach:	They propose a metric that suggests revision edits that mimic the human writing process . their results show that the metric offers more insightful feedback and distinguishes between texts .
Outcome:	The proposed metric can provide a self-explained text evaluation result in a human-understandable manner beyond the context-independent score.

Copied to clipboard

Fei Gao, Lijun Wu, Li Zhao, Tao Qin, Xueqi Cheng, Tie-Yan Liu

ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervision (2023.eacl-main)

Challenge:	Recurrent neural networks have achieved state-of-the-art results in many artificial intelligence tasks, such as language modeling, neural machine translation and speech recognition.
Approach:	They propose an efficient architecture to improve the efficiency of such RNN model training by adopting the group strategy for recurrent layers while exploiting the representation rearrangement strategy between layers as well as time steps.
Outcome:	The proposed architecture achieves comparable or better accuracy compared with baselines, with a much smaller number of parameters and at a lower computational cost.

Copied to clipboard

Qianying Liu, Wenyu Guan, Jianhao Shen, Fei Cheng, Sadao Kurohashi

Numerical Reasoning

Challenge:	Existing weakly-supervised methods for solving math word problems are expensive and time-consuming.
Approach:	They propose a weakly-supervised approach to solve math word problems . they propose 'comsearch' algorithm which compresses the search space by excluding mathematically equivalent equations.
Outcome:	The proposed algorithm can compress the search space by excluding mathematically equivalent equations.

Multi-Stage Pre-training for Automated Chinese Essay Scoring (2020.emnlp-main)

Copied to clipboard

Wei Song, Kai Zhang, Ruiji Fu, Lizhen Liu, Ting Liu, Miaomiao Cheng

Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning (2022.acl-long)

Challenge:	Existing methods for automatic essay scoring are based on hand-crafted surface-level features, but recent advances in representation learning have improved performance.
Approach:	They propose a pre-training based automated Chinese essay scoring method with weakly supervised pre- training, supervised cross- prompt fine-tuning and supervised target- prompt refine-tuneing.
Outcome:	The proposed method improves a state-of-the-art neural essay scorer in terms of effectiveness and domain adaptation ability, while in-depth analysis also reveals its limitations.

Copied to clipboard

Qin Liu, Rui Zheng, Bao Rong, Jingyi Liu, ZhiHua Liu, Zhanzhan Cheng, Liang Qiao, Tao Gui, Qi Zhang, Xuanjing Huang

Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs (2026.acl-long)

Challenge:	Existing approaches to generating adversarial perturbations scale up the cost of training computational complexity by the number of gradient steps it takes to obtain the adversarials.
Approach:	They propose a flood method which aims at better generalization and a criterion to bring hyper-parameter-dependent flooding into effect with a narrowed-down search space by measuring how the gradient steps taken within one epoch affect the loss of each batch.
Outcome:	The proposed method improves BERT’s resistance to textual adversarial attacks by a large margin and achieves state-of-the-art robust accuracy on various text classification and GLUE tasks.

Copied to clipboard

Yihua Zhu, Qianying Liu, Jiaxin Wang, Fei Cheng, Chaoran Liu, Akiko Aizawa, Sadao Kurohashi, Hidetoshi Shimodaira

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens (2025.acl-demo)

Challenge:	Autoregressive LLMs perform well on relational tasks that require linking entities via relational words, but it is unclear whether they learn the logical semantics of such relations or whether left-to-right order bias is involved.
Approach:	They propose a framework that generates text from symmetric/inverse triples and trains autoregressive models from scratch.
Outcome:	The proposed framework generates text from symmetric/inverse triples, trains autoregressive models from scratch, and evaluates memorization, logical inference, and in-context generalization to unseen entities.

Copied to clipboard

Jiacheng Liu, Taylor Blanton, Yanai Elazar, Sewon Min, Yen-Sung Chen, Arnavi Chheda-Kothary, Huy Tran, Byron Bischoff, Eric Marsh, Michael Schmitz, Cassidy Trier, Aaron Sarnat, Jenna James, Jon Borchardt, Bailey Kuehl, Evie Yu-Yen Cheng, Karen Farley, Taira Anderson, David Albright, Carissa Schoenick, Luca Soldaini, Dirk Groeneveld, Rock Yuren Pang, Pang Wei Koh, Noah A. Smith, Sophie Lebrecht, Yejin Choi, Hannaneh Hajishirzi, Ali Farhadi, Jesse Dodge

Vision-Language Models Can Self-Improve Reasoning via Reflection (2025.naacl-long)

Challenge:	tracing language models' outputs back to training data is a problem because they are trained on text corpora with trillions of tokens . existing methods for tracers have not been scaled to work within this multi-trillion-token setting .
Approach:	They propose a system that traces language models' outputs verbatim back to training data . OLMOTRACE retrieves documents from the model's training data that contain exact matches .
Outcome:	The proposed system can find verbatim matches between LM output and training data . it can be used to explore fact checking, hallucination, and creativity of language models .

Copied to clipboard

Kanzhi Cheng, Li YanTao, Fangzhi Xu, Jianbing Zhang, Hao Zhou, Yang Liu

ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5 (2025.acl-long)

Challenge:	Chain-of-thought (CoT) has been shown to improve the reasoning capability of large language models (LLMs).
Approach:	They propose a framework which iteratively enhances the model’s Vision-language Reasoning by Reflecting on CoT Rationales.
Outcome:	The proposed framework improves multimodal reasoning on vision-language tasks by 23% to 60% over baselines.

Copied to clipboard

Jiaming Zhou, Shiyao Wang, Shiwan Zhao, Jiabei He, Haoqin Sun, Hui Wang, Cheng Liu, Aobo Kong, Yujie Guo, Xi Yang, Yequan Wang, Yonghua Lin, Yong Qin

Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling (2021.findings-acl)

Challenge:	Automatic speech recognition systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0.
Approach:	They propose to use Mandarin speech datasets to analyze pronunciation and tone of children aged 3 to 5 and evaluate their models on speaker verification (SV) They find that the datasets are more robust than those used by adult speech recognition systems and are open-source and available for all academic purposes.
Outcome:	The proposed dataset includes 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation.

Copied to clipboard

Yutai Hou, Yongkui Lai, Cheng Chen, Wanxiang Che, Ting Liu

Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System (2025.findings-acl)

Challenge:	Existing few-shot learning methods learn a single task each time with a few examples . but, real-world applications often contain multiple closely related tasks .
Approach:	They propose a few-shot joint learning scheme that captures intent and slot relationships from only a handful of examples and adapts the bridged metric space to specific few- shot domain.
Outcome:	The proposed model outperforms baseline models on two public datasets on intent and slot . the proposed model significantly outperformed baseline models in one and five shots settings.

Copied to clipboard

Weize Chen, Jiarui Yuan, Chen Qian, Cheng Yang, Zhiyuan Liu, Maosong Sun

DarwinTOD: LLM-Driven Lifelong Self-evolution for Task-oriented Dialog Systems (2026.acl-long)

Challenge:	Large Language Models (LLMs) have emerged as powerful tools for a wide range of tasks, from * Equal Contribution.
Approach:	They propose a framework that enhances communication efficiency and task effectiveness in LLM-based multi-agent systems through training.
Outcome:	The proposed framework improves communication efficiency and task effectiveness on multi-agent tasks with 2.8x performance gain with less than 10% tokens on tasks requiring heavy information exchange.

Copied to clipboard

Shuyu Zhang, Yujie Liu, Xinru Wang, Cheng Zhang, Yanmin Zhu, Bin Li

Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation (2021.acl-long)

Challenge:	Continual learning approaches fail to achieve autonomy lifelong improvement in dynamic environments . current task-oriented dialog systems are static, unable to learn from ongoing interactions .
Approach:	They propose a lifelong self-evolving dialog framework that integrates evolutionary computation and LLM driven self-improvement into a single framework.
Outcome:	The proposed framework surpasses state-of-the-art methods and exhibits continuous performance gains throughout evolution.

Copied to clipboard

Bo Zhang, Xiaoming Zhang, Yun Liu, Lei Cheng, Zhoujun Li

AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models (2024.findings-emnlp)

Challenge:	Existing methods require to learn to adapt the target model by exploiting the source data and sharing the network architecture across domains.
Approach:	They propose a framework that allows to transfer the knowledge of source domain to the unlabeled target domain without using source data.
Outcome:	The proposed framework matches distributions between a trained source model and a set of target data and achieves superior performance on cross-domain text classification.

Copied to clipboard

Jiale Cheng, Yida Lu, Xiaotao Gu, Pei Ke, Xiao Liu, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) exhibit significant but subtle weaknesses, such as mistakes in instruction-following or coding tasks.
Approach:	They propose a framework to automatically expose weaknesses in Large Language Models (LLMs) they use three LLM-powered agents to perform comprehensive weakness identification .
Outcome:	The proposed framework shows that it is more effective than untargeted data augmentation methods like Self-Instruct to identify weaknesses in LLMs.

Copied to clipboard

Wenjun Hou, Yi Cheng, Kaishuai Xu, Wenjie Li, Jiang Liu

DialogGen: Multi-modal Interactive Dialogue System with Multi-turn Text-Image Generation (2025.findings-naacl)

Challenge:	Recent studies have focused on producing concise observations while neglecting the precise attributes that determine the severity of diseases.
Approach:	They propose a model that generates precise radiology reports via dynamic disease progression reasoning by combining historical and spatiotemporal information.
Outcome:	Experiments on two publicly available datasets show the proposed model can generate precise and accurate radiology reports with dynamic disease progression reasoning.

Copied to clipboard

Minbin Huang, Yanxin Long, Xinchi Deng, Ruihang Chu, Jiangfeng Xiong, Xiaodan Liang, Hong Cheng, Qinglin Lu, Wei Liu

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)

Challenge:	Text-to-image (T2I) generation models have advanced in recent years, but effective interaction with these models is challenging for average users due to the need for specialized prompt engineering knowledge and the inability to perform multi-turn image generation.
Approach:	They propose to use off-the-shelf MLLMs and T2I models to build a multi-modal interactive dialogue system (MIDS) that can generate correct output modalities and coherence of output images.
Outcome:	The proposed pipeline can generate correct output modalities and coherent multi-modal outputs compared with other state-of-the-art models.

Copied to clipboard

Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui

Programming Languages in NLP

Challenge:	coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored .
Approach:	They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding.
Outcome:	The proposed benchmark aims to accelerate the development of more scaffold-aware agents.

Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models (2025.findings-acl)

Copied to clipboard

Shuliang Liu, Xinze Li, Zhenghao Liu, Yukun Yan, Cheng Yang, Zheni Zeng, Zhiyuan Liu, Maosong Sun, Ge Yu

Two Streams, One Sarcasm: Orthogonal Expert Tuning for Holistic Multimodal Sarcasm Understanding (2026.acl-long)

Challenge:	Existing evaluation metrics cannot fairly evaluate the outputs of RAG models during training and evaluation.
Approach:	They propose a method which prompts LLMs to generate different judgments based on various combinations of judgment dimensions and utilizes the judge-consistency to evaluate these judgments.
Outcome:	The proposed method generates more accurate evaluations for RAG models across different RAG model and datasets.

Copied to clipboard

Diandian Guo, Cong Cao, Fangfang Yuan, Pin Xu, Cheng Hu, Zhicheng Zhang, Yu Liu, Yanbing Liu

Learning from Sibling Mentions with Scalable Graph Inference in Fine-Grained Entity Typing (2022.acl-long)

Challenge:	Existing benchmarks for multimodal satirical cognition hinder evaluation of multimodal Sarcasm Understanding . lack of a unified benchmark for holistic satire cognition hampers evaluation of MSU .
Approach:	They propose a framework to decouple experts into orthogonal shared perception and private execution streams to physically block gradient interference between tasks.
Outcome:	The proposed framework achieves superior performance on DocMSU-PLUS.

Copied to clipboard

Yi Chen, Jiayang Cheng, Haiyun Jiang, Lemao Liu, Haisong Zhang, Shuming Shi, Ruifeng Xu

Contrastive Distillation on Intermediate Representations for Language Model Compression (2020.emnlp-main)

Challenge:	Existing models struggle to handle hard mentions due to insufficient contexts, limiting their overall typing performance.
Approach:	They propose to exploit sibling mentions to enhance the mention representations by adding unseen test mentions as new nodes for inference.
Outcome:	The proposed model outperforms ten strong baseline models and outperformed strong baselines.

Copied to clipboard

Siqi Sun, Zhe Gan, Yuwei Fang, Yu Cheng, Shuohang Wang, Jingjing Liu

Effective Convolutional Attention Network for Multi-label Clinical Document Classification (2021.emnlp-main)

Challenge:	Existing methods to compress language models use a simple L_2 loss to distill knowledge in the intermediate representations of a large BERT model to a smaller one.
Approach:	They propose a method that uses knowledge distillation to distill knowledge through intermediate layers of the teacher via a contrastive objective.
Outcome:	The proposed method outperforms state-of-the-art methods on the GLUE benchmark.

Copied to clipboard

Yang Liu, Hua Cheng, Russell Klopfer, Matthew R. Gormley, Thomas Schaaf

Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection (2025.emnlp-main)

Challenge:	a large number of medical encounters need to be coded everyday due to long document sets and large label set.
Approach:	They propose a convolutional attention network for multi-label document classification problem . they use convolution-based encoders and convolution networks to aggregate information across documents .
Outcome:	The proposed model outperforms prior best model and multilingual Transformer model on a widely used dataset in the medical domain.

Copied to clipboard

Hong Zhang, Feng Zhao, Ruilin Zhao, Cheng Yan, Kangzheng Liu

MCS: An In-battle Commentary System for MOBA Games (2022.coling-1)

Challenge:	Existing methods for instruction selection rely on external models or rules, overlooking the intrinsic association between pre-trained model and instruction data.
Approach:	They propose a method that utilizes noise injection to identify the quality of instruction data without relying on external models.
Outcome:	The proposed method outperforms the model trained on the entire dataset and established baselines.

Copied to clipboard

Xiaofeng Qi, Chao Li, Zhongping Liang, Jigang Liu, Cheng Zhang, Yuanxin Wei, Lin Yuan, Guang Yang, Lanxiao Huang, Min Li

Challenge:	In-battle commentary is an important component of live streaming of e-sports competitions and is applicable to a wide range of scenarios like combat information analysis and live streaming.
Approach:	They propose a generative system for in-battle real-time commentary in mobile MOBA games and propose 'transform' method to convert match statistics and utterances into consistent encoding space.
Outcome:	The proposed system is based on real-time match statistics and events and can be used for live streaming, e-sports commentary and combat information analysis.

Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs (2026.findings-eacl)

Copied to clipboard

Honghao Liu, Xuhui Jiang, Chengjin Xu, Cehao Yang, Yiran Cheng, Lionel Ni, Jian Guo

Curriculum Consistency Learning for Conditional Sentence Generation (2024.emnlp-main)

Challenge:	Existing methods to protect PII from training on small corpora are difficult to implement in real-world applications.
Approach:	They propose an entity-based framework that synthesizes encrypted training data to protect PII.
Outcome:	The proposed framework outperforms base models and ensures PII security on limited-scale datasets while exhibiting a modest performance gap compared to models trained on unencrypted synthetic data.

Copied to clipboard

Liangxin Liu, Xuebo Liu, Lian Lian, Shengjun Cheng, Jun Rao, Tengfei Yu, Hexuan Deng, Min Zhang

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

Challenge:	Consistency learning (CL) has proven to be a valuable technique for improving the robustness of conditional sentence generation models.
Approach:	They propose a strategy that guides models to learn consistency in alignment with their current capacity to differentiate between features.
Outcome:	The proposed strategy delivers +2.0 accuracy point improvement compared with vanilla IT and +0.7 COMET scores over traditional CL methods in MT tasks.

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.

The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems (2025.findings-acl)

Copied to clipboard

Hongru Song, Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Jianming Lv, Maarten de Rijke, Xueqi Cheng

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)

Challenge:	Existing studies have focused on corpus poisoning, but there are no studies on adversarial attacks on RAG systems.
Approach:	They propose a novel imperceptible retrieve-to-generate attack against RAG systems . they propose regenerative reinforcement learning framework that tracks interactions between attacker and target RAG .
Outcome:	The proposed framework outperforms existing attacks on factual and non-factual RAG systems with small imperceptible text perturbations.

Copied to clipboard

Junxiao Yang, Haoran Liu, Jinzhe Tu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Jiaqi Weng, Jialing Tao, Hui Xue, Hongning Wang, Han Qiu, Minlie Huang

Challenge:	Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages.
Approach:	They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks.
Outcome:	The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B).

Compete to Complete: Co-opetition Adversarial Learning for Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Xin Liu, Yu-An Liu, Ruqing Zhang, Yixing Fan, Lixin Su, Jiafeng Guo, Xueqi Cheng

Reducing Word Omission Errors in Neural Machine Translation: A Contrastive Learning Approach (P19-1)

Challenge:	Existing approaches to reduce hallucination in large language models lack a robust mechanism for generating a generative model.
Approach:	They propose a framework that formulates retriever–generator training in RAG as a minimax game.
Outcome:	The proposed framework improves retrieval-augmented generation performance on seven benchmark datasets.

Copied to clipboard

Zonghan Yang, Yong Cheng, Yang Liu, Maosong Sun

GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification (P19-1)

Challenge:	Existing methods for reducing word omission errors in neural machine translation are prone to omit essential words on the source side.
Approach:	They propose a contrastive learning approach to reduce word omission errors in NMT by omitting words.
Outcome:	The proposed approach achieves better translation performance than baseline methods on Chinese-to-English, German-to English, and Russian-toEnglish translation tasks.

Copied to clipboard

Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun

Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems (2022.aacl-short)

Challenge:	Existing methods to extract information from evidence are unable to grasp relational and logical information among the evidence.
Approach:	They propose a graph-based evidence aggregating and reasoning framework to integrate evidence from multiple pieces of evidence.
Outcome:	The proposed framework achieves significant performance improvements on a large-scale benchmark dataset.

