Papers by Wang Gao

Simple Role Assignment is Extraordinarily Effective for Safety Alignment (2026.findings-acl)

Challenge:	Existing methods for few-shot Named Entity Recognition ignore entity boundaries and are time-consuming . a seminal span-based prototypical network solves the problem using two stages: span extraction and mention classification.
Approach:	They propose a seminal span-based prototypical network that tackles few-shot NER . they transform sequential tags into a global boundary matrix and use prototypical learning .
Outcome:	The proposed model outperforms strong baselines over multiple benchmarks.

Copied to clipboard

Zhou Ziheng, Jiakun Ding, Zhaowei Zhang, Ruosen Gao, Ying Nian Wu, Demetri Terzopoulos, Yipeng Kang, Fangwei Zhong, Junqi Wang

Challenge:	a new study proposes a role-conditioned pipeline for value alignment . principles alone are incomplete, and they provide little guidance on when and how a value applies in context.
Approach:	They propose a role-conditioned pipeline with role-based critics and a model-free approach that is based on role conditioning.
Outcome:	The proposed approach outperforms principle-based, Chain-of-Thought and other benchmarks.

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs (2026.acl-long)

Copied to clipboard

Yu Li, Xiaoran Shang, Qizhi Pei, Yun Zhu, Xin Gao, Honglin Lin, Zhanping Zhong, Zhuoshi Pan, Zheng Liu, Xiaoyang Wang, Conghui He, Dahua Lin, Feng Zhao, Lijun Wu

Structured Data in NLP

Challenge:	High-quality post-training data is the primary engine driving LLM capabilities . datasets are often treated as isolated artifacts, overlooking their true developmental context .
Approach:	They propose a framework to reconstruct the evolutionary graph of dataset development using data lineage.
Outcome:	The proposed framework characterizes domain-specific structural patterns in Math-oriented datasets and general-domain corpora.

Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction (2022.findings-emnlp)

Copied to clipboard

Jun Gao, Changlong Yu, Wei Wang, Huan Zhao, Ruifeng Xu

ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning (2025.findings-acl)

Challenge:	Existing data augmentation methods for event extraction are costly and time-consuming.
Approach:	They propose a data augmentation framework that randomly masks out an adjunct sentence fragment and infills a variable-length text span with a fine-tuned infilling model.
Outcome:	The proposed framework can generate more diverse data while keeping the original structure unchanged . it can replace a fragment of arbitrary length in the text with another fragment of variable length .

Copied to clipboard

Yeyuan Wang, Dehong Gao, Rujiao Long, Lei Yi, Linbo Jin, Libin Yang, Xiaoyan Cai

Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models (2024.findings-acl)

Challenge:	Recent advances have extended DPO to multimodal scenarios, achieving strong performance.
Approach:	They propose to use a sentence-level preference optimization technique to optimize individual sentences for more precise preference optimization without additional models or parameters.
Outcome:	Experiments show that Adaptive Sentence-level Preference Optimization significantly improves the alignment of multimodal models.

Copied to clipboard

Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Lin, Bo Wang

DisCo_Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec (2026.acl-long)

Challenge:	Social media has become a fertile ground for nurturing rumors and misinformation due to its lack of systematic moderation.
Approach:	They propose a framework to enhance the joint predictive capabilities of LLMs for stance detection and rumor verification tasks.
Outcome:	The proposed framework outperforms state-of-the-art methods and generalizes to non-LLMs accommodated as task models.

Copied to clipboard

Tao Li, Wenshuo Ge, Zhichao Wang, Zihao Cui, Yong Ma, Yingying Gao, Chao Deng, Shilei Zhang, Junlan Feng

K-order Ranking Preference Optimization for Large Language Models (2025.findings-acl)

Challenge:	DisCo-Speech is a zero-shot controllable text-to-speech framework . standard codecs entangle timbre and prosody, which hinders independent control in continuation-based LMs.
Approach:	They propose a disentangled speech codec and an LM-based generator to solve this problem . they propose fusion and reconstruction that merges content and prosody into unified tokens .
Outcome:	DisCo-Speech achieves competitive voice cloning and superior zero-shot prosody control.

Copied to clipboard

Shihao Cai, Chongming Gao, Yang Zhang, Wentao Shi, Jizhi Zhang, Keqin Bao, Qifan Wang, Fuli Feng

Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More (2025.emnlp-main)

Challenge:	Existing list-wise methods focus on optimizing list ranking consistency for LLMs to improve ranking abilities.
Approach:	They propose to extend the Plackett-Luce model to accommodate top-K ranking by extending the DPO’s Plact-Lucer model to dynamically determine appropriate K for different samples.
Outcome:	The proposed model can be extended to accommodate top-K ranking and improve training efficiency.

Copied to clipboard

Zichen Wen, Yifeng Gao, Shaobo Wang, Junyuan Zhang, Qintong Zhang, Weijia Li, Conghui He, Linfeng Zhang

Safety Sidecar: Reflection-Driven Runtime Control for Safer Agents (2026.findings-acl)

Challenge:	Vision tokens in multimodal large language models often dominate computational overhead due to excessive length compared to linguistic modality.
Approach:	They propose a token pruning method which defines an importance criterion for vision tokens and prunes the unimportant vision token during inference.
Outcome:	The proposed method can prune 88.9% of vision tokens while maintaining comparable performance.

Copied to clipboard

Wang Bin, Quan Jiazheng, Xingrui Yu, Hu Hansen, Yu Hao, Anjun Gao, Zhenglin Wan, Hui LI, Ivor Tsang

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models (2024.acl-long)

Challenge:	Existing safety controls fail to provide runtime intervention or cross-architecture portability for autonomous LLM agents.
Approach:	They propose a model-agnostic, plug-and-play module to provide arbitrary agent safety control and auditability.
Outcome:	The proposed module improves the secure-solution rate by 2.9–11.2 percentage points . it adds only 3.2s to end-to-end latency and a negligible average cost of 5.37 10-4 per scenario .

Copied to clipboard

Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li

Mixture of Diverse Size Experts (2024.emnlp-industry)

Challenge:	Despite the advances in large language models, they still face difficulties with multi-step reasoning tasks.
Approach:	They propose a method that randomly masks certain tokens within the chain of thought to improve model accuracy by 5% over standard supervised fine-tuning.
Outcome:	The proposed method improves accuracy and accuracy by 5% over standard fine-tuning with a few codes modified.

Copied to clipboard

Manxi Sun, Wei Liu, Jian Luan, Pengzhi Gao, Bin Wang

Challenge:	Recent large language models (LLMs) have shown superior performance in a variety of tasks due to the sub-linearly increasing computational costs.
Approach:	They propose a new MoE architecture with designed layers where experts have different sizes to mitigate this defect.
Outcome:	The proposed architecture surpasses existing MoEs by adaptively assigning the parameter budget to experts while maintaining the same total parameter size and number of experts.

Adversarial Domain Adaptation for Machine Reading Comprehension (D19-1)

Copied to clipboard

Huazheng Wang, Zhe Gan, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Hongning Wang

Do Large Language Models excel in Complex Logical Reasoning with Formal Language? (2025.emnlp-main)

Challenge:	Existing models for machine reading comprehension rely on large amounts of human-annotated in-domain data.
Approach:	They propose an unsupervised domain adaptation framework for Machine Reading Comprehension where the source domain has a large amount of labeled data, while only unlabeled passages are available in the target domain.
Outcome:	The proposed framework can be generalizable to different MRC models and datasets and can be extended to semi-supervised learning.

Copied to clipboard

Jin Jiang, Jianing Wang, Yuchen Yan, Yang Liu, Jianhua Zhu, Mengdi Zhang, Liangcai Gao

Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework (2023.acl-long)

Challenge:	Existing studies on LLMs have focused on formal language, but evaluations of their performance are limited.
Approach:	They propose to use a formal language to evaluate LLMs across logical reasoning problems using formal languages.
Outcome:	The proposed model outperforms Instruct models in three dimensions, taxonomy of tasks, and format of trajectories, and achieves the best generalization performance across other languages.

Copied to clipboard

Mingqi Gao, Xiaojun Wan, Jia Su, Zhefeng Wang, Baoxing Huai

A Generative Pre-Trained Language Model for Channel Prediction in Wireless Communications Systems (2025.emnlp-main)

Challenge:	Current evaluations of FEC models that depend on factuality metrics are not reliable and detailed enough.
Approach:	They propose a fine-grained evaluation framework that automatically evaluates FEC models on different error categories.
Outcome:	The proposed evaluation framework compares models on different error categories and finds the best training modes and significant differences in the performance of existing models.

Copied to clipboard

Bo Lin, Huanming Zhang, Yuhua Jiang, Yucong Wang, Tengyu Zhang, Shaoqiang Yan, Hongyao Li, Yihong Liu, Feifei Gao

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

Challenge:	Existing model-based channel prediction methods suffer from limited accuracy due to imperfect temporal modeling, while existing AI-based methods suffers from limited generalization due to inadequate training strategies.
Approach:	They propose a generative pre-trained language model for channel prediction based on channel correlation and train it based upon transformer decoder architecture.
Outcome:	The proposed model can learn various channel characteristics and perform impressive tasks across multiple dimensions.

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.

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

Copied to clipboard

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

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors (2025.emnlp-main)

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

Hao Fang, Jiawei Kong, Tianqu Zhuang, Yixiang Qiu, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Yaowei Wang, Min Zhang

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models (2024.findings-emnlp)

Challenge:	Existing methods to detect large language models (LLMs) generated for plagiarism use paraphrases to rewrite them to evade detection.
Approach:	They propose a training-free method that effectively fools text detectors using off-the-shelf LLMs by rewriting them to evade detection.
Outcome:	The proposed method deceives text detectors using off-the-shelf LLMs by rewriting them to produce human-like sentences that are less discernible by detectors.

Copied to clipboard

Kai Yao, Penglei Gao, Lichun Li, Yuan Zhao, Xiaofeng Wang, Wei Wang, Jianke Zhu

OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning (2024.findings-naacl)

Challenge:	Parameter-Efficient Fine-Tuning (PEFT) methods have gained popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks.
Approach:	They propose a method to optimize the importance of full layers with layer-wise importance scoring by leveraging the estimated importance scores.
Outcome:	The proposed method is compatible with PEFT methods that operate on a per-layer basis and achieves better performance.

Copied to clipboard

Fei Yu, Anningzhe Gao, Benyou Wang

Towards A “Novel” Benchmark: Evaluating Literary Fiction with Large Language Models (2025.findings-acl)

Challenge:	Large language models (LLMs) struggle with maintaining accuracy throughout multiple reasoning steps, especially in mathematical reasoning where an error in earlier steps can propagate to subsequent ones and ultimately leading to an incorrect answer.
Approach:	They propose an Outcome-supervised Value Model (OVM) that employs outcome supervision for training a value model, which prioritizes steps that lead to accurate conclusions.
Outcome:	The proposed model performs better on two multi-step reasoning datasets, GSM8K and Game of 24.

Copied to clipboard

Wenqing Wang, Mingqi Gao, Xinyu Hu, Xiaojun Wan

ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs) context windows have enabled them to process inputs over 100K tokens and generate outputs of up to 10K token.
Approach:	They propose a multi-level evaluation framework that incorporates ten metrics across the Macro, Meso, and Micro levels and an annotated fiction dataset.
Outcome:	The proposed framework incorporates ten metrics across the Macro, Meso, and Micro levels and is based on a human-human-AI dataset.

Copied to clipboard

Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou

Challenge:	Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth.
Approach:	They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning.
Outcome:	The proposed framework outperforms existing methods on ICLR 2025 papers.

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance (2025.emnlp-main)

Copied to clipboard

Songsheng Wang, Rucheng Yu, Zhihang Yuan, Chao Yu, Feng Gao, Yu Wang, Derek F. Wong

Evaluating and Enhancing the Robustness of Code Pre-trained Models through Structure-Aware Adversarial Samples Generation (2023.findings-emnlp)

Challenge:	Visual Language Models (VLMs) have significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models.
Approach:	They propose a framework to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model.
Outcome:	Empirical results show that the proposed framework improves the speed of the prediction task by 44%.