Copied to clipboard

Yibin Shen, Qianying Liu, Zhuoyuan Mao, Zhen Wan, Fei Cheng, Sadao Kurohashi

Exploiting Contextual Information via Dynamic Memory Network for Event Detection (D18-1)

Challenge:	Existing methods to solve Math Word Problems rely on human annotation . empirical results suggest that our method universally improves the performance on single-unknown and multiple-un unknown benchmarks.
Approach:	They propose a controlled equation generation solver by leveraging a set of control codes to guide the model to consider certain reasoning logic and decode the corresponding equations expressions transformed from the human reference.
Outcome:	The proposed method improves performance on single-unknown and multiple-un unknown benchmarks with 13.2% accuracy on the challenging multiple-unequal datasets.

Copied to clipboard

Shaobo Liu, Rui Cheng, Xiaoming Yu, Xueqi Cheng

Discourse-Aware Neural Extractive Text Summarization (2020.acl-main)

Challenge:	Existing methods for event detection only process context once . a multi-hop mechanism to capture contextual information improves performance .
Approach:	They propose to use dynamic memory network to capture contextual information . they propose to model event triggers by identifying word or phrase which most represents it .
Outcome:	The proposed model achieves best F1 score compared to the state-of-the-art models.

Copied to clipboard

Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu

From Implicit Graph Encoding to Explicit Evidence: A Training-Free LLM Framework for Temporal Knowledge Graph Reasoning (2026.findings-acl)

Challenge:	Recent studies have shown that sentence-based extractive models result in redundant or uninformative phrases in the extracted summaries.
Approach:	They propose a discourse-aware neural summarization model that extracts sub-sentential discourse units as candidates for extractive selection on a finer granularity.
Outcome:	Experiments show that the proposed model outperforms state-of-the-art models on popular summarization benchmarks.

Copied to clipboard

Guo Tang, Ke Cheng, Huiming Fan, Heng Chang, Wenxiang Zheng, Xianhao Ou, Junjia Xiang, Ming Liu, Yujun Zhou, Li Lanyu, Bing Qin

AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Challenge:	Existing Large Language Models (LLMs) struggle with implicit modality alignment and suboptimal graph linearization.
Approach:	They propose a training-free, test-time adaptive framework that reframes TKG prediction as explicit evidence-driven reasoning.
Outcome:	ExE-LLM outperforms fully trained graph neural networks on four benchmarks . it achieves SOTA performance in inductive settings, significantly outperforming fully trained neural networks .

Copied to clipboard

Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang

A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)

Challenge:	Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach:	They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome:	The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.

Copied to clipboard

Hanyu Lai, Xiao Liu, Junjie Gao, Jiale Cheng, Zehan Qi, Yifan Xu, Shuntian Yao, Dan Zhang, Jinhua Du, Zhenyu Hou, Xin Lv, Minlie Huang, Yuxiao Dong, Jie Tang

Evaluating Memory Capability in Continuous Lifelog Scenario (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages.
Approach:	They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies.
Outcome:	The proposed model can be used to understand and generate human natural languages.

Copied to clipboard

Jianjie Zheng, Zhichen Liu, Zhanyu Shen, Jingxiang Qu, Guanhua Chen, Yile Wang, Yang Xu, Yang Liu, Sijie Cheng

Challenge:	Existing benchmarks focus on online one-on-one chatting or human-AI interactions, neglecting real-world scenarios.
Approach:	They propose a framework to curate a lifelog benchmark that combines two subsets of audio data to address temporal leakage in offline settings.
Outcome:	The proposed framework outperforms existing benchmarks on live chats and AI interactions.

Unsupervised Concept Representation Learning for Length-Varying Text Similarity (2021.naacl-main)

Copied to clipboard

Xuchao Zhang, Bo Zong, Wei Cheng, Jingchao Ni, Yanchi Liu, Haifeng Chen

Representation Learning

Challenge:	Existing document similarity approaches suffer from the information gap caused by context and vocabulary mismatches when comparing varying-length texts.
Approach:	They propose an unsupervised concept representation learning approach to address this issue . they propose a concept-based document matching method to leverage recognition of local phrase features .
Outcome:	The proposed method achieves a better F1 score than baseline models on real-world data sets.

DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding (2026.findings-acl)

Copied to clipboard

Jiaming Zhou, Xuxin Cheng, Shiwan Zhao, Yuhang Jia, Cao Liu, Ke Zeng, Xunliang Cai, Yong Qin

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities (2023.acl-demo)

Challenge:	Autoregressive (AR) large audio language models are expensive in data and computation . prior work shows diffusion-based LALMs can improve audio understanding under matched settings .
Approach:	They propose a diffusion-based LALM that upgrades the speech encoder and employs dual semantic and acoustic adapters.
Outcome:	a new model improves over existing autoregressive large language models and is competitive to strong AR models . the proposed model can make use of limited training data and improve inference efficiency . a recent study shows that diffusion-based models can improve audio understanding .

Copied to clipboard

Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Gou, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan

Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection (2026.findings-acl)

Challenge:	Several pre-training models of different modalities are showing a rising trend of homogeneity in their model structures.
Approach:	They propose a toolkit that supports pre-training models of different modalities.
Outcome:	The proposed toolkit can match the performance of the original implementations on text, vision, and audio benchmarks.

Copied to clipboard

Zhuoyang Wu, Xinze Li, Zhenghao Liu, Yukun Yan, Zhiyuan Liu, Minghe Yu, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun

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

Challenge:	Existing studies treat SLMs as student models and use long-form Chains-of-Thought (CoTs) as supervision signals for Supervised Fine-Tuning (SFT). Existing research focuses on distilling reasoning ability from LLMs to enhance the mathematical reasoning performance of small-scale models.
Approach:	They propose a framework that refines teacher CoTs through an error-aware reflection process to enable the student model to construct more tailored teacher Cots.
Outcome:	Experiments on multiple mathematical reasoning benchmarks show that ORION improves performance by more than 2% over all baselines.

Copied to clipboard

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

Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support (2025.emnlp-industry)

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

Cen Zhao, Tiantian Zhang, Hanchen Su, Yufeng Zhang, Shaowei Su, Mingzhi Xu, Yu Liu, Wei Han, Jeremy Werner, Claire Na Cheng, Yashar Mehdad

Challenge:	Existing offline approaches to improve an LLM-based customer support system rely on batch annotations.
Approach:	They propose an agent-in-the-loop framework that integrates four key types of annotations directly into live customer operations: (1) pairwise response preferences, (2) agent adoption and rationales, (3) knowledge relevance checks, and (4) identification of missing knowledge.
Outcome:	The proposed framework reduces retraining cycles from months to weeks by integrating four key types of annotations directly into live customer operations.

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities (2025.naacl-long)

Copied to clipboard

Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao

AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models (2023.acl-short)

Challenge:	Recent research shows that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks.
Approach:	They propose a framework that crafts adversarial LLMs with enhanced jailbreak ability.
Outcome:	ADV-LLM significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs.

Copied to clipboard

Siheng Li, Cheng Yang, Yichun Yin, Xinyu Zhu, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang

DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering (2025.acl-long)

Challenge:	Existing research on information-seeking conversations is stymied by the lack of training data.
Approach:	They propose to use autoconv for synthetic conversation generation to capture the characteristics of the information-seeking process and fine tune an LLM with a few human conversations to generate synthetic conversations with high quality.
Outcome:	The proposed model improves on two commonly-used datasets and alleviates the dependence on human annotation.

Copied to clipboard

Rong Cheng, Jinyi Liu, Yan Zheng, Fei Ni, Jiazhen Du, Hangyu Mao, Fuzheng Zhang, Bo Wang, Jianye Hao

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

Challenge:	Existing approaches to multi-hop question answering struggle to identify and organize dynamic knowledge . et al., 2023; Liu e.t. al. 2023) suggest a dual-process framework for multi-step reasoning .
Approach:	They propose a synergistic dual-process framework that integrates reasoning and retrieval.
Outcome:	The proposed framework improves answer accuracy and coherence even in smaller-scale models.

Copied to clipboard

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

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

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

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

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents (2026.acl-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

Jinchang Zhu, Jindong Li, Cheng Zhang, Jiahong Liu, Menglin Yang

Asymmetric Mutual Learning for Multi-source Unsupervised Sentiment Adaptation with Dynamic Feature Network (2022.coling-1)

Challenge:	Existing memory systems represent conversation history as unstructured embedding vectors, retrieving information through semantic similarity.
Approach:	They propose a bio-inspired memory architecture that models memory as a dynamic graph with Hebbian learning dynamics.
Outcome:	The proposed architecture leverages both semantic similarity and learned associations . it can be used to build a bio-inspired memory graph with Hebbian learning dynamics .

Copied to clipboard

Rui Li, Cheng Liu, Dazhi Jiang

PEPE: Long-context Extension for Large Language Models via Periodic Extrapolation Positional Encodings (2025.findings-emnlp)

Challenge:	Recent work on pre-trained language models (PrLMs) on labeled sentiment datasets has shown significant improvements on widerange of NLP tasks, including sentiment classification.
Approach:	They propose a multi-source unsupervised sentiment adaptation problem with pre-trained features to exploit the extracted pre-train features for efficient domain adaptation.
Outcome:	The proposed model outperforms the state-of-the-art methods on multiple sentiment benchmarks and extensive ablation studies to verify the effectiveness of each module.

Copied to clipboard

Jikun Hu, Dongsheng Guo, Yuli Liu, Qingyao Ai, Lixuan Wang, Xuebing Sun, Qilei Zhang, Quan Zhou, Cheng Luo

Zero-shot Jianzi Recognition as Structured Visual Information Extraction in Open Compositional Symbolic Systems (2026.acl-long)

Challenge:	Long-context extension attempts to extend contextual window in pre-trained LLMs . primary method involves expanding initial positional encodings, disrupting positional learning .
Approach:	They propose a new extension strategy based on Rotary Position Embedding to extend contextual window in pre-trained large language models.
Outcome:	The proposed method can extend the contextual window in pre-trained large language models . expansion disrupts positional encodings learned during pre-training, authors show .

Copied to clipboard

Zehan Li, Fu Zhang, Zhijun Liu, Jingwei Cheng

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

Challenge:	Optical character recognition (OCR) is a relatively new form of tablature recognition, but its accuracy is limited due to its unbounded composition and manuscript-level variability.
Approach:	They propose a method that predicts component sequences under a zero-shot split and synthesize manuscript-like training images via component-wise style recomposition and manuscript-domain noise modeling.
Outcome:	The proposed method achieves 63.02% sequence accuracy on real-world Jianzi benchmark, surpassing Gemini-3-Pro by 35.11%.

Copied to clipboard

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

What Language Do Non-English-Centric Large Language Models Think in? (2025.findings-acl)

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

Chengzhi Zhong, Qianying Liu, Fei Cheng, Junfeng Jiang, Zhen Wan, Chenhui Chu, Yugo Murawaki, Sadao Kurohashi

MedQPA-Gen: Medical Question Proposing and Answering for Report Generation (2026.findings-acl)

Challenge:	Despite their robust performance in English, these models often exhibit reduced proficiency in non-English languages, and their outputs may reflect an inherent bias toward English-centric perspectives.
Approach:	They categorize non-English-centric large language models into two groups: CPMs and BLMs, which are pre-trained on a balanced mix of multiple languages from scratch.
Outcome:	The proposed models exhibit a pronounced internal preference for English tokens when projected into the vocabulary space.

Copied to clipboard

Weijie Liang, Xiyue Zhu, Ruike Zhu, Chenhao Li, Cheng Tang, Zhiyu Liu, Zhihua Gong, Shirui Luo, Yudu Li, Volodymyr Kindratenko

DEEM: Dynamic Experienced Expert Modeling for Stance Detection (2024.lrec-main)

Challenge:	Existing training paradigms fail to explicitly target factual accuracy, resulting in inaccuracies and serious patient safety risks.
Approach:	They propose an automatic and generalizable report evaluation technique that uses question proposing and answering to enable controllable, structured reasoning grounded in medical domain knowledge and the factual correctness of the report.
Outcome:	The proposed method can improve human preference scores and perform better on downstream tasks.

Copied to clipboard

Xiaolong Wang, Yile Wang, Sijie Cheng, Peng Li, Yang Liu

Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering (2023.acl-short)

Challenge:	Existing work on stance detection tasks using large language models shows promising results, but it may not be able to provide detailed background knowledge.
Approach:	They propose a method which leverages the generated experienced experts and lets LLMs reason in a semi-parametric way.
Outcome:	The proposed method outperforms methods with self-consistency reasoning and reduces bias.

Copied to clipboard

Hao Cheng, Hao Fang, Xiaodong Liu, Jianfeng Gao

Do LLM Agents Really Mimic Humans? Diagnosing and Aligning Microeconomic Behaviors in Macro-ABMs (2026.findings-acl)

Challenge:	Existing dense retrieval models are parameter-inefficient and underperform sparse counterparts.
Approach:	They propose a task-aware specialization for dEnse Retrieval architecture that enables parameter sharing by interleaving shared and specialized blocks in a single encoder.
Outcome:	The proposed architecture surpasses BM25 on questions and passages using 60% of the parameters as bi-encoder dense retrievers.

Copied to clipboard

Guangya Liu, Cheng Wang, Jiangtong Li, Huafei Wu, Changjun Jiang

Challenge:	Existing studies focus on replicating macro-level stylized facts while neglecting verification of micro-level decision-making.
Approach:	They propose a framework that replicates macro-level stylized facts while ignoring micro-level decision-making.
Outcome:	The proposed framework improves alignment with human trends and captures behavioral heterogeneity.

TRUST: Towards Robust Social Bot Detection via Uncertainty-Guided Pseudo-Labeling and Graph Structure Purification (2026.findings-acl)

Copied to clipboard

Ruixuan Xu, Mengting Hu, Zhunheng Wang, Ming Jiang, Rui Ying, Zhen Zhang, Hang Gao, Shuaipeng Liu, Renhong Cheng

Multi-Stage LLM Fine-Tuning with a Continual Learning Setting (2025.findings-naacl)

Challenge:	Existing graph-based detection models are vulnerable to deceptive message propagation, where bots deliberately interact with legitimate users.
Approach:	They propose a framework to mitigate deceptive message propagation by node-level uncertainty estimation and graph structure purification.
Outcome:	The proposed framework improves on three benchmark datasets and six GNN backbones on real-world social bots.

Copied to clipboard

Changhao Guan, Chao Huang, Hongliang Li, You Li, Ning Cheng, Zihe Liu, Yufeng Chen, Jinan Xu, Jian Liu

Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision (2023.findings-eacl)

Challenge:	Large language models (LLMs) have made significant progress in knowledge-intensive applications, but they may face a multi-stage continuous learning scenario.
Approach:	They propose a multi-stage continuous learning paradigm that includes a preference-based learning bias to identify potential knowledge conflicts and a self-distillation-based data augmentation strategy to expand and enrich the training corpus.
Outcome:	The proposed learning paradigm achieves a significant improvement in accuracy after 7 stages of fine-tuning compared to previous methods while preserving general knowledge.

Copied to clipboard

Zhen Wan, Fei Cheng, Qianying Liu, Zhuoyuan Mao, Haiyue Song, Sadao Kurohashi

Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs (2025.coling-main)

Challenge:	Existing methods ignore the intrinsic noise of distant supervision during the pre-training stage.
Approach:	They propose a weighted contrastive learning method that explicitly reduces noise . they leverage supervised data to estimate reliability and reduce noise compared to non-weighted baselines .
Outcome:	The proposed method reduces the noise of distant supervision and estimates reliability of pre-training instances.

Copied to clipboard

Chuang Liu, Renren Jin, Zheng Yao, Tianyi Li, Liang Cheng, Mark Steedman, Deyi Xiong

Challenge:	Existing benchmarks for evaluating large language models neglect key qualitative data attributes that can significantly impact the final rankings of LLMs.
Approach:	They propose a framework with three modules designed to assess diversity, redundancy, and difficulty.
Outcome:	The proposed framework systematically incorporates diversity, redundancy, and difficulty attributes and shows that they influence the ranking of LLMs.

KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction (2024.acl-long)

Copied to clipboard

Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Lixiang Lixiang, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

EBERT: Efficient BERT Inference with Dynamic Structured Pruning (2021.findings-acl)

Challenge:	None. None.. None!
Approach:	None. None.. None!
Outcome:	None. None. No. :

Copied to clipboard

Zejian Liu, Fanrong Li, Gang Li, Jian Cheng

Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation (2024.findings-emnlp)

Challenge:	Pruning has been demonstrated as an effective way of reducing computational complexity for deep networks, especially CNNs for computer vision tasks.
Approach:	They propose a dynamic structured pruning algorithm that prunes model weights at run-time . they propose to prune the unimportant heads in multi-head self-attention layers .
Outcome:	The proposed algorithm outperforms state-of-the-art methods on different tasks.

Copied to clipboard

Qin Zhu, Qinyuan Cheng, Runyu Peng, Xiaonan Li, Ru Peng, Tengxiao Liu, Xipeng Qiu, Xuanjing Huang

Dissecting GraphRAG: A Modular Analysis of Knowledge Structuring for Factoid Question Answering (2026.tacl-1)

Challenge:	Current LLMs are achieving better performance on various benchmarks, but their performance in practical applications does not always match their benchmark results.
Approach:	They propose to detect and rewrite leaked benchmarks without altering their difficulties by using Inference-Time Decontamination (ITD) to mitigate performance inflation caused by memorizing leaked samples.
Outcome:	The proposed method reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU.

Copied to clipboard

Noriki Nishida, Rumana Ferdous Munne, Shanshan Liu, Narumi Tokunaga, Yuki Yamagata, Fei Cheng, Kouji Kozaki, Yuji Matsumoto

TestAgent: An Adaptive and Intelligent Expert for Human Assessment (2025.findings-acl)

Challenge:	GraphRAG integrates structured knowledge graphs into question answering . high-quality triple extraction is critical, but lacks granularity and topical coherence . large language models suffer from inherent limitations in their internalized knowledge .
Approach:	They evaluate module-level design choices in GraphRAG for retrieval-augmented generation . they find that triple extraction is critical for accurate and comprehensive retrieval .
Outcome:	The proposed framework outperforms other retrieval-augmented generation frameworks in accuracy and efficiency.

Copied to clipboard

Junhao Yu, Yan Zhuang, Yuxuan Sun, Weibo Gao, Qi Liu, Mingyue Cheng, Zhenya Huang, Enhong Chen

a1: Steep Test-time Scaling Law via Environment Augmented Generation (2026.findings-acl)

Challenge:	Existing adaptive testing methods face several challenges due to mechanized nature of most algorithms and noisy response data.
Approach:	They propose to use large language models to enhance adaptive testing through interactive engagement to capture test-takers’ responses and anomalies.
Outcome:	The proposed agent achieves more accurate results with 20% fewer questions than state-of-the-art baselines and testers preferred it in speed, smoothness, and other dimensions.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Yuyao Ge, Jun Wan, Yurong Wu, Xueqi Cheng

FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have made remarkable advances in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks.
Approach:	They propose a framework that enhances LLM reasoning through real-time environmental feedback validating each reasoning step, dynamic branch exploration for investigating alternative solution paths when faced with errors, and experience-based learning from successful reasoning trajectories.
Outcome:	The proposed model outperforms comparable models by 24.4 percentage points across benchmarks while outperforming comparable models.

Copied to clipboard

Xiao Li, Bolin Zhu, Kaiwen Shi, Sichen Liu, Yin Zhu, Yiwei Liu, Gong Cheng

Logic-Thinker: Teaching Large Language Models to Think more Logically. (2025.findings-emnlp)

Challenge:	Existing datasets for numerical reasoning often lack explicit knowledge of formulas . current datasets do not provide process supervision information, resulting in incomplete reasoning .
Approach:	They propose a benchmark for formula-based numerical reasoning with 5,324 questions . they provide annotations in English and Chinese and a formula database as an external knowledge source .
Outcome:	The proposed model includes 5,324 questions requiring calculations grounded in external physics principles.

Copied to clipboard

Chengyao Wen, Qiang Cheng, Shaofei Wang, Zhizhen Liu, Deng Zhao, Lei Liang

OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents (2025.findings-acl)

Challenge:	Recent Large Reasoning Models (LRMs) have demonstrated the ability to generate long chains of thought (LongCoT) LongCoT still faces challenges such as redundancy and logical incoherence.
Approach:	They propose a neural-symbolic reasoning framework that generates chains of thought . they propose Logic-Thinker, which transforms symbolic solvers into chains of thoughts .
Outcome:	The proposed framework outperforms models fine-tuned with ThinkerCoT on logic reasoning tasks.

Copied to clipboard

Pengzhou Cheng, Zheng Wu, Zongru Wu, Tianjie Ju, Aston Zhang, Zhuosheng Zhang, Gongshen Liu

S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning (2025.acl-long)

Challenge:	Existing efforts to build GUI agents focused on the autonomous mode have failed to address the problem of over-execution.
Approach:	They propose an adaptive GUI agent that predicts confidence levels at each interaction step and elicits adaptive interaction.
Outcome:	The proposed GUI agent outperforms existing models on a complex dataset and on established benchmarks.

Copied to clipboard

Ruotian Ma, Peisong Wang, Cheng Liu, Xingyan Liu, Jiaqi Chen, Bang Zhang, Xin Zhou, Nan Du, Jia Li

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Challenge:	Existing approaches to incentivize LLMs’ deep thinking abilities require large-scale data or significant training efforts.
Approach:	They introduce an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.
Outcome:	The proposed framework outperforms models trained on long-CoT distilled data with 3.1k initialization samples and achieves an accuracy improvement of 51.0% to 81.6%.

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

Density-Aware Prototypical Network for Few-Shot Relation Classification (2023.findings-emnlp)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Jianfeng Wu, Mengting Hu, Yike Wu, Bingzhe Wu, Yalan Xie, Mingming Liu, Renhong Cheng

JarviX: A LLM No code Platform for Tabular Data Analysis and Optimization (2023.emnlp-industry)

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

Shang-Ching Liu, ShengKun Wang, Tsungyao Chang, Wenqi Lin, Chung-Wei Hsiung, Yi-Chen Hsieh, Yu-Ping Cheng, Sian-Hong Luo, Jianwei Zhang

Glyph: Scaling Context Windows via Visual-Text Compression (2026.acl-long)

Challenge:	Tabular data analysis is an important application task of large language models, but advanced models are not yet on par with expert level performance.
Approach:	They propose to employ Large Language Models to facilitate an automated guide and execute high-precision data analyzes on tabular datasets.
Outcome:	The proposed framework is based on large language models and an automated machine learning pipeline for predictive modeling.

Copied to clipboard

Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang

Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning (2022.emnlp-main)

Challenge:	Large language models (LLMs) traditionally represent text as sequences of discrete tokens . a long-context scaling problem requires processing more tokens more efficiently .
Approach:	They propose a framework that renders long texts into compact visual pages and processes them with a vision-language model.
Outcome:	The proposed framework renders long texts into compact visual pages and processes them with a vision-language model.

Copied to clipboard

Yi Cheng, Wenge Liu, Wenjie Li, Jiashuo Wang, Ruihui Zhao, Bang Liu, Xiaodan Liang, Yefeng Zheng

M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework (2025.emnlp-main)

Challenge:	Existing research on building ES conversation systems only considered single-turn interactions with users, which is over-simplified and has limited support for multi-turn systems.
Approach:	They propose a multi-turn ES conversation system that uses lookahead heuristics to estimate future user feedback after using particular strategies.
Outcome:	The proposed system significantly outperforms baselines in both dialogue generation and strategy planning.

Copied to clipboard

Yew Ken Chia, Liying Cheng, Hou Pong Chan, Maojia Song, Chaoqun Liu, Mahani Aljunied, Soujanya Poria, Lidong Bing

NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding (2024.findings-emnlp)

Challenge:	Existing benchmarks for large multimodal models focus on short documents with less than 50 pages and are limited to extraction-based questions.
Approach:	They propose a retrieval-aware tuning approach to improve the accuracy of multimodal document reading by 4.6%.
Outcome:	The proposed framework improves the accuracy of model responses by 4.6% compared to existing benchmarks on documents with hundreds of pages and longer documents with more complex content.

Copied to clipboard

Chunkit Chan, Cheng Jiayang, Yauwai Yim, Zheye Deng, Wei Fan, Haoran Li, Xin Liu, Hongming Zhang, Weiqi Wang, Yangqiu Song

Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction (2022.emnlp-main)

Challenge:	Theory of mind evaluations currently focus on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations.
Approach:	They propose a benchmark to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states.
Outcome:	The proposed benchmark builds upon the Belief-Desire-Intention theory and conducts the necessary empirical experiments to evaluate large language models.

Copied to clipboard

Zhen Wan, Qianying Liu, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi, Jiwei Li

Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models (2026.eacl-long)

Challenge:	Existing RE models are incapable of handling implicit expressions and long-tail relation types due to language complexity and data sparsity.
Approach:	They propose a method to enhance relation extraction using k nearest neighbors (kNN-RE) kNN is a nearest-neighbor search tool that allows the model to consult training relations at test time .
Outcome:	The proposed model outperforms the best model to date on ACE05, SciERC, and Wiki80 datasets and outperformed the best on i2b2 and Wik80 dataset.

Copied to clipboard

Chengzhi Zhong, Fei Cheng, Qianying Liu, Yugo Murawaki, Chenhui Chu, Sadao Kurohashi

7 Points to Tsinghua but 10 Points to ? Assessing Large Language Models in Agentic Multilingual National Bias (2025.findings-acl)

Challenge:	Prior studies show that large language models map multilingual content into English-aligned representations at intermediate layers before projecting them back into target-language token spaces in the later layers.
Approach:	They propose a method to identify and manipulate dimensions that are sparse and sparsity-based . they propose to use as few as 50 sentences of either parallel or monolingual data to manipulate these dimensions .
Outcome:	Experiments on a multilingual generation control task show the interpretability of these dimensions.

Copied to clipboard

Qianying Liu, Katrina Qiyao Wang, Fei Cheng, Sadao Kurohashi

LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models (2025.findings-acl)

Challenge:	Large Language Models have garnered significant attention for their capabilities in multilingual natural language processing, but studies on risks associated with cross biases are limited to immediate context preferences.
Approach:	They investigate multilingual bias in state-of-the-art Large Language Models by analyzing their responses to decision-making tasks across multiple languages.
Outcome:	The proposed model can provide personalized advice across university applications, travel, and relocation scenarios.

Copied to clipboard

Jiayi Gui, Yiming Liu, Jiale Cheng, Xiaotao Gu, Xiao Liu, Hongning Wang, Yuxiao Dong, Jie Tang, Minlie Huang

KnowCoder-X: Boosting Multilingual Information Extraction via Code (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated notable capabilities across various tasks, showcasing complex problem-solving abilities.
Approach:	They propose a benchmark to evaluate the rule-based logical reasoning capabilities of Large Language Models (LLMs) they create simulated scenarios in which models execute or plan operations to achieve specific outcomes.
Outcome:	The proposed benchmark evaluates the performance of large language models on a variety of scenarios with varying difficulty levels.

Copied to clipboard

Yuxin Zuo, Wenxuan Jiang, Wenxuan Liu, Zixuan Li, Long Bai, Hanbin Wang, Yutao Zeng, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Multilinguality

Challenge:	Empirical evidence indicates that Large Language Models exhibit spontaneous cross-lingual alignment in Information Extraction (IE) however, a significant imbalance across languages persists, highlighting an underlying deficiency.
Approach:	They propose a code LLM with advanced cross-lingual and multilingual capabilities for universal IE that standardizes the representation of multilingual schemas using Python classes and conducts IE alignment instruction tuning on translated instance prediction task.
Outcome:	The proposed model surpasses ChatGPT and SoTA by 30.17% without training in 29 unseen languages and significantly improves cross-lingual IE transferability.

CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision (2025.acl-long)

Copied to clipboard

YifeiLu YifeiLu, Fanghua Ye, Jian Li, Qiang Gao, Cheng Liu, Haibo Luo, Nan Du, Xiaolong Li, Feiliang Ren

Programming Languages in NLP

Challenge:	Existing approaches to tool invocation are often unnecessarily long and require lengthy reasoning paths.
Approach:	They propose a framework for stepwise code generation that improves LLM tool invocation . they incorporate two distinct process rewards: the On-the-spot and the Latent Reward .
Outcome:	The proposed framework improves LLM tool invocation by leveraging the concise nature of code.

Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks (2023.findings-acl)

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Yile Wang, Peng Li, Yang Liu

Low-Resource NLP

Challenge:	Recent studies focus on retrieval to solve knowledge-intensive tasks, but the potential of retrieval for non-knowledge-intensive (NKI) tasks remains under-explored.
Approach:	They propose a task-agnostic retrieval framework for NKI tasks that uses a static index and a prompt-guided reranker to re-rank the nearest evidence according to task-specific relevance.
Outcome:	The proposed framework outperforms state-of-the-art retrieval-augmented methods on NKI tasks and will be released for further research.

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability (2025.findings-emnlp)

Copied to clipboard

Dong Shu, Haiyan Zhao, Jingyu Hu, Weiru Liu, Ali Payani, Lu Cheng, Mengnan Du

MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper (2025.emnlp-main)

Challenge:	Large Vision-Language Models have demonstrated remarkable capabilities in processing both visual and textual information.
Approach:	They examine the challenge of alignment and misalignment in LVLMs through an explainability lens.
Outcome:	The findings highlight the need for standardized evaluation protocols and in-depth explainability studies.

Copied to clipboard

Runjia Zeng, Guangyan Sun, Qifan Wang, Tong Geng, Sohail Dianat, Xiaotian Han, Raghuveer Rao, Xueling Zhang, Cheng Han, Lifu Huang, Dongfang Liu

Can We Edit Multimodal Large Language Models? (2023.emnlp-main)

Challenge:	Empirical evaluations show that Mixture of Expert Prompt Tuning outperforms state-of-the-art parameter efficient baselines on SuperGLUE.
Approach:	They propose a pretrain-then-fine-tune paradigm for manifold mapping using multiple prompt experts.
Outcome:	Empirical results show that the proposed approach outperforms state-of-the-art methods on SuperGLUE while reducing activated prompts by 79.25%.

Copied to clipboard

Siyuan Cheng, Bozhong Tian, Qingbin Liu, Xi Chen, Yongheng Wang, Huajun Chen, Ningyu Zhang

XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser (2025.coling-main)

Challenge:	Existing methods to edit multimodal models have been used to incrementally infuse a language model with a new set of facts.
Approach:	They construct a benchmark for editing multimodal Large Language Models and establish metrics for evaluation.
Outcome:	The proposed benchmarks show that editing multimodal models is not as difficult as editing single-modal models.

Copied to clipboard

Xianfu Cheng, Hang Zhang, Jian Yang, Xiang Li, Weixiao Zhou, Fei Liu, Kui Wu, Xiangyuan Guan, Tao Sun, Xianjie Wu, Tongliang Li, Zhoujun Li

Multilinguality

Challenge:	Document AI parsing semi-structured image form is a key information extraction task.
Approach:	They propose a multimodal and multilingual semi-structured FORM PARSER which integrates SER and relation extraction into a unified framework.
Outcome:	The proposed framework achieves up to 1.79% improvement on RE tasks in multilingual and zero-shot settings.

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining (2025.coling-main)

Copied to clipboard

Zongru Wu, Pengzhou Cheng, Lingyong Fang, Zhuosheng Zhang, Gongshen Liu

Divergent Thinking: Escape the Homogeneity Trap in Generative Commonsense Reasoning (2026.findings-acl)

Challenge:	Existing backdoor defense methods are ineffective for generative large language models . generative LLMs output sequences of high-dimensional token logits instead of low-dimensional classification logits .
Approach:	They propose a method that leverages sample-wise gradients to identify backdoor samples without retraining LLMs.
Outcome:	The proposed method outperforms baselines significantly in identifying backdoor samples without retraining LLMs.

Copied to clipboard

Yiheng Tao, Kaiwen Cheng, Zhiwei Nie, Chang Liu, Jie Chen

Exploring the Impact of Model Scaling on Parameter-Efficient Tuning (2023.emnlp-main)

Challenge:	Generative commonsense reasoning requires models to synthesize coherent narratives that satisfy lexical constraints and commonsensical logic.
Approach:	They propose a framework that allows for deep semantic diversity rather than surface-level lexical variation.
Outcome:	The proposed framework achieves over 10% improvement in overall accuracy on NoRa and SPICE score on CommonGen-Lite.

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

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning (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

Fangzhi Xu, Hang Yan, Chang Ma, Haiteng Zhao, Qiushi Sun, Kanzhi Cheng, Junxian He, Jun Liu, Zhiyong Wu

T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)

Challenge:	Existing methods for enhancing LLM reasoning rely on supervisory signals . current methods rely heavily on outcome supervision and auxiliary reward models .
Approach:	They propose a gen-eralizable and purely unsupervised self-training framework to enhance LLM reasoning without supervision.
Outcome:	The proposed framework improves LLM reasoning without supervision without external supervision.

Copied to clipboard

Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang, Sashuai Zhou, Luping Liu, Xize Cheng, Shengpeng Ji, Zhenhui Ye, Tao Jin, Zhou Zhao

M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning (2024.emnlp-main)

Challenge:	Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio.
Approach:	They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities .
Outcome:	The proposed model improves in simple and complex scenarios with AI feedback learning.

Copied to clipboard

Taowen Wang, Yiyang Liu, James Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu

SLANG: New Concept Comprehension of Large Language Models (2024.emnlp-main)

Challenge:	Multimodal Large Language Models (MLLMs) exhibit remarkable performance across a wide range of domains.
Approach:	They propose a multimodal prompt tuning approach for efficient instruction tuning of MLLMs.
Outcome:	The proposed approach shows superior performance on multimodal evaluation datasets compared to state-of-the-art methods.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Xueqi Cheng

MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization (2026.findings-acl)

Challenge:	Dynamic nature of language limits the adaptability of Large Language Models (LLMs) Traditionally, LLMs are trained on static data, which limits their adaptability .
Approach:	They propose a benchmark to integrate novel data and assess LLMs’ ability to comprehend emerging concepts, alongside a causal inference-based approach to enhance LLM comprehension of new phrases and their colloquial context.
Outcome:	The proposed model outperforms baseline models in terms of precision and relevance in the comprehension of Internet slang and memes.

Copied to clipboard

Haidong Xin, Xinze Li, Zhenghao Liu, Yukun Yan, Shuo Wang, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun

Feature Structure Matching for Multi-source Sentiment Analysis with Efficient Adaptive Tuning (2024.lrec-main)

Challenge:	Existing memory systems can support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows.
Approach:	They propose a framework that augments memory systems with a self-evolving meta-memory . meta-meso is iteratively distilling transferable knowledge utilization experiences . results show MetaMem outperforms strong baselines by over 3.6% .
Outcome:	The proposed framework outperforms baselines by over 3.6% in the long-horizon human-LLM interaction.

Copied to clipboard

Rui Li, Cheng Liu, Yu Tong, Jiang Dazhi

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)

Challenge:	Existing domain matching methods tend to pull all feature instances close, but they are expensive and expensive to update.
Approach:	They propose to extract multi-layer features from a large pre-trained model and propose a dynamic parameter fusion module to exploit them for efficient and adaptive tuning.
Outcome:	The proposed framework is more robust and generalizable in the multi-source scenario.

Copied to clipboard

Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou

StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs (2025.findings-acl)

Challenge:	Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling.
Approach:	They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation.
Outcome:	The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes.

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Yuchen Niu, Hao Wang, Sicheng Zhou, Wenbing Huang, Yang Liu

Prompt Tuning with Contradictory Intentions for Sarcasm Recognition (2023.eacl-main)

Challenge:	Existing tool environments face challenges in balancing stability, scale, and realism, especially for benchmarking purposes.
Approach:	They propose a framework that trains specialized LLMs to accurately simulate real API responses by supervised fine-tuning and chain-of-thought reasoning.
Outcome:	The proposed framework achieves superior accuracy and stability compared to state-of-the-art methods on the newly constructed MirrorAPI-Bench and its integration into StableToolBench.