Copied to clipboard

Nuo Chen, Qiushi Sun, Jianing Wang, Ming Gao, Xiaoli Li, Xiang Li

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Pre-trained code models have made significant strides in the field of neural code intelligence, but they are susceptible to adversarial attacks that subtly modify the input sequence and can impair generalization.
Approach:	They propose a set of novel robustness evaluation methods based on the intrinsic structure of the code to explore the impact of imperceptible perturbation.
Outcome:	The proposed methods have demonstrated their effectiveness across a wide range of models and tasks, and are able to predict the performance of perturbed models.

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

Efficient Tool Use with Chain-of-Abstraction Reasoning (2025.coling-main)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Silin Gao, Jane Dwivedi-Yu, Ping Yu, Xiaoqing Ellen Tan, Ramakanth Pasunuru, Olga Golovneva, Koustuv Sinha, Asli Celikyilmaz, Antoine Bosselut, Tianlu Wang

Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation (2022.acl-long)

Challenge:	Recent large language models have made progress at interpreting and executing instructions.
Approach:	They propose a method to decouple general reasoning from specialized knowledge . they propose to use abstract reasoning chains and domain tools to reify each chain .
Outcome:	The proposed method outperforms baseline methods on QA and mathematical reasoning domains.

Copied to clipboard

Xinyu Pi, Bing Wang, Yan Gao, Jiaqi Guo, Zhoujun Li, Jian-Guang Lou

LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Challenge:	Existing Text-to-SQL parsers are vulnerable to perturbations in NL questions . we propose the Adversarial Table Perturbation (ATP) as a new attacking paradigm .
Approach:	They propose to use the Adversarial Table Perturbation to measure robustness of Text-to-SQL parsers against adversarial perturbations.
Outcome:	The proposed approach outperforms baseline methods in robustness evaluations on ADVETA and can be used in future projects.

Copied to clipboard

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Personalized Microblog Sentiment Classification via Adversarial Cross-lingual Multi-task Learning (D18-1)

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

Copied to clipboard

Weichao Wang, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

CodeExp: Explanatory Code Document Generation (2022.findings-emnlp)

Challenge:	Existing personalized microblog sentiment classification methods suffer from the insufficiency of discriminative tweets for personalization learning.
Approach:	They propose to use user-attention-based Convolutional Neural Networks to capture individuality and opinion bias in microblog posts and a novel adversarial cross-lingual learning framework to enrich the user post representation.
Outcome:	The proposed method outperforms state-of-the-art baseline algorithms with large margins on English and Chinese microblog datasets.

Copied to clipboard

Haotian Cui, Chenglong Wang, Junjie Huang, Jeevana Priya Inala, Todd Mytkowicz, Bo Wang, Jianfeng Gao, Nan Duan

SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis (2020.acl-main)

Challenge:	Existing code-to-text generation models produce only high-level code summaries that do not capture implementation-level choices essential for these scenarios.
Approach:	They propose a code explanation generation task that uses code docstrings to refine models.
Outcome:	The proposed model can generate well-structured long docstrings comparable to human-written ones.

Copied to clipboard

Hao Tian, Can Gao, Xinyan Xiao, Hao Liu, Bolei He, Hua Wu, Haifeng Wang, Feng Wu

Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer (2023.emnlp-main)

Challenge:	sentiment knowledge is ignored in sentiment analysis, despite its use in pretraining.
Approach:	They propose to use sentiment knowledge to learn a unified sentiment representation for multiple sentiment analysis tasks.
Outcome:	The proposed method outperforms strong pre-training baseline on three kinds of sentiment tasks.

Copied to clipboard

Ruize Gao, Zhirui Zhang, Yichao Du, Lemao Liu, Rui Wang

OpenHuEval: Evaluating Large Language Model on Hungarian Specifics (2025.findings-acl)

Challenge:	Nearest Neighbor Machine Translation (kNN-MT) is a powerful domain adaptation tool . the reasons for its success have not been thoroughly investigated .
Approach:	They propose to integrate pre-trained Neural Machine Translation models with token-level retrieval . they propose to implicitly execute gradient descent on the output projection layer of NMT .
Outcome:	The proposed approach outperforms model fine-tuning on in-domain tests while achieving better performance on out-of-domain sets.

Copied to clipboard

Haote Yang, Xingjian Wei, Jiang Wu, Noémi Ligeti-Nagy, Jiaxing Sun, Yinfan Wang, Győző Zijian Yang, Junyuan Gao, Jingchao Wang, Bowen Jiang, Shasha Wang, Nanjun Yu, Zihao Zhang, Shixin Hong, Hongwei Liu, Wei Li, Songyang Zhang, Dahua Lin, Lijun Wu, Gábor Prószéky, Conghui He

TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators (2025.findings-acl)

Challenge:	Recent advances in Large Language Models (LLMs) represent significant strides toward artificial general intelligence (AGI).
Approach:	They introduce OpenHuEval, the first benchmark for LLMs focusing on the Hungarian language and specifics.
Outcome:	The framework reveals intrinsic patterns and mechanisms of LLMs in non-English languages, with Hungarian serving as an example.

Copied to clipboard

Jianling Li, ShangZhan Li, Zhenye Gao, Qi Shi, Yuxuan Li, Zefan Wang, Jiacheng Huang, WangHaojie WangHaojie, Jianrong Wang, Xu Han, Zhiyuan Liu, Maosong Sun

DRBO: Mitigating Short Board Effect via Dynamic Reward Balancing in Multi-reward LLM Optimization (2025.findings-emnlp)

Challenge:	Triton is a high-level Python-like programming language for building efficient GPU kernels.
Approach:	They propose a TritonBench benchmark that provides a comprehensive evaluation of Tritonic operators on widely deployed GPUs.
Outcome:	The proposed benchmarks show that current LLMs struggle to generate efficient Triton operators on widely deployed GPUs aligned with industry applications.

Copied to clipboard

Nuo Chen, Yufei Gao, Yongnan Jin, Yan Hu, Anningzhe Gao, Lingyong Yan, Benyou Wang

Challenge:	a new framework to optimize large language models (LLMs) for evaluation metrics is needed to balance weaker metrics.
Approach:	They propose a Dynamic Reward Balancing Optimization framework to mitigate the "short-board effect" they apply it to single-task and multi-type task scenarios .
Outcome:	The proposed framework improves performance and balances performance across multiple metrics.

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)

Copied to clipboard

Zheng Liu, Honglin Lin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Conghui He, Bin Cui, Wentao Zhang, Lijun Wu

Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs (2026.acl-long)

Challenge:	Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations .
Approach:	They propose a framework to synthesize complex charts and reliable reasoning data from scratch.
Outcome:	Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models .