Copied to clipboard

Yiyi Liu, Ruqing Zhang, Yixing Fan, Jiafeng Guo, Xueqi Cheng

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training (2024.acl-long)

Challenge:	Recent advances have shown that Pre-trained Language Models (PLMs) can achieve promising performance in many downstream Natural Language Processing (NLP) tasks.
Approach:	They propose to incorporate prior knowledge about contradictory intentions into prompt tuning for sarcasm recognition by mimicking the actual intention by verbalizer engineering.
Outcome:	The proposed model mimics the actual intention by prompt construction and indicates whether the actual intent contradicts the literal content by verbalizer engineering.

Copied to clipboard

Jiale Cheng, Xiao Liu, Kehan Zheng, Pei Ke, Hongning Wang, Yuxiao Dong, Jie Tang, Minlie Huang

Knowledge-Rich Self-Supervision for Biomedical Entity Linking (2022.findings-emnlp)

Challenge:	Large language models are often not well aligned with human intents, which requires additional training.
Approach:	They propose to use Black-Box Prompt Optimization (BPO) to perform alignments on large language models that are not well aligned with human intents.
Outcome:	The proposed model outperforms existing models and is model-agnostic.

Copied to clipboard

Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon

From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2025.emnlp-main)

Challenge:	Entity linking is challenging in high-value domains with myriad entities . standard classification approaches suffer from the annotation bottleneck .
Approach:	They propose a self-supervised approach to learn domain knowledge for biomedical entity linking . it generates self-reported mention examples on unlabeled text and trains contextual encoder .
Outcome:	The proposed method outperforms existing methods by 20 points in accuracy on biomedical datasets.

Copied to clipboard

Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, Huan Liu

Challenge:	Recent advances in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm . traditional methods of assessment and evaluation fail in dynamic and open-ended scenarios .
Approach:	They propose a paradigm where LLMs are leveraged to perform scoring, ranking, or selection for machine learning evaluation scenarios.
Outcome:	The proposed model-based judgment and evaluation paradigms are based on large language models and are compared to the current model-driven evaluation paradigm.

Explicit Inductive Inference using Large Language Models (2024.findings-emnlp)

Copied to clipboard

Tianyang Liu, Tianyi Li, Liang Cheng, Mark Steedman

OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation (2025.acl-long)

Challenge:	Large Language Models (LLMs) suffer a signifi- cant performance drop when entailment labels disagree with the attestation label of hypothesis H.
Approach:	They propose a pipeline that exploits an LLM's attestation bias to do explicit inductive inference . they transform a premise into attested alternatives and aggregate the results .
Outcome:	The proposed pipeline improves the performance of large language models on inference tasks and alleviates the attestation bias.

Copied to clipboard

Qinglin Zhang, Luyao Cheng, Chong Deng, Qian Chen, Wen Wang, Siqi Zheng, Jiaqing Liu, Hai Yu, Chao-Hong Tan, Zhihao Du, ShiLiang Zhang

Trustworthy and Explainable Causal Representation Learning in Transformers (2026.findings-acl)

Challenge:	Full-duplex spoken dialogue systems allow simultaneous bidirectional communication . low latency and natural interactions in full-duplice systems remains a challenge .
Approach:	They propose a multi-stage post-training scheme that adapts a text large language model into a speech-text dialogue LLM.
Outcome:	The proposed model can model human conversation behaviors with low latency and natural interactions with low delay.

Copied to clipboard

Yang Liu, Yinghao Zhang, Lin Liu, Jiuyong Li, Debo Cheng, Zaiwen Feng

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues? (2025.emnlp-industry)

Challenge:	Existing approaches to interpretable representation learning rely on masks that weight the significance of input features, but the origin of these masks is uncertain.
Approach:	They propose a causal framework that directly learns identifiable representations from attention weights rather than relying on importance masks.
Outcome:	The proposed framework learns identifiable and explainable representations from attention weights, rather than masks, and guarantees faithfulness on real-world datasets.

Copied to clipboard

Haoxin Wang, Xianhan Peng, Huang Cheng, Yizhe Huang, Ming Gong, Chenghan Yang, Yang Liu, Jiang Lin

Challenge:	ECom-Bench is a benchmark framework for evaluating LLM agent with multimodal capabilities in e-commerce customer support domain.
Approach:	They introduce a benchmark framework for evaluating LLM agent with multimodal capabilities in the e-commerce customer support domain.
Outcome:	The proposed benchmark features dynamic user simulation based on persona information from real e-commerce customer interactions and a realistic task dataset derived from authentic ecommerce dialogues.

KELE: A Multi-Agent Framework for Structured Socratic Teaching with Large Language Models (2025.findings-emnlp)

Copied to clipboard

Xian Peng, Pan Yuan, Dong Li, Junlong Cheng, Qin Fang, Zhi Liu

TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense (2026.findings-acl)

Challenge:	Socratic teaching places high demands on teachers’ expertise and real-time feedback capabilities, making it difficult to scale in large educational settings.
Approach:	They propose a multi-agent framework for structured Socratic teaching with LLMs that integrates a structured SocRule and a consultant-teacher collaborative teaching mechanism.
Outcome:	The proposed framework outperforms existing LLMs in natural language generation and dialogue comprehension in the classroom.

Copied to clipboard

Cheng Liu, Xiaolei Liu, Xingyu Li, Bangzhou Xin, Kangyi Ding

DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space (2024.lrec-main)

Challenge:	Existing jailbreak defense paradigms rely on static detection of prompts, outputs, or internal states . hidden states in critical layers during decoding carry stronger and more stable risk signals .
Approach:	They propose a decoding-time defense framework that aggregates hidden-state trajectories via a sliding window to quantify risk in real time.
Outcome:	The proposed framework achieves an average defense rate of 95% in 12 jailbreak attacks and open-source LLMs.

Copied to clipboard

Jianxiang Xiang, Zhenhua Liu, Haodong Liu, Yin Bai, Jia Cheng, Wenliang Chen

Pruning as a Domain-specific LLM Extractor (2024.findings-naacl)

Challenge:	Existing studies have tried to introduce discrete or Gaussian-based latent variables to address the one-to-many problem, but the diversity is limited.
Approach:	They propose a diffusion model to enhance the diversity of dialogue generation by using continuous latent variables instead of discrete ones.
Outcome:	The proposed model greatly enhances diversity of dialog response while keeping the coherence.

Copied to clipboard

Nan Zhang, Yanchi Liu, Xujiang Zhao, Wei Cheng, Runxue Bao, Rui Zhang, Prasenjit Mitra, Haifeng Chen

Challenge:	Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array of NLP tasks.
Approach:	They propose a method for pruning large language models using general or task-specific weights to extract a compressed, task-agnostic LLM.
Outcome:	The proposed method extracts a compressed, domain-specific, and task- agnostic LLM by identifying LLM weights that are pivotal for general capabilities, like linguistic capability and multi-task solving, and domain- specific knowledge.

AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent (2026.findings-acl)

Copied to clipboard

Sun Hui, Ding Yanfeng, Huidong Ma, Chang Xu, Keyan Jin, Lizheng Zu, Cheng Zhong, Xiaoguang Liu, Gang Wang, Wentong Cai

Cognitive Modeling

Challenge:	Lossless compression has made significant advancements in Genomics Data storage, sharing and management.
Approach:	They propose a novel agent-based GD Compressor with 3 layers with a multi-agent named Leader and Worker.
Outcome:	The proposed method improves on existing methods with low-level modeling and limited adaptability and user-unfriendly interface.

Automated Generation of Accurate & Fluent Medical X-ray Reports (2021.emnlp-main)

Copied to clipboard

Hoang Nguyen, Dong Nie, Taivanbat Badamdorj, Yujie Liu, Yingying Zhu, Jason Truong, Li Cheng

Can Graph Descriptive Order Affect Solving Graph Problems with LLMs? (2025.acl-long)

Challenge:	Existing medical report generation efforts focus on producing human-readable reports, yet the generated text may not be well aligned to the clinical facts.
Approach:	They propose to automate the generation of medical reports from chest X-ray image inputs . medical reports are the primary medium, which physicians communicate findings from scans - authors say .
Outcome:	The proposed method achieves fluency and clinical accuracy on common metrics.

Copied to clipboard

Yuyao Ge, Shenghua Liu, Baolong Bi, Yiwei Wang, Lingrui Mei, Wenjie Feng, Lizhe Chen, Xueqi Cheng

Nested Event Extraction upon Pivot Element Recognition (2024.lrec-main)

Challenge:	Large language models (LLMs) have achieved significant success in reasoning tasks, including mathematical reasoning and logical deduction.
Approach:	They conduct the first comprehensive analysis of how the order of graph descriptions impacts LLM performance.
Outcome:	The results show that graph descriptions significantly improve LLMs’ comprehension of graph structures, and the robustness of LLM models to graph description order varies across different tasks.

Copied to clipboard

Weicheng Ren, Zixuan Li, Xiaolong Jin, Long Bai, Miao Su, Yantao Liu, Saiping Guan, Jiafeng Guo, Xueqi Cheng

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering (2024.emnlp-main)

Challenge:	Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively.
Approach:	They propose a new model that extracts nested events mainly based on recognizing PEs.
Outcome:	The proposed model can extract nested events based on recognizing PEs . it incorporates information from both event types and argument roles to improve performance .

Copied to clipboard

Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training (2025.findings-acl)

Challenge:	Existing retrieval-augmented generation methods rely on multiple calls of large language models (LLMs) Large-language models lack knowledge underrepresented in training data and still face hallucinations.
Approach:	They propose an efficient retriever for multi-hop question answering that generates new queries iteratively without the need for LLM calls.
Outcome:	The proposed method surpasses existing methods on three open-domain multi-hop question-answering datasets.

Copied to clipboard

Jun Rao, Zepeng Lin, Xuebo Liu, Xiaopeng Ke, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

A Generative Framework for Personalized Sticker Retrieval (2025.findings-emnlp)

Challenge:	Large Language Models often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities.
Approach:	They propose to use self-generated dis-preferred weakness data to enhance model performance with a targeted training approach that minimizes interference with existing knowledge base.
Outcome:	The proposed approach ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to existing methods.

Copied to clipboard

Changjiang Zhou, Ruqing Zhang, Jiafeng Guo, Yu-An Liu, Fan Zhang, Ganyuan Luo, Xueqi Cheng

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)

Challenge:	Existing relevance-based generative retrieval methods lack personalization, leading to a mismatch between diverse user expectations and the retrieved results.
Approach:	They propose a representation learning model that learns discriminative user representations to encode user-specific sticker preferences.
Outcome:	The proposed framework outperforms state-of-the-art methods in generating relevant stickers for queries.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer (2025.findings-naacl)

Challenge:	Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically.
Approach:	They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance.
Outcome:	The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs.

Copied to clipboard

Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Zhuosheng Zhang, Gongshen Liu

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents (2026.acl-long)

Challenge:	Existing attacks are classified into end-to-end and pre-training types based on the attack phase . Existing backdoor attacks are based upon perplexity, fine-pruning, and maxEntropy.
Approach:	They propose an entropy-based poisoning filter that mitigates backdoor attacks . they propose an invisible and universal task-agnostic backdoor attack via syntactic transfer .
Outcome:	The proposed attack can transfer backdoors to various downstream tasks while preserving pre-trained language models' pre-training capabilities.

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

Cross-Thought for Sentence Encoder Pre-training (2020.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

Shuohang Wang, Yuwei Fang, Siqi Sun, Zhe Gan, Yu Cheng, Jingjing Liu, Jing Jiang

Safety in Large Reasoning Models: A Survey (2025.findings-emnlp)

Challenge:	Existing models to pretrain sentence encoders with large unlabeled corpus are lacking in linguistic information retrieval.
Approach:	They propose a novel approach to pre-training sequence encoder using transformers . they propose to train a Transformer-based sequence encoded over a large set of short sequences based on a set of masked words .
Outcome:	The proposed approach outperforms state-of-the-art encoders on hotpotQA by improving intermediate information retrieval performance.

Copied to clipboard

Cheng Wang, Yue Liu, Baolong Bi, Duzhen Zhang, Zhong-Zhi Li, Yingwei Ma, Yufei He, Shengju Yu, Xinfeng Li, Junfeng Fang, Jiaheng Zhang, Bryan Hooi

RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning (2024.emnlp-main)

Challenge:	Large Reasoning Models (LRMs) have a high level of advanced reasoning capabilities, but they are vulnerable and vulnerable.
Approach:	This paper presents the first comprehensive survey of Large Reasoning Models . it explores the new safety risks, attacks, and defense strategies specific to LRMs based on reasoning .
Outcome:	The proposed study examines the safety and security risks of large reasoning models.

Copied to clipboard

Haoyu Wang, Tianci Liu, Ruirui Li, Monica Cheng, Tuo Zhao, Jing Gao

Chain-of-Skills: A Configurable Model for Open-Domain Question Answering (2023.acl-long)

Challenge:	Pre-trained language models have strong generalizability, but fine-tuning involves updating all parameters, rendering full fine-uning resource-intensive.
Approach:	They propose a parameter-efficient fine-tuning method that updates all pre-trained parameters during inference.
Outcome:	The proposed method outperforms baseline methods on five benchmarks across 20 datasets.

Copied to clipboard

Kaixin Ma, Hao Cheng, Yu Zhang, Xiaodong Liu, Eric Nyberg, Jianfeng Gao

Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models (2026.findings-acl)

Challenge:	Using customized retrieval models, model transferability and scalability are limited.
Approach:	They propose a modular retrieval model where individual modules correspond to key skills that can be reused across datasets.
Outcome:	The proposed model outperforms self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA.

Copied to clipboard

Kainan Liu, Yong Zhang, Ning Cheng, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao

The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning (2025.findings-acl)

Challenge:	Existing methods for fine-tuning pre-trained models are limited due to suboptimal activation subspaces.
Approach:	They propose a method that leverages tail eigenvectors of model output activations to construct low-rank adapters.
Outcome:	The proposed method outperforms existing methods across 16 benchmarks and surpasses full fine-tuning in certain scenarios.

Copied to clipboard

Bingxiang He, Ning Ding, Cheng Qian, Jia Deng, Ganqu Cui, Lifan Yuan, Haiwen Hong, Huan-ang Gao, Longtao Huang, Hui Xue, Huimin Chen, Zhiyuan Liu, Maosong Sun

QuoteR: A Benchmark of Quote Recommendation for Writing (2022.acl-long)

Challenge:	Existing work on instruction tuning has focused on task level, without considering that tasks are artificially defined and, to LLMs, merely consist of tokens and representations.
Approach:	They propose a training data arrangement framework that allows for continual learning and loss reduction.
Outcome:	The proposed framework promotes continual learning and loss reduction on unseen tasks.

Copied to clipboard

Fanchao Qi, Yanhui Yang, Jing Yi, Zhili Cheng, Zhiyuan Liu, Maosong Sun

Challenge:	Existing methods to recommend quotes are evaluated on unpublished datasets .
Approach:	They propose to build a dataset that is open and contains three parts including English, standard Chinese and classical Chinese.
Outcome:	The proposed model outperforms existing methods on all three parts of QuoteR.

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents (2025.findings-emnlp)

Copied to clipboard

Pengzhou Cheng, Haowen Hu, Zheng Wu, Zongru Wu, Tianjie Ju, Daizong Ding, Zhuosheng Zhang, Gongshen Liu

AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2025.acl-long)

Challenge:	MLLM-powered GUI agents expose multiple interaction-level triggers, causing backdoor attacks . backdoor injection maximizes feature difference across sample classes, improving flexibility .
Approach:	They propose a framework for red-teaming backdoor attacks using MLLMs . they construct composite triggers by combining goal and interaction levels .
Outcome:	The proposed framework is effective and stealthy for red-teaming backdoor attacks.

Copied to clipboard

Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang, Jie Tang, Yuxiao Dong

“Not Aligned” is Not “Malicious”: Being Careful about Hallucinations of Large Language Models’ Jailbreak (2025.coling-main)

Challenge:	Existing studies on Android agents lack systematic research on open-source and closed-source models.
Approach:	They propose a framework for Android agents that includes an operation environment and a reproducible benchmark.
Outcome:	The proposed framework lifts the success rate of open-source LLMs and LMMs from 4.59% to 21.50% for LLM and 1.93% to 13.28% for LMM.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Jiayi Mao, Xueqi Cheng

MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing (2026.acl-demo)

Challenge:	“Jailbreak” is a major safety concern of Large Language Models (LLMs).
Approach:	They propose a benchmarking framework to evaluate "jailbreak" outputs . they propose specialized validation framework to ensure outputs are useful malicious instructions .
Outcome:	The proposed framework enhances existing benchmarks to ensure outputs are useful . it also aims to evaluate the true potential of jailbroken outputs to cause harm to human society.

Copied to clipboard

Yang Liu, Jinxuan Cai, Yishen Li, Qi Meng, Zedi Liu, Xin Li, Chen Qian, Chuan Shi, Cheng Yang

Leveraging Language-based Representations for Better Solving Symbol-related Problems with Large Language Models (2025.coling-main)

Challenge:	Large language model-based multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration.
Approach:	They propose a graph-centric framework for orchestrating large language model-based multi-agent systems . they compile a user's natural-language intent into an editable workflow specification and then into an executable graph .
Outcome:	The proposed framework compiles natural-language intent into an executable graph and then compile and executes it at runtime.

Copied to clipboard

Yile Wang, Sijie Cheng, Zixin Sun, Peng Li, Yang Liu

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction (2025.emnlp-main)

Challenge:	Symbols are used in abstract reasoning, chemical property prediction, and tabular question-answering.
Approach:	They propose a method that converts symbols to language-based representations to improve their accuracy.
Outcome:	The proposed method improves the accuracy of symbols in language-based models.

Copied to clipboard

Wenxuan Liu, Zixuan Li, Long Bai, Yuxin Zuo, Daozhu Xu, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs (2025.emnlp-main)

Challenge:	Event Extraction (EE) is a long-standing target, but lacks an efficient and effective annotation framework to construct the corresponding datasets.
Approach:	They propose an LLM-based collaborative annotation framework that refines annotations of triggers from distant supervision and carries out argument annotation.
Outcome:	The proposed framework outperforms state-of-the-art methods on the largest EE dataset to date . it achieves the F1 scores of 90% and 85.3% on the human-annotated test set .