Copied to clipboard

Xinyu Gao, Shaonan Wang, Nai Ding

Beyond Surface-Level Pattern Trap: LLM Agents for Faster and Smarter Cross-Architecture Code Migration (2026.findings-acl)

Challenge:	Decoder-only large language models are brittle to minor grammatical perturbations, causing reliability problems.
Approach:	They propose a checkpoint-compatible gated tree cross-attention branch that reads constituency chunk memory while keeping the backbone architecture unchanged.
Outcome:	The proposed framework strengthens syntactic competence beyond continued training benchmarks and transformer backbones without compromising commonsense reasoning.

Copied to clipboard

Weijia Li, KE Gao, Pengfei Chen, Jiajie Li, Xinyu Wang, Yiran Le, Yize Wu, Ling Li

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

Challenge:	cross-architecture code migration is a resource-intensive and errorprone task.
Approach:	a framework for cross-architecture code migration is proposed to decouple implementation details through functional mining and code refactoring.
Outcome:	a new framework improves performance and correctness over state-of-the-art frameworks on OpenCV migration tasks.

Copied to clipboard

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

TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation (2025.findings-emnlp)

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

Chengrui Huang, Shen Gao, Zhengliang Shi, Dongsheng Wang, Shuo Shang

Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)

Challenge:	Existing tool-learning methods often overlook fine-grained optimization of internal tool call details.
Approach:	They propose a training paradigm for constructing token-level tool-use preference datasets . reversed dataset construction is a method for creating high-quality, multi-turn tool-user datasets by reversing the generation flow.
Outcome:	a new training paradigm improves tool-using performance and generalizes results.

Copied to clipboard

Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang

AdaTooler-V: Adaptive Tool-Use for Images and Videos (2026.findings-acl)

Challenge:	Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale.
Approach:	They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data.
Outcome:	The proposed framework transforms user-generated content into user queries and generates responses from the policy model.

Copied to clipboard

Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang, Xiangyu Yue

Chain-of-Jailbreak Attack for Image Generation Models via Step by Step Editing (2025.findings-acl)

Challenge:	Existing models exhibit blind tool-use reasoning patterns, which significantly increases inference overhead and degrades model performance.
Approach:	They propose an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools.
Outcome:	The proposed model outperforms existing methods in visual reasoning tasks.

Copied to clipboard

Wenxuan Wang, Kuiyi Gao, Youliang Yuan, Jen-tse Huang, Qiuzhi Liu, Shuai Wang, Wenxiang Jiao, Zhaopeng Tu

Incentivizing Strong Reasoning from Weak Supervision (2026.eacl-long)

Challenge:	Text-based image generation models, such as Stable Diffusion and DALL-E 3, hold significant potential in content creation and publishing workflows . however, considerable efforts are being made to prevent the generation of harmful content, such abusive, violent, or pornographic material.
Approach:	They propose a chain-of-jailbreak method which decomposes malicious queries into multiple sub-queries and iteratively edits images based on these sub-questions.
Outcome:	The proposed method can bypass safeguards of image generation models for over 60% cases, significantly outperforms other jailbreaking methods (14%)

Copied to clipboard

Yige Yuan, Teng Xiao, Shuchang Tao, Xue Wang, Jinyang Gao, Bolin Ding, Bingbing Xu

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

Challenge:	Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on expensive high-quality demonstrations and reinforcement learning.
Approach:	They propose to incentivize reasoning abilities of large language models without expensive demonstrations and reinforcement learning.
Outcome:	The proposed model can recover 94% of the gains of expensive RL at a fraction of the cost.

Copied to clipboard

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

ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions (2024.findings-acl)

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

Copied to clipboard

Honglin Lin, Siyu Li, Guoshun Nan, Chaoyue Tang, Xueting Wang, Jingxin Xu, Rong Yankai, Zhouzhili Zhouzhili, Yutong Gao, Qimei Cui, Xiaofeng Tao

Visual Data in NLP

Challenge:	Existing approaches to image retrieval from contextual descriptions (IRCD) lag behind human performance in IRCD.
Approach:	They propose a method that relies on a doubly contextual alignment scheme for challenging IRCD.
Outcome:	The proposed method can yield comparable results with GPT-4V, despite fewer parameters.

Can’t See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs (2025.acl-long)

Copied to clipboard

Wenxuan Wang, Xiaoyuan Liu, Kuiyi Gao, Jen-tse Huang, Youliang Yuan, Pinjia He, Shuai Wang, Zhaopeng Tu

Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding (2022.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images.
Approach:	They propose a multimodal safety awareness benchmark to evaluate MLLMs across 29 safety scenarios with 1,500 carefully curated image-prompt pairs.
Outcome:	The proposed model is able to identify unsafe content and avoid over-sensitivity that can hinder helpfulness.

Copied to clipboard

Rui Cao, Yihao Wang, Yuxin Liang, Ling Gao, Jie Zheng, Jie Ren, Zheng Wang

Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning (2024.findings-naacl)

Challenge:	Unsupervised contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data.
Approach:	They propose a momentum contrastive learning model with negative sample queue for sentence embedding with a simulated model with EMA update mechanism.
Outcome:	The proposed model achieves a Spearman’s correlation of 77.27% on the semantic text similarity task and a maximum traceable distance metric.

Copied to clipboard

Jianing Wang, Chengyu Wang, Chuanqi Tan, Jun Huang, Ming Gao

BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering (2024.emnlp-main)

Challenge:	Existing studies have explored multiple aspects that affect the performance of large language models (LLMs) such as input-output mapping, extensive data resources, and the ability to train on labeled examples.
Approach:	They propose a framework that injects knowledge into LLMs during continual self-supervised pre-training and judiciously selects examples with high knowledge relevance.
Outcome:	The proposed framework outperforms baseline models and improves by more than 13% and 7% on text classification and question-answering tasks.

Copied to clipboard

Haoyu Wang, Ruirui Li, Haoming Jiang, Jinjin Tian, Zhengyang Wang, Chen Luo, Xianfeng Tang, Monica Cheng, Tuo Zhao, Jing Gao

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)

Challenge:	Retrieval-augmented Large Language Models struggle with complex inputs and noisy knowledge retrieval hindering model effectiveness.
Approach:	They propose a query generation method that integrates query generation blending with knowledge filtering to enhance retrieval-augmented LLMs.
Outcome:	The proposed approach surpasses state-of-the-art benchmarks on open-domain question answering benchmarks.

Copied to clipboard

Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen

Challenge:	Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios.
Approach:	They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance.
Outcome:	The proposed framework improves model capabilities across all domains and scales.

ProQA: Structural Prompt-based Pre-training for Unified Question Answering (2022.naacl-main)

Copied to clipboard

Wanjun Zhong, Yifan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan

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

Challenge:	Existing QA research on question answering is focused on specific question types, knowledge domains, or reasoning skills.
Approach:	They propose a unified QA paradigm that solves various tasks through a single model.
Outcome:	The proposed model improves QA-centric ability on 11 QA benchmarks.

Copied to clipboard

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

Self-Renewal Prompt Optimizing with Implicit Reasoning (2024.findings-emnlp)

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

Copied to clipboard

Zihan Liang, Ben Chen, Zhuoran Ran, Zihan Wang, Huangyu Dai, Yufei Ma, Dehong Gao, Xiaoyan Cai, Libin Yang

Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization (2023.acl-long)

Challenge:	Recent advances in NLP have been driven by the development of Large Language Models (LLMs).
Approach:	They propose a self-renewal approach to optimize LLM outputs to better align with human preferences without supervised fine-tuning.
Outcome:	The proposed approach improves outputs to better align with human preferences across LLMs and tasks without supervised fine-tuning.

Copied to clipboard

Pengcheng He, Baolin Peng, Song Wang, Yang Liu, Ruochen Xu, Hany Hassan, Yu Shi, Chenguang Zhu, Wayne Xiong, Michael Zeng, Jianfeng Gao, Xuedong Huang

ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations (2025.naacl-long)

Challenge:	Z-Code++ is a pre-trained language model optimized for abstractive text summarization.
Approach:	They propose a pre-trained language model optimized for abstractive text summarization that uses a two-phase pre-training technique to improve model's performance.
Outcome:	The proposed model outperforms the competing models on low-resource summarization tasks in zero-shot and few-shot settings.

Copied to clipboard

Yichuan Li, Xinyang Zhang, Chenwei Zhang, Mao Li, Tianyi Liu, Pei Chen, Yifan Gao, Kyumin Lee, Kaize Ding, Zhengyang Wang, Zhihan Zhang, Jingbo Shang, Xian Li, Trishul Chilimbi

Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset (2022.emnlp-main)

Challenge:	Existing benchmarks for recommendation explanation evaluation lack item diversity and user preferences data.
Approach:	They propose a model-agnostic recommendation explanation evaluation benchmark based on Amazon e-commerce categories with implicit preferences . they propose two novel automatic evaluators that enable scalable and human-preference aligned evaluation of explanations .
Outcome:	The proposed model-agnostic evaluation benchmark outperforms existing methods in a variety of domains.

Copied to clipboard

Haolin Deng, Yanan Zhang, Yangfan Zhang, Wangyang Ying, Changlong Yu, Jun Gao, Wei Wang, Xiaoling Bai, Nan Yang, Jin Ma, Xiang Chen, Tianhua Zhou

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

Challenge:	Existing EE datasets define fixed event types and design specific schemas for each of them, failing to cover diverse events emerging from the online text.
Approach:	They propose to use a sentence-level dataset to benchmark Open Event Extraction without restricting event types.
Outcome:	The proposed dataset contains more than 42,000 news titles in 34 topics collected from Chinese web pages.

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

Towards Unified Prompt Tuning for Few-shot Text Classification (2022.findings-emnlp)

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

Jianing Wang, Chengyu Wang, Fuli Luo, Chuanqi Tan, Minghui Qiu, Fei Yang, Qiuhui Shi, Songfang Huang, Ming Gao

uniblock: Scoring and Filtering Corpus with Unicode Block Information (D19-1)

Challenge:	Prompt-based fine-tuning has boosted performance of Pre-trained Language Models (PLMs) on few-shot text classification, but PLMs are unfamiliar with prompt-style expressions during pre-training, which limits the few- shot learning performance on downstream tasks.
Approach:	They propose a framework for prompt-based fine-tuning that captures prompting semantics from non-target NLP datasets and propose 'Prompt-Options-Verbalizer' for joint prompt learning across different NLP tasks.
Outcome:	Experiments show that the proposed framework outperforms state-of-the-art prompt-based fine-tuning frameworks on few-shot text classification tasks.

Copied to clipboard

Yingbo Gao, Weiyue Wang, Hermann Ney

Challenge:	Existing methods to remove sentences consisting of illegal characters are tedious and repetitive.
Approach:	They propose a statistical method to identify illegal characters in natural language processing . they use a fixed-size feature vector to generate a Gaussian mixture model for each sentence .
Outcome:	The proposed method can score sentences and filter corpus on clean corpus and improve performance.

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

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

Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework (2021.findings-emnlp)

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

Yaqing Wang, Haoda Chu, Chao Zhang, Jing Gao

Dependency Position Encoding for Relation Extraction (2022.findings-naacl)

Challenge:	Named entity recognition (NER) is a language understanding task that requires large amounts of in-domain labeled data to perform well.
Approach:	They propose a framework which learns from natural language supervision and enables the identification of never-seen entity classes without using in-domain labeled data.
Outcome:	The proposed method brings 10%, 23% and 26% improvements over baselines in few-shot learning, domain transfer and zero-shot settings respectively.

Copied to clipboard

Qiushi Guo, Xin Wang, Dehong Gao

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)

Challenge:	Existing methods to extract relation extraction from sentence are limited in focusing on leveraging dependency information.
Approach:	They propose dependency position encoding (DPE) that incorporates dependency connections and dependency types into the self-attention mechanism to distinguish the importance of different word dependencies.
Outcome:	The proposed method significantly outperforms the previous methods on SemEval 2010 Task 8, KBP37, and TACRED.

Copied to clipboard

Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

Rethinking Multi-Modal Alignment in Multi-Choice VideoQA from Feature and Sample Perspectives (2022.emnlp-main)

Challenge:	Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs.
Approach:	They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.
Outcome:	Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 .