Copied to clipboard

Hexiang Tan, Fei Sun, Sha Liu, Du Su, Qi Cao, Xin Chen, Jingang Wang, Xunliang Cai, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng

Challenge:	Existing detection methods fail to account for self-consistent error . study identifies self-consistency errors and evaluates them .
Approach:	They propose a method that fuses hidden state evidence from an external verifier LLM to detect self-consistent errors.
Outcome:	The proposed method significantly enhances performance on self-consistent errors across three LLM families.

ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement (2026.acl-long)

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Shuzheng Si, Cheng Gao, Zhitong Wang, Yingli Shen, Wenhao Li, Zhu Liu, Yufeng Han, Jiayi Wu, Cunliang Kong, Maosong Sun

Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage (2026.acl-long)

Challenge:	Existing supervised neural methods for coreference resolution are underexplored . current methods rely on small language models, but their potential is underexploited .
Approach:	They propose a framework that integrates an enhanced supervised model with LLM-based reasoning.
Outcome:	The proposed method surpasses existing state-of-the-art methods in coreference resolution.

Copied to clipboard

Xueting Li, Qi Liu, Chenghao Xu, Xu Yang, Guangtao Lyu, Jiahua Li, Cheng Deng

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding (2026.acl-long)

Challenge:	Existing visual token pruning methods leverage simple metrics derived from human experience, such as attention or similarity, to rank and select tokens within a highly entangled feature space.
Approach:	They propose a novel visual token pruning method that uses a concept-driven paradigm to quantify the Marginal Semantic Gain of each token's contribution to uncovered concepts.
Outcome:	The proposed method outperforms state-of-the-art methods in a concept-driven model while maintaining semantic completeness.

Copied to clipboard

Shuang Cheng, Yuhua Jiang, Zineng Zhou, Dawei Liu, Tao Wang, Linfeng Zhang, Biqing Qi, Bowen Zhou

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)

Challenge:	Existing block-wise discrete diffusion models lack robust autoregressive (AR) decoders.
Approach:	They propose a block-wise discrete diffusion framework for large-scale vision-language understanding with a progressive beta noise curriculum.
Outcome:	The proposed framework improves training efficiency, convergence stability, and task performance over conventional block diffusion.

Copied to clipboard

Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu

Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking Models (2026.acl-long)

Challenge:	Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability.
Approach:	They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks.
Outcome:	The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity.

Copied to clipboard

Yu-An Liu, Ruqing Zhang, Hongru Song, Jiafeng Guo, Yixing Fan, Xueqi Cheng

Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning (2025.coling-main)

Challenge:	Existing defenses for neural ranking models are data-centric and require retraining and adversarial data generation.
Approach:	They propose a model-centric defense that addresses vulnerability at its architectural source without costly retraining or adversarial data generation.
Outcome:	The proposed approach outperforms state-of-the-art models on MS MARCO and TREC 19 while maintaining strong performance on clean data.

Copied to clipboard

Xiaoye Qu, Jiashuo Sun, Wei Wei, Daizong Liu, Jianfeng Dong, Yu Cheng

Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation (2026.acl-long)

Challenge:	Large Vision-Language Models (LVLMs) have impressive capabilities in multi-modal context comprehension, but they still suffer from hallucination problems due to inconsistent outputs with the image content.
Approach:	They propose a training-free framework MVP to reduce hallucinations in Large Vision-Language Models . they propose multi-view information-seeking strategy to perceive the comprehensive information in the image .
Outcome:	The proposed framework reduces hallucinations in large vision-language models by combining multi-view multi-path reasoning with multi-vision multi-path reasoning.

Copied to clipboard

Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, Yunhong Wang

UnitedQA: A Hybrid Approach for Open Domain Question Answering (2021.acl-long)

Challenge:	Existing frameworks that focus on static tools and static assets are ineffective for self-evolving agents.
Approach:	They propose a paradigm of co-evolutionary Capability Expansion and Experience Distillation that leverages accumulated experience to guide dynamic creation of assets.
Outcome:	The proposed framework improves performance in single-task and cross-task settings by 18.53% over standard LLMs, 11.80% over agents evolving solely through experience, and 6.46% over those evolving solelly through asset creation.

Copied to clipboard

Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao

TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route (2025.emnlp-main)

Challenge:	Recent work on open-domain question answering focuses on either extractive or generative readers exclusively.
Approach:	They propose a hybrid approach to extractive and generative readers that leverages both models.
Outcome:	The proposed approach outperforms state-of-the-art models on NaturalQuestions and TriviaQA respectively.

Copied to clipboard

Hongyi Luo, Qing Cheng, Daniel Matos, Hari Krishna Gadi, Yanfeng Zhang, Lu Liu, Yongliang Wang, Niclas Zeller, Daniel Cremers, Liqiu Meng

Debiasing Word Embeddings with Nonlinear Geometry (2022.coling-1)

Challenge:	Existing studies on large language models have limited evaluation of their geospatial cognition . a unified framework for evaluating geospcial cognition in LLMs remains absent .
Approach:	They propose a benchmark to evaluate the geospatial route cognition of Large Language Models . they propose 'pathbuilder' tool for converting natural language instructions into navigation routes .
Outcome:	The proposed framework and metrics evaluate 9 state-of-the-art LLMs on route reversal task.

Copied to clipboard

Lu Cheng, Nayoung Kim, Huan Liu

OpenResearcher: Unleashing AI for Accelerated Scientific Research (2024.emnlp-demo)

Challenge:	Existing methods for debiasing word embeddings are limited to individual social categories . however, real-world corpora typically present multiple social categories that may correlate or intersect with each other.
Approach:	They propose a method to debias word embeddings using nonlinear geometry of individual biases.
Outcome:	Empirical results show that the proposed method mitigates biases associated with individual social categories and treats each category in isolation.

Copied to clipboard

Yuxiang Zheng, Shichao Sun, Lin Qiu, Dongyu Ru, Cheng Jiayang, Xuefeng Li, Jifan Lin, Binjie Wang, Yun Luo, Renjie Pan, Yang Xu, Qingkai Min, Zizhao Zhang, Yiwen Wang, Wenjie Li, Pengfei Liu

InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration (2024.findings-emnlp)

Challenge:	Global scientific publications are growing annually by about 4%-5% (Pinedo et al., 2024).
Approach:	They introduce an AI-assisted platform that answers diverse questions from researchers using Retrieval-Augmented Generation (RAG) they develop various tools to understand queries, search from the scientific literature, filter retrieved information, provide accurate and comprehensive answers, and self-refine answers.
Outcome:	OpenResearcher is built on Retrieval-Augmented Generation (RAG) to integrate Large Language Models (LLMs) with up-to-date, domain-specific knowledge.

Copied to clipboard

Fali Wang, Runxue Bao, Suhang Wang, Wenchao Yu, Yanchi Liu, Wei Cheng, Haifeng Chen

Mitigating Spurious Correlations via Counterfactual Contrastive Learning (2025.findings-emnlp)

Challenge:	Large Language Models have exceptional capabilities in open generation, yet they encounter difficulties with tasks that require intensive knowledge.
Approach:	They propose a framework that integrates unknown knowledge into LLMs without overlap . they propose integrating domain-specific knowledge graphs into Llms to reduce knowledge forgetting .
Outcome:	The proposed framework outperforms state-of-the-art baselines in integrating new knowledge into LLMs.

Copied to clipboard

Fengxiang Cheng, Chuan Zhou, Xiang Li, Alina Leidinger, Haoxuan Li, Mingming Gong, Fenrong Liu, Robert Van Rooij

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space (2024.acl-long)

Challenge:	Existing methods to distinguish causally related words from spurious correlations are limited by the number of causally correlated words in a sentence.
Approach:	They propose to use probabilistic probability of necessity and probability of sufficiency to identify causal relationships rather than spurious correlations between words and class labels.
Outcome:	The proposed method is based on a contrastive learning approach name CPNS and is validated on public datasets.

Copied to clipboard

Zongru Wu, Zhuosheng Zhang, Pengzhou Cheng, Gongshen Liu

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models (2024.acl-demos)

Challenge:	Prior work attempts to mitigate backdoor learning during training LMs on poisoned datasets . backdoor attack poisons a small portion of training data by implanting specific text patterns .
Approach:	They propose a multi-scale low-rank adaptive model that prioritizes learning of clean mapping . they propose radial scalings to reduce the success rate of diverse backdoor attacks .
Outcome:	The proposed model outperforms baselines significantly in the frequency space . it reduces the success rate of diverse backdoor attacks to below 15% across datasets .

Copied to clipboard

Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, Huajun Chen

Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights (2025.findings-naacl)

Challenge:	Large Language Models (LLMs) suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data.
Approach:	They propose an easy-to-use knowledge editing framework for Large Language Models that allows users to easily edit updated knowledge and adjust undesired behavior while minimizing the impact on unrelated inputs.
Outcome:	The proposed framework surpasses traditional fine-tuning in terms of reliability and generalization.

Copied to clipboard

Yang Liu, Lan Lan, Jiahuan Cao, Hiuyi Cheng, Kai Ding, Lianwen Jin

ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentation (2024.findings-emnlp)

Challenge:	Ancient Chinese poetry presents unique challenges for Large Language Models due to data scarcity and limited ability of general LLMs when dealing with ACP.
Approach:	They propose a specialized Retrieval-Augmented Generation framework to improve LLMs' performance . they use 1.1 million ancient poems and 990K related texts to address hallucination issues .
Outcome:	The proposed framework improves performance of LLMs in ancient Chinese poetry domain from 49.2% to 89.0%.

Copied to clipboard

Wenjun Hou, Yi Cheng, Kaishuai Xu, Yan Hu, Wenjie Li, Jiang Liu

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse (2024.findings-acl)

Challenge:	Existing approaches to radiology report generation lack inter-report consistency, exhibiting biases towards common patterns and susceptibility to lesion variants.
Approach:	They propose a method which improves the inter-report consistency of radiology report generation by extracting lesions from input images and examining their characteristics.
Outcome:	The proposed system captures similarities in semantically equivalent lesions and can be used to generate reports for two semantically identical cases.

Copied to clipboard

Wanli Yang, Fei Sun, Xinyu Ma, Xun Liu, Dawei Yin, Xueqi Cheng

Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog (P19-1)

Challenge:	Even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks.
Approach:	They propose to use perplexity as a surrogate metric to determine whether an edited model's performance is affected by a single edit.
Outcome:	The proposed method shows that even a single edit can cause model collapse, manifesting as significant performance degradation in various benchmark tasks.

Copied to clipboard

Zhe Gan, Yu Cheng, Ahmed Kholy, Linjie Li, Jingjing Liu, Jianfeng Gao

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)

Challenge:	Existing models for visual dialog infer the answer through multiple reasoning steps.
Approach:	They propose a model for visual dialog that uses multi-step reasoning to answer questions about an image.
Outcome:	The proposed model achieves a new state-of-the-art of 64.47% on the VisDial v1.0 dataset .

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu

Investigating Hallucinations in Simultaneous Machine Translation: Knowledge Distillation Solution and Components Analysis (2025.naacl-long)

Challenge:	Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning.
Approach:	They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs.
Outcome:	The proposed benchmarks demonstrate the stability of the proposed system and its caching system.

Copied to clipboard

Donglei Yu, Xiaomian Kang, Yuchen Liu, Feifei Zhai, Nanchang Cheng, Yu Zhou, Chengqing Zong

Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge (2022.findings-emnlp)

Challenge:	Existing methods to mitigate hallucinations in siMT generate fluency but unfaithful translation.
Approach:	They propose a method that utilizes the OMT model to mitigate hallucinations in SiMT.
Outcome:	The proposed method reduces hallucinations and improves the SiMT performance.

Copied to clipboard

Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, Jianfeng Gao

Open-ended Commonsense Reasoning with Unrestricted Answer Candidates (2023.findings-emnlp)

Challenge:	Existing open-domain question answering methods rely on the retriever to gather all evidence in isolation, but our approach uses an intermediary module to perform a chain of reasoning over the retrieved set.
Approach:	They propose a new open-domain question answering framework that integrates an intermediary module into the current retriever-reader pipeline and integrates it into the model.
Outcome:	The proposed framework outperforms the state-of-the-art on two OTT-QA datasets with an exact match score of 47.3 (45% relative gain).

Copied to clipboard

Chen Ling, Xuchao Zhang, Xujiang Zhao, Yanchi Liu, Wei Cheng, Mika Oishi, Takao Osaki, Katsushi Matsuda, Haifeng Chen, Liang Zhao

Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs (2025.findings-acl)

Challenge:	Current approaches to commonsense reasoning are limited due to limited answer scope.
Approach:	They propose to solve a commonsense question without a pre-defined answer scope . they leverage pre-trained language models to iteratively retrieve reasoning paths on the external knowledge base .
Outcome:	The proposed method achieves better performance on two commonsense benchmark datasets.

Copied to clipboard

Runchu Tian, Yanghao Li, Yuepeng Fu, Siyang Deng, Qinyu Luo, Cheng Qian, Shuo Wang, Xin Cong, Zhong Zhang, Yesai Wu, Yankai Lin, Huadong Wang, Xiaojiang Liu

Challenge:	Positional biases in large language models hinder their ability to process long inputs.
Approach:	They propose a benchmark to assess positional bias in large language models involving multiple pieces of relevant information.
Outcome:	The proposed benchmark assesses the performance of long-context language models by examining their models with different input lengths and tasks.

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Jun Rao, Yunjie Liao, Xuebo Liu, Zepeng Lin, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains (2025.acl-long)

Challenge:	Existing methods for preference optimization of large language models use pairs of positive and negative samples, but the quality of positive samples may become similar during training, complicating preference learning.
Approach:	SeaPO introduces error types commonly occurring in large language models to improve preference learning.
Outcome:	SeaPO introduces error types into model Preference Optimization to improve model performance . negative samples are more erroneous than positive samples, and preference-based training mitigates errors .

Copied to clipboard

Juntian Zhang, Chuanqi Cheng, Yuhan Liu, Wei Liu, Jian Luan, Rui Yan

VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation (2025.emnlp-main)

Challenge:	Existing vision-language models struggle to disentangle information scattered across complex visual inputs, leading to performance degradation.
Approach:	They propose a focus-centric visual chain paradigm that enhances VLMs’ perception, comprehension, and reasoning abilities in multi-image scenarios.
Outcome:	The proposed approach achieves average performance gains of 3.16% and 2.24% across two distinct model architectures, without compromising the general vision-language capabilities.

Copied to clipboard

Yuhao Wang, Heyang Liu, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang

Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction (2020.findings-emnlp)

Challenge:	Experimental results show VocalNet outperforms existing open-source speech LLMs despite limited training data.
Approach:	They propose a scalable and model-agnostic training framework and a novel multi-token prediction paradigm for speech generation.
Outcome:	The proposed model outperforms open-source speech LLMs while outperforming existing open-sourced models.

Copied to clipboard

Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan, Heng Ji, Daojian Zeng, Fei Cheng, Daisuke Kawahara, Sadao Kurohashi

MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking (2024.lrec-main)

Challenge:	Existing methods to extract relation triplets from plain text introduce exposure bias . prior work has focused on pipeline methods that ignore intrinsic interactions between subtasks and propagate classification errors through the tasks.
Approach:	They propose a model that reduces the decoding length to three within a triplet and removes the order among triplets.
Outcome:	The proposed model overfits to both datasets while showing better generalization.

Copied to clipboard

Tianwen Tang, Tong Zhu, Haodong Liu, Yin Bai, Jia Cheng, Wenliang Chen

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents (2026.acl-long)

Challenge:	Existing zero-shot dialogue state tracking models suffer from domain transferring and partial prediction problems.
Approach:	They propose to establish connections between similar slots in different domains to improve model transfer performance in unseen domains.
Outcome:	Empirical results show that the proposed model achieves the goal accuracy of 57.13% on MultiWOZ2.1 and 55.4.

Copied to clipboard

Jiayu Liu, Cheng Qian, Zhaochen Su, Qing Zong, Shijue Huang, Bingxiang He, Yi R. Fung

LLM-FP4: 4-Bit Floating-Point Quantized Transformers (2023.emnlp-main)

Challenge:	Existing evaluations of Large Language Models (LLMs) focus on task completion, but neglect a crucial capability: the ability to devise and adjust cost-optimal plans in response to changing environments.
Approach:	They propose a scalable, cost-centric benchmark to evaluate agents’ economic reasoning and replanning abilities.
Outcome:	Evaluating leading open-sourced and proprietary models on CostBench reveals a substantial gap in cost-aware planning .

Copied to clipboard

Shih-yang Liu, Zechun Liu, Xijie Huang, Pingcheng Dong, Kwang-Ting Cheng

GPT-RE: In-context Learning for Relation Extraction using Large Language Models (2023.emnlp-main)

Challenge:	Existing quantization solutions are integer-based and struggle with bit widths below 8 bits.
Approach:	They propose a method for quantizing weights and activations in large language models down to 4-bit floating-point values in a post-training manner.
Outcome:	The proposed method outperforms existing methods on common sense zero-shot reasoning tasks by 12.7 points.

Copied to clipboard

Zhen Wan, Fei Cheng, Zhuoyuan Mao, Qianying Liu, Haiyue Song, Jiwei Li, Sadao Kurohashi

M3TQA: Massively Multilingual Multitask Table Question Answering (2026.findings-acl)

Challenge:	Existing approaches to in-context learning (ICL) are lacking in relation extraction (RE) . emergence of large language models (LLMs) such as GPT-3 represents a significant advancement in natural language processing.
Approach:	They propose to incorporate task-aware representations into demonstration retrieval and enrich the demonstrations with gold label-induced reasoning logic.
Outcome:	The proposed model achieves SOTA and competitive performances on the Semeval and SciERC datasets.

Copied to clipboard

Daixin Shu, Jian Yang, Zhenhe Wu, Xianjie Wu, Xianfu Cheng, Guan Xiangyuan, Yanghai Wang, Pengfei Wu, Tingyang Yang, Hualei Zhu, Wei Zhang, Ge Zhang, Jiaheng Liu, Zhoujun Li

Experiential Co-Learning of Software-Developing Agents (2024.acl-long)

Challenge:	Existing multilingual table benchmarks suffer from geolinguistic imbalance - overrepresenting certain languages and lacking sufficient scale for rigorous cross-lingual analysis.
Approach:	They propose a framework for massively multilingual table question answering that includes tables expanded to 97 languages from Chinese and English sources.
Outcome:	Experiments on state-of-the-art LLMs show that synthetically generated training data significantly boosts performance, especially for low-resource languages.

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

Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models (2025.acl-long)

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

Fangzhi Xu, Qiushi Sun, Kanzhi Cheng, Jun Liu, Yu Qiao, Zhiyong Wu

CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards (2025.emnlp-main)

Challenge:	Existing methods to fine-tune Large Language Models without human annotations are lacking in the field of natural language training.
Approach:	They propose an environment-guided neural-symbolic self-training framework to overcome two main challenges: the scarcity of symbolic data and the limited proficiency of LLMs in processing symbolic language.
Outcome:	The proposed framework overcomes two main challenges: the scarcity of symbolic data, and the limited proficiency of LLMs in processing symbolic language.

Copied to clipboard

Cheng Liu, Yifei Lu, Fanghua Ye, Jian Li, Xingyu Chen, Feiliang Ren, Zhaopeng Tu, Xiaolong Li

Challenge:	Existing approaches to role-playing language models rely on prompt engineering or supervised fine-tuning to emulate character behaviors but neglect the underlying cognitive mechanisms driving these behaviors.
Approach:	They propose a novel RPLA adopting a cognize-then-respond reasoning paradigm that leverages dual cognition for more contextually grounded and psychologically coherent responses.
Outcome:	The proposed RPLA outperforms baselines and generalizes effectively across diverse role-playing tasks.

Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation (2026.findings-acl)

Copied to clipboard

Yubo Jiang, Xin Yang, Abudukelimu Wuerkaixi, Zheming Yuan, Xuxin Cheng, Cao Liu, Ke Zeng, Fengying Xie, Zhiguo Jiang, Haopeng Zhang

Robustness Testing of Language Understanding in Task-Oriented Dialog (2021.acl-long)

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

Jiexi Liu, Ryuichi Takanobu, Jiaxin Wen, Dazhen Wan, Hongguang Li, Weiran Nie, Cheng Li, Wei Peng, Minlie Huang

APo-VAE: Text Generation in Hyperbolic Space (2021.naacl-main)

Challenge:	a lack of systematic studies on the robustness of language understanding models in task-oriented dialog systems is limiting . authors propose a model-agnostic toolkit LAUG to approximate natural language perturbations .
Approach:	They propose a model-agnostic toolkit LAUG to approximate natural language perturbations for testing the robustness of language understanding models in task-oriented dialog systems.
Outcome:	The proposed toolkit reveals critical robustness issues in state-of-the-art models.

Copied to clipboard

Shuyang Dai, Zhe Gan, Yu Cheng, Chenyang Tao, Lawrence Carin, Jingjing Liu

Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs (2024.emnlp-main)

Challenge:	Existing models that learn embeddings only in Euclidean vector space do not account for such structural property of language.
Approach:	They propose a Poincare Variational Autoencoder to capture latent hierarchies in hyperbolic space . they propose enabling adversarial learning procedures to empower robust model training .
Outcome:	The proposed model outperforms existing models in a hyperbolic latent space . it captures latent language hierarchies in hyperbolical space and is robust to training .

Copied to clipboard

Cheng Gao, Chaojun Xiao, Zhenghao Liu, Huimin Chen, Zhiyuan Liu, Maosong Sun

TLUE: A Tibetan Language Understanding Evaluation Benchmark (2025.emnlp-main)

Challenge:	Existing studies focus on case-to-case retrieval using lengthy queries, which does not match real-world scenarios.
Approach:	They propose a method to construct query-candidate pairs and build the largest LCR dataset to date, LEAD.
Outcome:	Experimental results show that the method can provide ample training signals for LCR models.

Copied to clipboard

Fan Gao, Cheng Huang, Yutong Liu, Nyima Tashi, Xiangxiang Wang, Thupten Tsering, Ban Ma-bao, Renzeng Duojie, Gadeng Luosang, Rinchen Dongrub, Dorje Tashi, Xiao Feng Cd, Yongbin Yu, Hao Wang

DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router (2026.findings-eacl)

Challenge:	Low-resource languages, like Tibetan, remain underrepresented in large language models' evaluations.
Approach:	They propose a Tibetan Language Understanding Evaluation Benchmark to assess LLMs' proficiency in Tibetan . they use a multi-task understanding benchmark and a safety benchmark to evaluate models .
Outcome:	The proposed benchmark shows that most large language models perform below the random baseline, especially in Tibetan language processing.

Copied to clipboard

Minghao Guo, Qingcheng Zeng, Xujiang Zhao, Yanchi Liu, Wenchao Yu, Mengnan Du, Haifeng Chen, Wei Cheng

EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs (2024.lrec-main)

Challenge:	Existing RAG methods lack fine-grained control over query and source sides, resulting in noisy retrieval and shallow reasoning.
Approach:	They propose an agentic RAG framework that integrates information sieving via LLM-as-a-knowledge-router.
Outcome:	Experiments on multi-hop QA tasks across heterogeneous sources demonstrate improved reasoning depth, retrieval precision, and interpretability over conventional approaches.

Copied to clipboard

Cheng Jiayang, Lin Qiu, Chunkit Chan, Xin Liu, Yangqiu Song, Zheng Zhang

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026.acl-long)

Challenge:	Existing frameworks for leveraging background knowledge of narratives are limited.
Approach:	They propose a framework to ground free-texts to eventuality-centric KGs for narrative reasoning . their framework is based on a set of probabilistic probabilistic models that are grounded in the real world .
Outcome:	The proposed framework outperforms baseline models while providing interpretable evidence.

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.

When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent Systems (2026.findings-acl)

Copied to clipboard

Xin Yang, Junhao Wang, Bintao Tang, Xuxin Cheng, Cao Liu, Ke Zeng, Wenyuan Jiang

Challenge:	MAS-BENCH isolates coordination under explicit communication constraints . CAMOC significantly improves coordination success and efficiency across backends .
Approach:	They propose a distributed-sorting benchmark that isolates coordination under explicit communication constraints.
Outcome:	MAS-BENCH improves coordination success and efficiency across backends . CAMOC significantly improves efficiency under shared-state interaction .

SHIELD: LLM-Driven Schema Induction for Predictive Analytics in EV Battery Supply Chain Disruptions (2024.emnlp-industry)

Copied to clipboard

Zhi-Qi Cheng, Yifei Dong, Aike Shi, Wei Liu, Yuzhi Hu, Jason O’Connor, Alexander Hauptmann, Kate Whitefoot

Uni-Dubbing: Zero-Shot Speech Synthesis from Visual Articulation (2024.acl-long)

Challenge:	EV battery supply chain is vulnerable to disruptions caused by natural disasters and geopolitical tensions.
Approach:	They propose a system integrating Large Language Models with domain expertise for EV supply chain risk assessment.
Outcome:	Evaluated on 12,070 paragraphs from 365 sources (2022-2023), SHIELD outperforms baseline GCNs and LLM+prompt methods in disruption prediction.

Copied to clipboard

Songju Lei, Xize Cheng, Mengjiao Lyu, Jianqiao Hu, Jintao Tan, Runlin Liu, Lingyu Xiong, Tao Jin, Xiandong Li, Zhou Zhao

Biomedical Concept Normalization by Leveraging Hypernyms (2021.emnlp-main)

Challenge:	Multimodal speech synthesis is a key challenge due to the scarcity of datasets that pair audio with corresponding video.
Approach:	They propose a method that incorporates modality alignment during the pre-training phase on multimodal datasets and freezes the video modality extraction component and the encoder module within the pretrained weights.
Outcome:	The proposed method achieves a reduced word error rate (WER) of 31.73%, surpassing the previous best of 33.9% with single-modality audio.

Copied to clipboard

Cheng Yan, Yuanzhe Zhang, Kang Liu, Jun Zhao, Yafei Shi, Shengping Liu

Challenge:	Biomedical Concept Normalization (BCN) is widely used in biomedical text processing . despite numerous surface variants of biomedically-defined concepts, it remains challenging and unsolved.
Approach:	They propose a framework that uses hypernyms and synonyms to facilitate BCN . they use list-wise training to make use of both hypernies and synonym entities .
Outcome:	The proposed framework outperforms the state-of-the-art model on the NCBI dataset.

Improving Domain Generalization for Prompt-Aware Essay Scoring via Disentangled Representation Learning (2023.acl-long)

Copied to clipboard

Zhiwei Jiang, Tianyi Gao, Yafeng Yin, Meng Liu, Hua Yu, Zifeng Cheng, Qing Gu

bert2BERT: Towards Reusable Pretrained Language Models (2022.acl-long)

Challenge:	Existing AES models are either prompt-specific or prompt-adaptive and cannot generalize well on “unseen” prompts.
Approach:	They propose a prompt-aware neural AES model to extract comprehensive representation for essay scoring, including both prompt-invariant and prompt-specific features.
Outcome:	The proposed model extracts comprehensive representation for essay scoring, including both prompt-invariant and prompt-specific features.

Copied to clipboard

Cheng Chen, Yichun Yin, Lifeng Shang, Xin Jiang, Yujia Qin, Fengyu Wang, Zhi Wang, Xiao Chen, Zhiyuan Liu, Qun Liu

Uncertainty Quantification for In-Context Learning of Large Language Models (2024.naacl-long)

Challenge:	Pre-training large language models can be expensive and wasteful.
Approach:	They propose a method which can transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and a two-stage learning method to further accelerate the pre-training.
Outcome:	The proposed method can transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and significantly improve the pre-training efficiency of the large model.

Copied to clipboard

Chen Ling, Xujiang Zhao, Xuchao Zhang, Wei Cheng, Yanchi Liu, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Jie Ji, Guangji Bai, Liang Zhao, Haifeng Chen

Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States (2025.acl-long)

Challenge:	Existing studies on in-context learning have focused on quantifying the uncertainty associated with the model's response, but they neglect the complexity of the LLM and the uniqueness of in-constitut learning.
Approach:	They propose a method to quantify the uncertainty associated with in-context learning and propose corresponding estimation method to quantify both types of uncertainties.
Outcome:	The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.

Copied to clipboard

Yang Xiao, Jiashuo Wang, Qiancheng Xu, Changhe Song, Chunpu Xu, Yi Cheng, Wenjie Li, Pengfei Liu

Linguistics & Cognitive NLP

Challenge:	Existing benchmarks assess basic Theory of Mind abilities but neglect temporal evolution of mental states in real-world social contexts.
Approach:	They propose a benchmark specifically designed to evaluate Large Language Models' ability to understand and track the temporal progression of mental states across interconnected scenarios.
Outcome:	The proposed benchmarks underperform humans by 44.7% and show that they can model the dynamic nature of human mental states better than existing models.

InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding (2025.findings-emnlp)

Copied to clipboard

Cheng Jiayang, Qianqian Zhuang, Haoran Li, Chunkit Chan, Xin Liu, Lin Qiu, Yangqiu Song

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning (2026.acl-long)

Challenge:	Existing grounding approaches work well for simple queries, but many real-world information needs require synthesizing multiple pieces of evidence.
Approach:	They introduce "integrative grounding" to evaluate the ability to ground large language models in external knowledge sources.
Outcome:	The proposed approach is robust to redundant evidence, but rationalizes using internal knowledge when information is incomplete.

Copied to clipboard

Changyu Liu, Yiyang Liu, Taowen Wang, Qiao Zhuang, James Chenhao Liang, Wenhao Yang, Renjing Xu, Qifan Wang, Dongfang Liu, Cheng Han

Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding (2022.findings-emnlp)

Challenge:	Existing vision-language-action models are unsuitable for simulated or physical-world deployments . current methods fail when confronted with inherent real-world dynamic variability.
Approach:	They propose a test-time reinforcement learning framework that enables on-the-fly policy adaptation during inference.
Outcome:	Empirical results show that the proposed framework improves adaptability, stability and task success in dynamic, previously unseen scenarios.

Copied to clipboard

Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun, Zeyu Xiong

Won’t Get Fooled Again: Answering Questions with False Premises (2023.acl-long)

Challenge:	Existing methods for temporal sentence grounding ignore two crucial issues . 1) Boundary-bias: the video downsampling process may lose these two frames . 2) Reasoning-biases: such incorrect new boundary frames lead to the reasoning bias .
Approach:	They propose a siamese sampling mechanism to generate additional contextual frames . they use a reasoning strategy to learn the inter-relationship among these frames a .
Outcome:	Extensive experiments demonstrate the effectiveness of a new siamese sampling network on three challenging datasets.

Copied to clipboard

Shengding Hu, Yifan Luo, Huadong Wang, Xingyi Cheng, Zhiyuan Liu, Maosong Sun

Question Answering

Challenge:	Pre-trained language models (PLMs) are often easily deceived by tricky questions such as “How many eyes does the sun have?” .
Approach:	They annotate a FalseQA dataset containing 2365 human-written FPQs and find that PLMs are capable of discriminating FPqs by fine-tuning on moderate numbers.
Outcome:	The proposed model can discriminate on FPQs by fine-tuning on moderate numbers of examples and generate reasonable explanations for false premise questions.

ODL-TempLLM: Ontology-Guided and Description Logic-Reasoned Temporal Reasoning with LLMs (2026.acl-long)

Copied to clipboard

Jinshuo Liu, Cheng Bi, Meng Wang, Juan Deng, Donghong Ji, Jeff Z. Pan

JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning (2024.acl-demos)

Challenge:	Temporal reasoning is crucial for large language models to understand event concurrency and complex temporal interactions in natural language.
Approach:	They propose an ontology-guided and description logic–constrained temporal reasoning paradigm that shifts focus from internal inference to the explicit modeling of temporal structure.
Outcome:	The proposed method outperforms state-of-the-art methods by 2.07–31.83 F1 points and 1.00–30.73 EM points, exhibiting strong generalization and highlighting the potential of explicit temporal reasoning.

Copied to clipboard

Anique Tahir, Lu Cheng, Huan Liu

Discourse Self-Attention for Discourse Element Identification in Argumentative Student Essays (2020.emnlp-main)

Challenge:	Large Language Models (LLMs) face significant memory constraints when fine-tuning large prompt sequences.
Approach:	They propose a framework for PEFT-compatible fine-tuning of large language models, leveraging distributed training.
Outcome:	The proposed framework improves performance 12x compared to Hugging Face/DeepSpeed implementation with four GPUs while consuming less than half the VRAM per GPU.

Copied to clipboard

Wei Song, Ziyao Song, Ruiji Fu, Lizhen Liu, Miaomiao Cheng, Ting Liu

SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)

Challenge:	Despite its importance, discourse element identification is challenging due to the ambiguity of sentences . the number of elaboration sentences could be 10 times more than the number edna sentences.
Approach:	They propose to use sentence positional encodings to explicitly represent sentence positions and inter-sentence attentions to capture sentence interactions and enhance sentence representation.
Outcome:	The proposed model improves on a Chinese and English dataset.

Copied to clipboard

Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing

GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression (2025.emnlp-main)

Challenge:	Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages.
Approach:	They propose a series of language models that specifically focuses on Southeast Asian languages.
Outcome:	SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations .

Copied to clipboard

Kainan Liu, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, Jing Xiao

Towards Robust Temporal Activity Localization Learning with Noisy Labels (2024.lrec-main)

Challenge:	Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing these layers to reduce inference cost.
Approach:	They propose a framework that removes redundant layers to reduce inference cost by preserving sensitivity-aware singular values.
Outcome:	The proposed framework outperforms existing methods in 90% of the original model under a 20% compression ratio.

Copied to clipboard

Daizong Liu, Xiaoye Qu, Xiang Fang, Jianfeng Dong, Pan Zhou, Guoshun Nan, Keke Tang, Wanlong Fang, Yu Cheng

Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement (2026.findings-eacl)

Challenge:	Existing methods for temporal activity localization are expensive and difficult to satisfy due to subjective labeling.
Approach:	They propose a new TAL setting where a TAL model should be robust to mixed training data with noisy moment boundaries.
Outcome:	The proposed method is significantly more robust to noisy training data than existing methods.

Copied to clipboard

Wangyang Ying, Yanchi Liu, Xujiang Zhao, Wei Cheng, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen

Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Challenge:	Recent advances in large language models (LLMs) show potential for graph extraction, but often yield ill-formed structures or misinterpret logical constructs such as gateways.
Approach:	They propose a framework that treats procedural graph extraction as a multi-round reasoning process with structural and logical refinement agents.
Outcome:	The proposed framework achieves significant improvements in structural correctness and logical consistency over strong baselines.

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.

Patient Knowledge Distillation for BERT Model Compression (D19-1)

Copied to clipboard

Siqi Sun, Yu Cheng, Zhe Gan, Jingjing Liu

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization (2026.findings-acl)

Challenge:	Pre-trained language models such as BERT have proven to be highly effective for natural language processing tasks, but the high demand for computing resources hinders their application in practice.
Approach:	They propose to compress an original large model (teacher) into an equally-effective lightweight shallow network (student) Empirically, this translates into improved results on multiple NLP tasks with a significant gain in training efficiency, without sacrificing model accuracy.
Outcome:	The proposed model reduces the computational cost of training models using the teacher model into a lightweight shallow network.

Copied to clipboard

Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang

Search-Oriented Conversational Query Editing (2023.findings-acl)

Challenge:	Large Language Models (LLMs) can solve complex tasks through iterative information retrieval.
Approach:	They propose a turn-level stage-aware policy optimization approach to solve this problem . they introduce a first-occurrence latent reward mechanism to allocate partial rewards .
Outcome:	Experiments show that TSPO outperforms state-of-the-art models on Qwen2.5-3B and 7B models.

Copied to clipboard

Kelong Mao, Zhicheng Dou, Bang Liu, Hongjin Qian, Fengran Mo, Xiangli Wu, Xiaohua Cheng, Zhao Cao

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities (2024.findings-emnlp)

Challenge:	Existing CQR models are not learned toward improving the downstream search performance . existing models generate the rewrite token-by-token from scratch .
Approach:	They propose a text editing-based CQR model tailored for conversational search . they propose rewrite tokens are selected from the dialogue in a non-autoregressive fashion .
Outcome:	The proposed model outperforms state-of-the-art models on three conversational search benchmarks while having low rewriting latency.