Copied to clipboard

Shaoning Xiao, Long Chen, Kaifeng Gao, Zhao Wang, Yi Yang, Zhimeng Zhang, Jun Xiao

Do Multi-hop Readers Dream of Reasoning Chains? (D19-58)

Challenge:	Existing approaches to VideoQA focus on utilizing frame- or object-level visual representations, but they neglect visual-language interactions.
Approach:	They propose to break down video into trajectories and first leverage trajectory feature in VideoQA to enhance alignment between two modalities.
Outcome:	The proposed method outperforms all the state-of-the-art models on the NExT-QA benchmark.

Copied to clipboard

Haoyu Wang, Mo Yu, Xiaoxiao Guo, Rajarshi Das, Wenhan Xiong, Tian Gao

Question Answering

Challenge:	Existing models for multihop reasoning are limited in their performance . multi-hop reasoning requires the ability to gather information from multiple passages .
Approach:	They propose a method that provides the full reasoning chain of multiple passages instead of just one final passage where the answer appears.
Outcome:	The proposed model improves on existing models by providing the full reasoning chain of multiple passages instead of just one final passage where the answer appears.

Non-parallel Accent Transfer based on Fine-grained Controllable Accent Modelling (2023.findings-emnlp)

Copied to clipboard

Linqin Wang, Zhengtao Yu, Yuanzhang Yang, Shengxiang Gao, Cunli Mao, Yuxin Huang

NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning (2026.acl-long)

Challenge:	Existing accent transfer methods rely on parallel data or speech recognition models.
Approach:	They propose to use mutual information learning to disentangle accent features and control the accent of the generated speech during the inference time.
Outcome:	The proposed framework achieves superior performance to baseline models in accentedness and audio quality.

Copied to clipboard

Yanyi Su, Hongshuai Wang, Zhifeng Gao, Jun Cheng

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting (2024.emnlp-main)

Challenge:	Existing representation methods fail to fully capture olfactory pathway . current approaches focus on isolated segments of the olefactory pathways .
Approach:	They propose a representation learning framework that aligns molecular structure, receptor sequence, and natural language description.
Outcome:	The proposed framework achieves state-of-the-art and excellent zero-shot generalization . it decouples contributions of molecular structure, receptor sequence, and natural language description .

Copied to clipboard

Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, Yanfu Zhang

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation (2021.tacl-1)

Challenge:	Pretrained large language models excel in a variety of natural language processing tasks . however, they pose significant security risks due to their tendency to memorize training data .
Approach:	They propose a method to estimate LLM memorization using dynamic, prefix-dependent soft prompts.
Outcome:	The proposed method can achieve maximum relative improvement of 135.3% and 39.8% over baseline compared to state-of-the-art methods.

Copied to clipboard

Xiaozhi Wang, Tianyu Gao, Zhaocheng Zhu, Zhengyan Zhang, Zhiyuan Liu, Juanzi Li, Jian Tang

Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)

Challenge:	Existing language representation models (PLMs) cannot capture factual knowledge from text.
Approach:	They propose a unified model for Knowledge Embedding and Pre-trained LanguagERepresentation which integrates factual knowledge into PLMs and produces effective text-enhanced KE with the strong PLM.
Outcome:	The proposed model improves on existing pre-trained language representation models and improves their performance on various NLP tasks.

Copied to clipboard

Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Wang, Xiaodan Zhu

Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling (2026.acl-long)

Challenge:	Existing methods for AVE are limited on rare attributes due to poor generalization ability.
Approach:	They propose to leverage pretraining and transfer learning to address weaknesses in existing methods.
Outcome:	The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources.

Copied to clipboard

Yujie Chen, Tailai Chen, Yifeng Gao, Zoe Wanying He, Yijue Xu, Shaobo Wang, Linfeng Zhang

Listen, Decipher and Sign: Toward Unsupervised Speech-to-Sign Language Recognition (2023.findings-acl)

Challenge:	Existing methods to reduce sequence length rely on heuristics that break compatibility with hardware-efficient kernels like FlashAttention.
Approach:	They propose a method that selectively halts stabilized tokens by monitoring layer-wise update dynamics of the self-attention mechanism.
Outcome:	The proposed method can reduce prefill complexity while preserving model accuracy and hardware efficiency.

Copied to clipboard

Liming Wang, Junrui Ni, Heting Gao, Jialu Li, Kai Chieh Chang, Xulin Fan, Junkai Wu, Mark Hasegawa-Johnson, Chang Yoo

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

Challenge:	Existing supervised sign language recognition systems rely on well-annotated data . instead, an unsupervised speech-to-sign language recognition system learns to translate between spoken and sign languages by observing only non-parallel speech and sign-language corpora.
Approach:	They propose an unsupervised speech-to-sign language recognition system that can translate between spoken and sign languages by observing only non-parallel speech and sign-language corpora.
Outcome:	The proposed approach outperforms baseline models on sign language corpora by 50% . the proposed approach is available at https://github.com/cactuswiththoughts/UnsupSpeech2Sign.git .

Copied to clipboard

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

SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)

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

Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke

Challenge:	Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis.
Approach:	They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis.
Outcome:	SciAssess evaluates 11 LLMs on multiple tasks across scientific fields.

Copied to clipboard

Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu

DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs (2026.acl-long)

Challenge:	Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer.
Approach:	They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions.
Outcome:	The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios.

Copied to clipboard

Bo Zhang, Jiawei Zhang, Cong Gao, Bingxu Han, Minghao Hu, Jun Zhang, Yunbo Cao, Zhunchen Luo, Wen Yao, Guotong Geng, Zhong Wang

MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)

Challenge:	Existing methods for calibration of large reasoning models (LRMs) focus on clean inputs, leaving noise unexplored.
Approach:	They propose a confidence calibration framework for character-level noisy inputs that extracts uncertainty signals from both the empirical answer distribution and the model’s predictive distribution and integrates them via a learned calibrator.
Outcome:	Experiments on multiple mathematical reasoning benchmarks show that DisCal outperforms existing calibration methods under noisy inputs, reducing expected calibration error (ECE) by up to 39.21% and improving Area Under the Receiver Operating Characteristic Curve (AUROC) by 31.44%.

Copied to clipboard

Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Yongbin Li, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Hamid Alinejad-Rokny, Xiaobo Xia, Jingkuan Song, Fei Huang

Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding (2026.acl-long)

Challenge:	a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling .
Approach:	They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution.
Outcome:	The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data.