Copied to clipboard

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Hongcheng Gao, Yilong Xu, Xueqi Cheng

Challenge:	Existing methods to update parametric knowledge of large language models (LLMs) are outdated and incontext editing (KE) is not effective due to the substantial cost associated with retraining.
Approach:	They propose a new decoding technique that enhances in-context editing (ICE) they propose to use parametric knowledge to update the models' knowledge .
Outcome:	The proposed technique improves ICE performance while incurring only half the latency.

SemAttack: Natural Textual Attacks via Different Semantic Spaces (2022.findings-naacl)

Copied to clipboard

Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li

Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better (2024.acl-long)

Challenge:	Existing approaches to attack pre-trained language models suffer from low success rates or fail to search efficiently in the exponentially large perturbation space.
Approach:	They propose an efficient framework to generate natural adversarial text by constructing different semantic perturbation functions.
Outcome:	The proposed framework generates natural adversarial texts for different languages with high success rates.

Copied to clipboard

Shengchao Liu, Xiaoming Liu, Yichen Wang, Zehua Cheng, Chengzhengxu Li, Zhaohan Zhang, Yu Lan, Chao Shen

Learning to Instruct: Fine-Tuning a Task-Aware Instruction Optimizer for Black-Box LLMs (2025.findings-emnlp)

Challenge:	Existing methods to detect MGT from human-written texts are inadequate . existing methods are fine-tuned and zero-shot metric-based, but they can be more accurate.
Approach:	They propose a novel fine-tuned detector that can detect MGT from human-written texts by contrastive learning on selective perturbation.
Outcome:	The proposed method outperforms the state-of-the-art by 1.20% on four public datasets.

Copied to clipboard

Yunzhe Qi, Jinjin Tian, Tianci Liu, Ruirui Li, Tianxin Wei, Hui Liu, Xianfeng Tang, Monica Xiao Cheng, Jingrui He

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)

Challenge:	Learning to Instruct is a new paradigm for black-box LLMs with inaccessible internal states.
Approach:	They propose a new paradigm that formulates instruction optimization as an LLM fine-tuning objective for a white-box “instruction engineer” LLM.
Outcome:	The proposed framework outperforms strong baselines in performance and efficiency.

Copied to clipboard

Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng

Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework (2025.findings-acl)

Challenge:	Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome .
Approach:	They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens.
Outcome:	The proposed method reduces token usage by up to 44% while preserving accuracy.

Copied to clipboard

Kaishuai Xu, Tiezheng Yu, Yi Cheng, Wenjun Hou, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li

CMIG: Conceptual Metaphor Theory-Inspired Framework for Metaphorical Image Generation (2026.findings-acl)

Challenge:	Existing methods for fine-tuning open-source LLMs are limited to text-based analysis under predefined general criteria.
Approach:	They propose a framework that fine-tunes LLMs to replicate the evaluation explanations and judgments of proprietary models.
Outcome:	The proposed evaluation framework outperforms existing fine-tuned evaluation methods in effectiveness and robustness.

Copied to clipboard

Qingbao Huang, Cheng Yang, Jiawei Yao, Zhiyue Liu, Yi Cai, Xingmao Zhang

Uncertainty Propagation on LLM Agent (2025.acl-long)

Challenge:	Existing text-to-image systems often produce visually plausible but semantically literal outputs.
Approach:	They propose a structured prompting framework inspired by Conceptual Metaphor Theory . they propose to identify source–target mappings, filter projectable source attributes and select a visual realization strategy in a reproducible reasoning workflow.
Outcome:	The proposed framework improves semantic alignment and controllability on metaphor prompts.

Copied to clipboard

Qiwei Zhao, Dong Li, Yanchi Liu, Wei Cheng, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Huaxiu Yao, Chen Zhao, Haifeng Chen, Xujiang Zhao

Challenge:	Existing methods for estimating uncertainty in large language models (LLMs) focus on final-step outputs, which fail to account for cumulative uncertainty over multi-step decision-making process and dynamic interactions between agents and their environments.
Approach:	They propose a framework that propagates uncertainty through each step of an LLM-based agent’s reasoning process.
Outcome:	Extensive experiments on benchmark datasets show that the proposed framework outperforms state-of-the-art methods by 20%.

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)

Copied to clipboard

Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang

Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)

Challenge:	Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence.
Approach:	They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included .
Outcome:	The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model.

Copied to clipboard

Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng

AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge.
Approach:	They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy.
Outcome:	The proposed model protects private data while enhancing the model's knowledge.

Copied to clipboard

Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu

Posterior Differential Regularization with f-divergence for Improving Model Robustness (2021.naacl-main)

Challenge:	Significant concerns emerge when addressing cultural sensitivity and local values.
Approach:	They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models.
Outcome:	The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks.

Copied to clipboard

Hao Cheng, Xiaodong Liu, Lis Pereira, Yaoliang Yu, Jianfeng Gao

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation (2025.emnlp-main)

Challenge:	Recent studies show that pre-trained models suffer catastrophic degradation in out-of-domain generalization to datasets with domain shift or adversarial scenarios.
Approach:	They propose to regularize the posterior difference between clean and noisy inputs by using a Jacobian regularization framework and a virtual adversarial training framework.
Outcome:	The proposed framework can improve model robustness in fully supervised and semi-supervised settings.

Copied to clipboard

Jiayu Yao, Shenghua Liu, Yiwei Wang, Lingrui Mei, Baolong Bi, Yuyao Ge, Zhecheng Li, Xueqi Cheng

Mitigating Bias in Session-based Cyberbullying Detection: A Non-Compromising Approach (2021.acl-long)

Challenge:	Existing RAG models are sensitive to the order in which evidence is presented, resulting in unstable performance and biased reasoning.
Approach:	They propose to quantify position bias in multimodal RAG systems by using position sensitivity index . they also develop a visualization framework to trace attention allocation patterns across decoder layers .
Outcome:	The proposed framework shows that multimodal interactions intensify position bias compared to unimodal settings and that this bias increases logarithmically with retrieval range.

Copied to clipboard

Lu Cheng, Ahmadreza Mosallanezhad, Yasin Silva, Deborah Hall, Huan Liu

MixLLM: Dynamic Routing in Mixed Large Language Models (2025.naacl-long)

Challenge:	Existing efforts to enhance the performance of session-based cyberbullying detection have overlooked unintended social biases in existing datasets.
Approach:	They propose a model-agnostic debiasing strategy that leverages a reinforcement learning technique to mitigate unintended biases in existing datasets.
Outcome:	The proposed approach can mitigate unintended biases without impairing the detection performance.

Copied to clipboard

Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen

MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models (2026.findings-eacl)

Challenge:	Large Language Models (LLMs) exhibit potential artificial generic intelligence, however, their usage is costly with high response latency.
Approach:	They develop a dynamic contextual-bandit-based routing system for query-LLM assignment that leverages query tags to enhance query embeddings.
Outcome:	The proposed model maximizes response quality and minimizes cost and latency.

Copied to clipboard

Siwei Wu, King Zhu, Yu Bai, Yiming Liang, Yizhi Li, Haoning Wu, Jiaheng Liu, Ruibo Liu, Xingwei Qu, Xuxin Cheng, Ge Zhang, Wenhao Huang, Chenghua Lin

EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving (2026.findings-acl)

Challenge:	Current multimodal benchmarks focus on facts within individual images, but neglect associative relations among multiple images.
Approach:	They propose a multi-image relational association task and a MMRA benchmark to evaluate LVLMs.
Outcome:	The proposed benchmarks show that entity-level multi-image perception tasks pose greater challenges than image-level tasks.

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

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)

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

Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning (2026.acl-long)

Challenge:	Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references.
Approach:	They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings.
Outcome:	The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading.

Copied to clipboard

Songxin Qu, Tai-Ping Sun, Yun-Jie Wang, Huan-Yu Liu, Cheng Xue, Xiao-Fan Xu, Han Fang, Yang Yang, Yu-Chun Wu, Guo-Ping Guo, Zhao-Yun Chen

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning (2026.findings-acl)

Challenge:	Large language models lack reliability in scientific domains that require strict adherence to physical constraints.
Approach:	They propose a large-scale dataset constructed via a task-adaptive strategy and a hybrid verification protocol that combines deterministic solvers with semantic auditing to guarantee scientific rigor.
Outcome:	The proposed model outperforms baselines and general-purpose preference models and is competitive with proprietary models.

Copied to clipboard

Yi Chen, Yuying Ge, Rui Wang, Yixiao Ge, Junhao Cheng, Ying Shan, Xihui Liu

Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models (2025.acl-long)

Challenge:	Recent reinforcement learning approaches have advanced reasoning in Large Language Models (LLMs), yet their adaptation to multimodal LLMs remains underexplored.
Approach:	They propose a reinforcement learning framework that eliminates KL penalties and rewards consistency . they propose GRPO-CARE, which outperforms standard GR PO, with a base reward for accuracy and an adaptive bonus for consistency.
Outcome:	The proposed framework outperforms standard GRPO on the most difficult evaluation level and reasoning consistency test benchmarks.

Copied to clipboard

Xinxin Liu, Aaron Thomas, Cheng Zhang, Jianyi Cheng, Yiren Zhao, Xitong Gao

Soft Contextual Data Augmentation for Neural Machine Translation (P19-1)

Challenge:	Existing methods for fine-tuning large language models require expensive training on consumer-grade hardwares.
Approach:	They propose a sparsity-based approach that introduces trainable sparse adaptations to the weight matrices in the model and offers greater flexibility in selecting fine-tuned parameters.
Outcome:	The proposed method outperforms other methods for a simple yet effective baseline for nLP tasks while sacrificing performance.

Copied to clipboard

Fei Gao, Jinhua Zhu, Lijun Wu, Yingce Xia, Tao Qin, Xueqi Cheng, Wengang Zhou, Tie-Yan Liu

Machine Translation

Challenge:	Existing methods for enhancing training data are limited in natural language tasks due to text characteristics.
Approach:	They propose a data augmentation method that softly augments a randomly chosen word in a sentence by its contextual mixture of multiple related words.
Outcome:	The proposed method outperforms baseline methods on small and large scale machine translation datasets.

Conformal Event Prediction with Temporal Knowledge Graph (2026.findings-acl)

Copied to clipboard

Cheng Hu, Cong Cao, Fangfang Yuan, Diandian Guo, Pin Xu, Yu Liu, Yanbing Liu

Knowledge Representation

Challenge:	Current event prediction methods lack rigorous uncertainty quantification, which limits their reliability for decision-making.
Approach:	They propose a conformal prediction framework that applies conformal predictions to event prediction to address this challenge.
Outcome:	The proposed framework guarantees coverage while improving efficiency on three public datasets.

Chinese Court Simulation with LLM-Based Agents System (2026.findings-acl)

Copied to clipboard

Kaiyuan Zhang, Jiaqi Li, Yueyue Wu, Haitao Li, Cheng Luo, Shaokun Zou, Yujia Zhou, Weihang Su, Yiqun Liu, Qingyao Ai

CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning (2024.acl-long)

Challenge:	Existing studies have neglected the systematic design and procedure evaluation of court simulations, which are critical to the credibility and usage of court simulators in practice.
Approach:	They propose a court simulation paradigm based on the real-world procedure structure of Chinese courts and a framework that focuses on both legal judgment prediction and court procedure analysis.
Outcome:	The proposed model outperforms judges and lawyers from the real trials in many aspects.

Copied to clipboard

Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Cheng Jiayang, Chunkit Chan, Yangqiu Song

Exploring the Potential of ChatGPT on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations (2024.findings-eacl)

Challenge:	Existing approaches to generalize commonsense reasoning lack instantiated knowledge and require pre-built concept taxonomies and annotations.
Approach:	They propose a framework that iteratively performs contextualized conceptualization and instantiation over commonsense knowledge bases by instructing large language models to generate both types of knowledge with critic filtering.
Outcome:	Empirical results show that distilling CANDLE on student models provides benefits across three downstream tasks.

Copied to clipboard

Chunkit Chan, Cheng Jiayang, Weiqi Wang, Yuxin Jiang, Tianqing Fang, Xin Liu, Yangqiu Song

Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition (2026.eacl-long)

Challenge:	Recent studies have demonstrated ChatGPT's remarkable few-shot, even zero-shot learning abilities when compared to other models.
Approach:	They quantitatively evaluate the performance of ChatGPT on inter-sentential relations such as temporal relations, causal relations, and discourse relations.
Outcome:	The proposed model performs well on temporal relations, causal relations, and discourse relations.

Copied to clipboard

Shanshan Liu, Noriki Nishida, Fei Cheng, Narumi Tokunaga, Rumana Ferdous Munne, Yuki Yamagata, Kouji Kozaki, Takehito Utsuro, Yuji Matsumoto

Challenge:	Existing methods for recognizing ontology concepts are limited by the number of annotations available.
Approach:	They propose an evaluation framework built on hierarchical concept indices and novel metrics to measure generalization.
Outcome:	The proposed evaluation framework is built on hierarchical concept indices and novel metrics to measure generalization.

UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (2023.emnlp-main)

Copied to clipboard

Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, Qi Zhang

The Law of Knowledge Overshadowing: Towards Understanding, Predicting and Preventing LLM Hallucination (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have impressive capabilities but need for task-specific prompt engineering can hinder their generalization.
Approach:	They propose a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input.
Outcome:	The proposed model is universally applicable across tasks and models . it mitigates hallucination problem in chatGPT, and it improves even the strongest LLMs.

Copied to clipboard

Yuji Zhang, Sha Li, Cheng Qian, Jiateng Liu, Pengfei Yu, Chi Han, Yi R. Fung, Kathleen McKeown, ChengXiang Zhai, Manling Li, Heng Ji

AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation (2023.acl-long)

Challenge:	Hallucination is a persistent challenge in large language models where even with rigorous quality control, models often generate distorted facts.
Approach:	They propose a new framework to quantify factual hallucinations by modeling knowledge overshadowing.
Outcome:	The proposed framework improves model factuality on Overshadow (27.9%), MemoTrap (13.1%) and NQ-Swap (18.3%).

Copied to clipboard

Rongjie Huang, Huadai Liu, Xize Cheng, Yi Ren, Linjun Li, Zhenhui Ye, Jinzheng He, Lichao Zhang, Jinglin Liu, Xiang Yin, Zhou Zhao

Filter-then-Generate: Large Language Models with Structure-Text Adapter for Knowledge Graph Completion (2025.coling-main)

Challenge:	Existing models for speech-to-speech translation suffer from distinct degradation in noisy environments and fail to translate visual speech.
Approach:	They propose a text-based audio-visual speech-to-speech translation model that integrates visual information with audio-only data to improve system robustness.
Outcome:	The proposed model outperforms models trained on audio-only corpus in two languages . it also improves with low-resource audio-visual data, compared with baselines .

Copied to clipboard

Ben Liu, Jihai Zhang, Fangquan Lin, Cheng Yang, Min Peng

ECON: On the Detection and Resolution of Evidence Conflicts (2024.emnlp-main)

Challenge:	Empirical evidence suggests that LLMs perform worse than conventional KGC approaches.
Approach:	They propose a filter-then-generate paradigm and a multiple-choice question format to harness the capability of LLMs while mitigating the issue casused by hallucinations.
Outcome:	The proposed method achieves substantial performance gain compared to existing state-of-the-art methods.

Copied to clipboard

Cheng Jiayang, Chunkit Chan, Qianqian Zhuang, Lin Qiu, Tianhang Zhang, Tengxiao Liu, Yangqiu Song, Yue Zhang, Pengfei Liu, Zheng Zhang

MCS-Bench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in Chinese Classical Studies (2025.acl-long)

Challenge:	Recent studies have shown that AI generated content is more likely to dominate search results, making it difficult to detect when compared to human-produced content.
Approach:	They propose a method for generating diverse, validated evidence conflicts to simulate real-world misinformation scenarios.
Outcome:	The proposed method enables the detection of conflicting information in real-world scenarios and shows that weaker models struggle with similar answer conflicts while stronger models show robust performance.

Copied to clipboard

Yang Liu, Jiahuan Cao, Hiuyi Cheng, Yongxin Shi, Kai Ding, Lianwen Jin

Open Domain Question Answering with A Unified Knowledge Interface (2022.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced visual and language understanding, but their potential in Chinese Classical Studies (CCS) remains underexplored due to the lack of specialized benchmarks.
Approach:	They propose to develop a multimodal benchmark specifically designed for Chinese Classical Studies across multiple subdomains to bridge this gap.
Outcome:	The proposed benchmark spans seven core subdomains with a total of 45 meticulously designed tasks.

Copied to clipboard

Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, Jianfeng Gao

Contextual Text Style Transfer (2020.findings-emnlp)

Challenge:	a retriever-reader framework is popular for open domain question answering . however, accessing heterogeneous knowledge sources through a unified interface remains unknown .
Approach:	They propose a retriever-reader framework that uses explicit knowledge to access heterogeneous knowledge sources through a unified interface.
Outcome:	The proposed framework can benefit from the expanded knowledge index, the authors show . their approach sets the single-model state-of-the-art on Natural Questions .

Copied to clipboard

Yu Cheng, Zhe Gan, Yizhe Zhang, Oussama Elachqar, Dianqi Li, Jingjing Liu

Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks (2026.acl-long)

Challenge:	Existing methods for text style transfer are limited by the lack of parallel data.
Approach:	They propose a task to translate a sentence into a desired style with its surrounding context taken into account.
Outcome:	The proposed model outperforms state-of-the-art methods across style accuracy, content preservation and contextual consistency metrics.

Copied to clipboard

Xiang Cheng, Yulan Hu, Xiangwen Zhang, Lu Xu, Lide Tan, Zheng Pan, Xin Li, Yong Liu

False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize (2026.findings-acl)

Challenge:	Existing studies on LLM performance on travel planning have shown that existing settings are limited due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries.
Approach:	They propose a benchmark to evaluate LLMs' planning and tool-use abilities in real-world settings by collecting user queries, user preferences, and tools from real scenarios.
Outcome:	The proposed benchmark evaluates agents' capabilities in real-world settings and shows that even advanced models exhibit imbalanced performance across different capabilities.