Copied to clipboard

Yuhang Zhou, Mingrui Zhang, Ke Li, Mingyi Wang, Qiao Liu, Qifei Wang, Jiayi Liu, Fei Liu, Serena Li, Weiwei LI, Mingze Gao, Abhishek Kumar, Xiangjun Fan, Zhuokai Zhao, Lizhu Zhang

GODBench: A Benchmark for Multimodal Large Language Models in Video Comment Art (2025.acl-long)

Challenge:	Large language models (LLMs) have shown promise on understanding and reasoning over tables, but current approaches remain limited.
Approach:	They propose a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering.
Outcome:	The proposed framework decomposes table reasoning into three specialized roles: planning, coding, and answering.

Copied to clipboard

Yiming Lei, Chenkai Zhang, Zeming Liu, Haitao Leng, ShaoGuo Liu, Tingting Gao, Qingjie Liu, Yunhong Wang

Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model (2023.findings-acl)

Challenge:	Existing benchmarks for video comment art are constrained by their limited modalities and insufficient categories, hindering creativity in video-based comment art creation.
Approach:	They propose a benchmark that integrates video and text modalities to evaluate MLLMs’ abilities to compose video Comment art.
Outcome:	The proposed framework integrates video and text modalities to evaluate MLLMs’ abilities to compose video comment art.

Copied to clipboard

Xiao Wang, Weikang Zhou, Qi Zhang, Jie Zhou, SongYang Gao, Junzhe Wang, Menghan Zhang, Xiang Gao, Yun Wen Chen, Tao Gui

2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition (2023.findings-emnlp)

Challenge:	Pretrained language models have achieved remarkable success in various natural language processing tasks.
Approach:	They propose to use end-task knowledge to select a tiny subset of pretraining corpus to influence performance.
Outcome:	The proposed model outperforms pretrained models on eight datasets covering four domains with 0.45% of the data and a three-orders-of-magnitude lower computational cost.

Copied to clipboard

Jiasheng Zhang, Xikai Liu, Xinyi Lai, Yan Gao, Shusen Wang, Yao Hu, Yiqing Lin

Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale (2024.emnlp-main)

Challenge:	Named Entity Recognition (NER) tasks are a fundamental task of natural language processing (NLP).
Approach:	They propose a text-to-text framework for Few-Shot Named Entity Recognition (NER) that employs instruction finetuning and auxiliary tasks to enhance the model's understanding of entity types in the overall semantic context of a sentence.
Outcome:	The proposed framework outperforms existing Few-Shot NER methods and remains competitive with state-of-the-art NER algorithms.

Copied to clipboard

Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Chen, Xidong Wang, Zhenyang Cai, Ke Ji, Xiang Wan, Benyou Wang

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Multimodal large language models (MLLMs) lack visual knowledge in medical applications due to data privacy concerns and high annotation costs.
Approach:	They refined medical image-text pairs from PubMed and employed MLLMs (GPT-4V) to denoise and reformat the data.
Outcome:	The proposed model significantly improves the MMMU Health & Medicine track and shows that it can be used in multimodal scenarios.

Copied to clipboard

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages (2025.findings-naacl)

Challenge:	Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context.
Approach:	They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration.
Outcome:	Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness.

Copied to clipboard

Xuhan Huang, Qingning Shen, Yan Hu, Anningzhe Gao, Benyou Wang

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated strong performance across various natural language processing tasks, but their proficiency in mathematical reasoning remains a key challenge.
Approach:	They propose a process-oriented framework to evaluate LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth.
Outcome:	The proposed framework evaluates LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth.

Copied to clipboard

Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Tianyu Liu, Baobao Chang

IHEval: Evaluating Language Models on Following the Instruction Hierarchy (2025.naacl-long)

Challenge:	Existing mathematical verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions.
Approach:	They propose a natural language feedback-enhanced verifier that can validate the correctness of response generated by policy models by constructing automatically generated training data and a two-stage training paradigm.
Outcome:	The proposed verifier significantly improves in verification and reinforcement learning and alleviates data-demanding problems of the reward model.

Copied to clipboard

Zhihan Zhang, Shiyang Li, Zixuan Zhang, Xin Liu, Haoming Jiang, Xianfeng Tang, Yifan Gao, Zheng Li, Haodong Wang, Zhaoxuan Tan, Yichuan Li, Qingyu Yin, Bing Yin, Meng Jiang

UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning (2021.acl-long)

Challenge:	Instruction-tuned language models (LMs) are increasingly deployed as interactive services across various applications.
Approach:	They propose a benchmark to evaluate models' ability to follow the instruction hierarchy by comparing their models to a set of benchmarks.
Outcome:	The proposed benchmark covers 3,538 examples across nine tasks covering cases where instructions in different priorities either align or conflict.

Copied to clipboard

Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, Haifeng Wang

Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation (2025.findings-naacl)

Challenge:	Existing pre-training methods focus on single-modal tasks or multi-modal ones . large-scale pre- training has drawn much attention in both the community of Compute Vision (CV) and Natural Language Processing (NLP).
Approach:	They propose a UNIfied-MOdal pre-training architecture which can adapt to both single-modal and multi-modal understanding and generation tasks.
Outcome:	The proposed model can learn more generalizable representations with rich non-paired single-modal data.

Copied to clipboard

Yu Wang, Jiaxin Zhang, Xiang Gao, Wendi Cui, Peng Li, Kamalika Das

Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) often experience “contextual hallucination” where they prioritize self-generated content over input context, leading to a disregard for pertinent details.
Approach:	They propose a method that dynamically adjusts attention maps to enhance contextual relevance by using a trained classifier to identify attention maps likely to induce hallucinations.
Outcome:	The proposed approach reduces hallucinations across open-source models on summarization and open-book QA tasks.

Copied to clipboard

Chen Cai, Zheng Wang, Jianjun Gao, Wenyang Liu, Ye Lu, Runzhong Zhang, Kim-Hui Yap

Under the Shadow of Babel: How Language Shapes Reasoning in LLMs (2025.findings-emnlp)

Challenge:	Existing VideoQA models struggle to adapt to new questions or tasks posed by newly available content.
Approach:	They propose a continual learning framework that fine-tunes a large language model for a sequence of tasks and integrates specific question constraint prompting, knowledge acquisition prompting and visual temporal awareness prompting.
Outcome:	The proposed model achieves 55.14% accuracy on both NExT-QA and DramaQA datasets and 71.24% accuracy for DramaQA.