Copied to clipboard

Cheng Wang, Zeming Wei, Qin Liu, Wenxuan Zhou, Muhao Chen

Large Language Models for Data Annotation and Synthesis: A Survey (2024.emnlp-main)

Challenge:	Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in Large Language Models’ internal representations.
Approach:	They propose to use probing-based methods to study separability of malicious and benign inputs in LLMs' internal representations to detect harmful and benign content.
Outcome:	The proposed methods show that they learn superficial patterns rather than semantic harmfulness.

Copied to clipboard

Zhen Tan, Dawei Li, Song Wang, Alimohammad Beigi, Bohan Jiang, Amrita Bhattacharjee, Mansooreh Karami, Jundong Li, Lu Cheng, Huan Liu

Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model (2024.naacl-long)

Challenge:	Existing surveys focus on LLMs' specific utility for data annotation and synthesis.
Approach:	They propose to use large language models to generate annotations from raw data . they also propose to review learning strategies for models utilizing LLM-generated annotations .
Outcome:	The proposed models can be used to improve the efficacy of machine learning models by generating and labeling raw data with relevant information.

Copied to clipboard

Cheng Qian, Chenyan Xiong, Zhenghao Liu, Zhiyuan Liu

Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism (2026.acl-long)

Challenge:	Large Language Models (LLMs) have made significant progress in utilizing tools, but their closed-source nature and high inference costs pose limitations on their adaptability.
Approach:	They propose a framework that performs task-solving by first creating a toolkit and then integrating the planning and calling of tools through a chain-of-solve approach.
Outcome:	The proposed model performs task-solving by harnessing Toolink's creativity and CoS ability on ChatGPT and finetunes the LLaMA-7B model.

Copied to clipboard

Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou

Towards Robust Neural Machine Translation (P18-1)

Challenge:	Existing models lack task-guided specialized memory mechanisms . specialized generalist models excel at general language tasks but struggle in specialized domains.
Approach:	They propose a specialized generalist model with specialized memory and updater that can optimize for specialized domains.
Outcome:	The proposed model matches or surpasses baselines on general benchmarks and achieves lowest perplexity across specialized domains.

Copied to clipboard

Yong Cheng, Zhaopeng Tu, Fandong Meng, Junjie Zhai, Yang Liu

Intention Knowledge Graph Construction for User Intention Relation Modeling (2026.eacl-long)

Challenge:	Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation models.
Approach:	They propose adversarial stability training to make encoder and decoder robust to perturbations by enabling them to behave similarly for the original input and its perturbed counterpart.
Outcome:	The proposed approach improves translation quality and robustness over strong models on Chinese-English, English-German and English-French translation tasks.

Copied to clipboard

Jiaxin Bai, Zhaobo Wang, Junfei Cheng, Dan Yu, Zerui Huang, Weiqi Wang, Xin Liu, Chen Luo, Yanming Zhu, Bo Li, Yangqiu Song

NewsDialogues: Towards Proactive News Grounded Conversation (2023.findings-acl)

Challenge:	Existing knowledge graphs focus on connecting intentions but lacks the ability to model the relationships between different intentions.
Approach:	They propose a framework to automatically generate an intention knowledge graph, capturing connections between user intentions.
Outcome:	The proposed model outperforms state-of-the-art methods and shows its utility.

Copied to clipboard

Siheng Li, Yichun Yin, Cheng Yang, Wangjie Jiang, Yiwei Li, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang

LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)

Challenge:	Hot news is one of the most popular topics in daily conversations.
Approach:	They propose a task where a dialogue system can lead the conversation based on key topics of the news.
Outcome:	The proposed method can lead conversations based on key topics of the news . it can also be used in information-seeking and chit-chat scenarios .

Copied to clipboard

Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li

DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition (2023.findings-acl)

Challenge:	Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training.
Approach:	They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks.

Copied to clipboard

Chunkit Chan, Xin Liu, Jiayang Cheng, Zihan Li, Yangqiu Song, Ginny Wong, Simon See

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router (2026.acl-long)

Challenge:	Existing works on implicit discourse relation recognition focus on syntax features and lack of connectives.
Approach:	They propose a prompt-based path prediction method that integrates the interactive information and intrinsic senses among the hierarchy in IDRR.
Outcome:	The proposed method shows significant improvement against competitive baselines.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Ruibin Yuan, Xueqi Cheng

Targeted Adversarial Training for Natural Language Understanding (2021.naacl-main)

Challenge:	Current alignment approaches rely on refusal alignment to avoid harmful content . large language models are often overly cautious or overlook subtle harmful content.
Approach:	They propose a framework for fine-grained safe generation in Large Language Models that enables real-time, token-level harmfulness detection and redaction without loss in capability.
Outcome:	The proposed framework achieves over 90% in F1 score for detecting and redacting harmful content while preserving overall utility and informativeness of the model’s responses.

Copied to clipboard

Lis Pereira, Xiaodong Liu, Hao Cheng, Hoifung Poon, Jianfeng Gao, Ichiro Kobayashi

OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)

Challenge:	Existing adversarial training approaches focus on making adversarials less expensive or regularizing rather than replacing the standard training objective.
Approach:	They propose an algorithm to introspect current mistakes and prioritize adversarial training steps to where the model errs the most.
Outcome:	The proposed algorithm improves adversarial training for natural language understanding by introspecting mistakes and prioritizing training steps to where the model errs the most.

Copied to clipboard

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting (2026.acl-short)

Challenge:	Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs.
Approach:	They propose a framework that integrates dialogue, reasoning, and personalized recommendation.
Outcome:	Experiments across public benchmarks show state-of-the-art performance.

Copied to clipboard

Cheng Wang, Qin Liu, Wenxuan Zhou, Muhao Chen

HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Excessive exploitation can cause the model to become overconfident in its suboptimal solutions, thereby limiting its capabilities to explore novel reasoning strategies.
Approach:	They propose a method that dynamically down-weights extreme token-level updates via a Gaussian kernel and reduces the instability caused by the trade-off.
Outcome:	The proposed method improves downstream performance across reasoning benchmarks and stabilizes entropy as training progresses.

Copied to clipboard

Jie Ouyang, Tingyue Pan, Mingyue Cheng, Ruiran Yan, Yucong Luo, Jiaying Lin, Qi Liu

Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context (2025.emnlp-main)

Challenge:	Current approaches to addressing knowledge outdating in LLMs struggle with retrieval and generation aspects when handling outdated information.
Approach:	They propose a benchmark to evaluate the impact of outdated information on RAG . they use token-level diff algorithms and LLM pipelines to create a large-scale QA dataset .
Outcome:	The proposed benchmark analyzes the impact of outdated information on RAG performance.

Copied to clipboard

Rushi Wang, Jiateng Liu, Cheng Qian, Yifan Shen, Yanzhou Pan, Zhaozhuo Xu, Ahmed Abbasi, Heng Ji, Denghui Zhang

Identifying while Learning for Document Event Causality Identification (2024.acl-long)

Challenge:	Incorporating external context can enhance the response quality of Large Language Models (LLMs). however, real-world contexts often mix relevant information with disproportionate inappropriate content.
Approach:	They propose a Poisoned Context Testbed to pair queries with real-world contexts . they propose 'rw-Steering' to internalize inappropriate signals .
Outcome:	The proposed model improves response quality by 39.8% and reverses undesirable behavior curve.

Copied to clipboard

Cheng Liu, Wei Xiang, Bang Wang

Challenge:	Existing studies focus on causality existence, but ignore causal direction.
Approach:	They propose a new identifying while learning mode for the ECI task that takes care of the causal direction and updates events’ representations for boosting next round of causality identification.
Outcome:	The proposed method outperforms the state-of-the-art methods on two public datasets.

Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts (2025.findings-acl)

Copied to clipboard

Zeliang Zhang, Xiaodong Liu, Hao Cheng, Chenliang Xu, Jianfeng Gao

Challenge:	Large Language Models (LLMs) have outstanding performance by learning a large number of model parameters on large amounts of data.
Approach:	They propose a method of grouping and pruning similar experts to improve the model’s parameter efficiency by a range of natural language tasks.
Outcome:	The proposed method outperforms other model pruning methods on a range of natural language tasks.

LogToP: Logic Tree-of-Program with Table Instruction-tuned LLMs for Controlled Logical Table-to-Text Generation (2026.findings-eacl)

Copied to clipboard

Yupian Lin, Guangya Yu, Cheng Yuan, Huan Du, Hui Luo, Yuang Bian, Jingping Liu, Zhidong He, Wen Du, Tong Ruan

Multi-Fact Correction in Abstractive Text Summarization (2020.emnlp-main)

Challenge:	Existing LLMs are difficult to achieve satisfactory results in table-related tasks.
Approach:	They propose to develop a specialized logical table-to-text generation model that can be used for table-related tasks.
Outcome:	The proposed model achieves state-of-the-art on a Logic2Text dataset.

Copied to clipboard

Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, Jackie Chi Kit Cheung, Jingjing Liu

BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction (2024.acl-long)

Challenge:	Existing abstractive summarization systems generate incorrect facts with respect to the source text.
Approach:	They propose a suite of two factual correction models that leverages question-answering knowledge to make corrections in system-generated summaries via span selection.
Outcome:	The proposed model improves factuality of news summarization without sacrificing summary quality.

Copied to clipboard

Yinhao Bai, Yalan Xie, Xiaoyi Liu, Yuhua Zhao, Zhixin Han, Mengting Hu, Hang Gao, Renhong Cheng

HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training (2020.emnlp-main)

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

Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan, Licheng Yu, Jingjing Liu

Can Large Language Models Act as Ensembler for Multi-GNNs? (2025.emnlp-main)

Challenge:	HERO is a framework for large-scale video+language omni-representation learning.
Approach:	They propose a framework for large-scale video+language omni-representation learning that encodes multimodal inputs in a hierarchical structure and uses Masked Language Modeling and Masked Frame Modeling to train models.
Outcome:	The proposed framework achieves state-of-the-art on multiple benchmarks over text-based video/video-moment retrieval, video question answering (QA), Video-and-language Inference and video Captioning tasks across different domains.

Copied to clipboard

Hanqi Duan, Yao Cheng, Jianxiang Yu, Yao Liu, Xiang Li

Toward Annotator Group Bias in Crowdsourcing (2022.acl-long)

Challenge:	Existing graph neural networks lack the inherent semantic understanding capability of rich textual attributes, limiting their effectiveness in applications.
Approach:	They propose a model that integrates multiple GNNs and LLMs to provide an ensemble for multi-GNNs.
Outcome:	The proposed model outperforms existing models in terms of semantic understanding of graph structures and graph structures.

Copied to clipboard

Haochen Liu, Joseph Thekinen, Sinem Mollaoglu, Da Tang, Ji Yang, Youlong Cheng, Hui Liu, Jiliang Tang

Fisher-Driven Adaptive Locating for Knowledge Editing in Large Language Models (2026.acl-long)

Challenge:	Annotator group bias is a common problem in crowdsourcing, but is often overlooked .
Approach:	They propose a probabilistic framework to capture annotator group bias using an extended Expectation Maximization algorithm.
Outcome:	The proposed model can model annotator group bias over competitive datasets and demonstrate that it is effective over multiple datasets.

Copied to clipboard

Chenghao Xu, Jiexi Yan, Guangtao Lyu, Qi Liu, Muli Yang, Cheng Deng

Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Challenge:	Existing methods for locating and editing static knowledge are costly and risk catastrophic forgetting or error.
Approach:	They propose a Fisher-driven adaptation-aware locating strategy that dynamically identifies which model components should be edited for a given knowledge update.
Outcome:	Experiments on standard benchmarks show that FiDAL improves editing effectiveness and knowledge preservation across multiple editing methods.

Copied to clipboard

Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs (2024.findings-emnlp)

Challenge:	Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach:	They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome:	The proposed system outperforms baselines in the open domain task-solving benchmark.

Copied to clipboard

Wenhua Cheng, Weiwei Zhang, Haihao Shen, Yiyang Cai, Xin He, Lv Kaokao, Yi Liu

AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models (2021.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated exceptional proficiency in language-related tasks, but their deployment poses significant memory and storage requirements.
Approach:	They propose a method that optimizes rounding values and weight clipping within 200 steps.
Outcome:	The proposed method achieves exceptional results across 2 to 4 bits while maintaining low tuning costs and avoiding additional inference overhead.

Copied to clipboard

Yichun Yin, Cheng Chen, Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization (2024.findings-emnlp)

Challenge:	Pre-trained language models (PLMs) have achieved great success in natural language processing.
Approach:	They propose a method that automatically searches architecture hyper-parameters in BERT . they use one-shot learning and the search space to provide an adaptive development way .
Outcome:	The proposed method outperforms both the baseline and distillation-based methods on GLUE and SQUAD benchmarks.

Copied to clipboard

Xijie Huang, Zechun Liu, Shih-Yang Liu, Kwang-Ting Cheng

Wav2SQL: Direct Generalizable Speech-To-SQL Parsing (2024.findings-acl)

Challenge:	Low-Rank Adaptation (LoRA) improves training efficiency by updating only a small portion of the weights in Large Language Models.
Approach:	They propose a rotation-aware scheme to fine-tune rotated outlier-free LLMs for effective weight-activation quantization.
Outcome:	The proposed method improves low-bit LoRA convergence and post-training quantization robustness.

Copied to clipboard

Huadai Liu, Rongjie Huang, Jinzheng He, Gang Sun, Ran Shen, Xize Cheng, Zhou Zhao

Re3: Relevance & Recency Retrieval for Mitigating Temporal Hallucination (2026.acl-long)

Challenge:	Existing models for speech-driven SQL parsing are based on a cascaded approach, resulting in data scarcity and inconsistent performance.
Approach:	They propose a direct generalizable speech-to-SQL parsing model which avoids error compounding across cascaded systems.
Outcome:	The proposed model avoids error compounding and achieves state-of-the-art results by 4.7% improvement over baseline.

Copied to clipboard

Jiawei Cao, Jie Ouyang, Mingyue Cheng, Zhaomeng Zhou, Chunli Liu, Yupeng Li, Zirui Liu, Shijin Wang

ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web (2026.acl-long)

Challenge:	Existing retrievers suffer from temporal-semantic misalignment and outdated-document interference . Existing frameworks suffer from both temporal validity and outdated factual versions .
Approach:	They propose a framework that mitigates temporal hallucinations by embedding heterogeneous temporal signals into the semantic space to ensure retrieval fidelity.
Outcome:	Experiments show that Re3 outperforms baselines by 9.7% in generation accuracy . the framework outperformed strongest baselines on challenging dynamic tasks .

Copied to clipboard

Zhiyuan Yao, Zishan Xu, Yifu Guo, Zhiguang Han, Cheng Yang, Shuo Zhang, Weinan Zhang, Xingshan Zeng, Weiwen Liu

Challenge:	Existing routers that use hardcoded tools are limited by scalability and generality bottlenecks.
Approach:	They propose a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems.
Outcome:	The proposed pipeline can train routers with dynamic context understanding to create the plug-and-play Light Routing Agent.

ECoK: Emotional Commonsense Knowledge Graph for Mining Emotional Gold (2024.findings-acl)

Copied to clipboard

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

Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation (2025.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

Hengran Zhang, Minghao Tang, Keping Bi, Jiafeng Guo, Shihao Liu, Daiting Shi, Dawei Yin, Xueqi Cheng

RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection (2025.acl-long)

Challenge:	Existing studies on large language models for document utility annotations have shown that they improve retrieval performance and RAG outcomes compared to models trained on human annotations.
Approach:	They propose a model that maximizes their summed marginal likelihood to annotate document utility on multiple positive samples per query.
Outcome:	The proposed model maximizes the marginal likelihood of multiple positive samples per query.

Copied to clipboard

Wenjun Hou, Yi Cheng, Kaishuai Xu, Heng Li, Yan Hu, Wenjie Li, Jiang Liu

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage (2025.findings-emnlp)

Challenge:	Existing approaches to enhance radiology report generation overlook the knowledge already embedded within the models, leading to redundant information integration.
Approach:	They propose a framework for enhancing radiology report generation with supplementary knowledge injection that leverages both internal and external knowledge.
Outcome:	Extensive experiments on MIMIC-CXR, CheXpert-Plus, and IU X-ray show that the proposed model outperforms state-of-the-art LLMs in both language quality and clinical accuracy.

Copied to clipboard

Guangwei Zhang, Qisheng Su, Jiateng Liu, Cheng Qian, Yanzhou Pan, Yanjie Fu, Denghui Zhang

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models (2023.findings-emnlp)

Challenge:	Traditional methods address leaks only after content is generated, which can lead to the exposure of sensitive information.
Approach:	They propose a proactive approach: examining LLMs’ internal states before text generation to detect potential leaks.
Outcome:	The proposed framework ensures adherence to copyright and licensing requirements while enhancing data privacy and ethical standards.

Copied to clipboard

Cheng Qian, Chi Han, Yi Fung, Yujia Qin, Zhiyuan Liu, Heng Ji

Parameter-Efficient Fine-Tuning via Circular Convolution (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning.
Approach:	They propose a framework that enables LLMs to create their own tools using documentation and code realization.
Outcome:	The proposed framework outperforms existing chain-of-thought, program-of thought, and tool-using baselines on MATH and TabMWP benchmarks.

Copied to clipboard

Aochuan Chen, Jiashun Cheng, Zijing Liu, Ziqi Gao, Fugee Tsung, Yu Li, Jia Li

LEGENT: Open Platform for Embodied Agents (2024.acl-demos)

Challenge:	Low-Rank Adaptation (LoRA) has gained popularity for fine-tuning large foundation models, but its intrinsic low-rank characteristic may limit its performance.
Approach:	They propose a low-rank adaptive method that uses low-ranked matrices to represent weight changes.
Outcome:	The proposed method reduces trainable parameters and mitigates heavy memory consumption associated with full delta matrices by sequentially multiplying mathbf A and mathbb B with the activation.

Copied to clipboard

Zhili Cheng, Zhitong Wang, Jinyi Hu, Shengding Hu, An Liu, Yuge Tu, Pengkai Li, Lei Shi, Zhiyuan Liu, Maosong Sun