Copied to clipboard

Chenxi Wang, Yixuan Zhang, Lang Gao, Zixiang Xu, Zirui Song, Yanbo Wang, Xiuying Chen

Linguistics & Cognitive NLP

Challenge:	linguistic relativity suggests that the structure of language shapes cognitive patterns . large language models internalize the habitual logical structures embedded in different languages, authors say .
Approach:	a study introduces a bilingual dataset for causal reasoning in Chinese and English.
Outcome:	a new study shows that large language models internalize reasoning biases shaped by language . the model internalizes language-specific preferences and rigidly applies them to atypical inputs, the study shows .

Reference Attack: A New Cross-Modal Jailbreaking Attack against Multimodal Large Language Models (2026.acl-long)

Copied to clipboard

Yulong Wang, Yifei Fu, Jiayi Gao

Document Segmentation Matters for Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have raised significant safety concerns about generated content, drawing attention from both academia and industry.
Approach:	They propose a reference-guided cross-modal jailbreak method that enhances existing prompt-to-image injection attacks by exploiting MLLMs’ semantic reconstruction capabilities.
Outcome:	The proposed method achieves an attack success rate of over 93% on leading MLLMs including ChatGPT, Gemini, Claude, and the widely used open-source LLaMA model.

Copied to clipboard

Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, Guoshan Lu, Gang Chen, Fanchao Qi, Maosong Sun

Syntactic Text Processing

Challenge:	Existing rule-based chunking methods lead to suboptimal splits, where overly large chunks introduce irrelevant information and small chunks lack semantic coherence.
Approach:	They propose a method that leverages document summaries as pseudo-instructions to guide chunking by computing semantic similarity between sentences and the summary.
Outcome:	Experiments on multiple open-domain question-answering benchmarks show that PIC significantly improves retrieval accuracy (Hits@k) and end-to-end QA performance (Exact Match) without any additional training.

UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations (2025.acl-long)

Copied to clipboard

Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, Bing Yin, Meng Jiang

Depth Growing for Neural Machine Translation (P19-1)

Challenge:	Existing conversational search systems are usually built with two different models . this separation restricts the system from leveraging the model's intrinsic knowledge simultaneously . Existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses.
Approach:	They propose to unify dense retrieval and response generation for large language models in conversation by fine-tuning and mitigating data discrepancy.
Outcome:	The proposed model can outperform existing models on five conversational search datasets and reduce inconsistency risks while mitigating data discrepancy.

Copied to clipboard

Lijun Wu, Yiren Wang, Yingce Xia, Fei Tian, Fei Gao, Tao Qin, Jianhuang Lai, Tie-Yan Liu

AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Challenge:	Neural machine translation models with tens and even more than a hundred blocks have shown effectiveness in image recognition.
Approach:	They propose a two-stage approach with three specially designed components to construct deeper NMT models.
Outcome:	The proposed approach improves on WMT14 EnglishGerman and EnglishFrench translation tasks.

Copied to clipboard

Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang

CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback (2025.findings-emnlp)

Challenge:	Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach:	They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome:	The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.

Copied to clipboard

Yifan Wang, Shen Gao, Jiabao Fang, Rui Yan, Billy Chiu, Shuo Shang

UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation (2025.acl-long)

Challenge:	Existing Sequential Recommendation Systems (SRS) rely on collaborative filtering signals and fail to capture real-time user preferences.
Approach:	They propose a framework that integrates the long-term preference modeling of SRS with the real-time preference elicitation of CRS.
Outcome:	The proposed framework integrates the long-term preference modeling of SRS with the real-time preference elicitation of CRS.

Copied to clipboard

Jun Gao, Qi Lv, Zili Wang, Tianxiang Wu, Ziqiang Cao, Wenjie Li

Error Comparison Optimization for Large Language Models on Aspect-Based Sentiment Analysis (2025.acl-long)

Challenge:	Existing methods to improve reasoning abilities of Large Language Models (LLMs) have limitations due to excessive growth in context length, causing large hardware burden.
Approach:	They propose a novel Unified ICL framework that unifies demonstration compression, demonstration selection, and final response generation.
Outcome:	The proposed framework unifies demonstration compression, demonstration selection, and final response generation.

Copied to clipboard

Qianlong Wang, Keyang Ding, Hengxin Gao, Hui Wang, Ruifeng Xu

ODDA: An OODA-Driven Diverse Data Augmentation Framework for Low-Resource Relation Extraction (2025.findings-acl)

Challenge:	Existing methods for aspect-based sentiment analysis (ABSA) only compare current predictions and labels on each sample, yet fail to perceive and understand its error outputs from different degrees.
Approach:	They propose a framework that can perceive and understand the degree of errors by learning from comparative error pairs.
Outcome:	The proposed framework exceeds baselines and achieves the desired performance.

Copied to clipboard

Yijie Zhong, Yunfan Gao, Xiaolian Zhang, Haofen Wang

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

Challenge:	Existing methods for low-resource relation extraction (LRE) lack diversity, leading to suboptimal performance.
Approach:	They propose to use large language models to augment relation extraction models by observing the RE model's behavior and replacing schema constraints with attribute constraints.
Outcome:	Experiments on three widely-used benchmarks show that the proposed method outperforms state-of-the-art methods while maintaining enhanced model stability.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction (2021.acl-long)

Challenge:	Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach:	They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome:	The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.

Copied to clipboard

Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos Santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Coarse-to-fine Few-shot Learning for Named Entity Recognition (2023.findings-acl)

Challenge:	Open-domain question answering is a task to answer questions using passages with diverse topics.
Approach:	They propose a model that aggregates evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions.
Outcome:	The proposed model achieves state-of-the-art performance on AmbigQA dataset and shows competitive performance on NQ-Open and TriviaQA.

Copied to clipboard

Ruotian Ma, Zhang Lin, Xuanting Chen, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yun Wen Chen

HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification (2024.eacl-long)

Challenge:	Existing few-shot NER solutions do not consider sub-class discrimination and various granularity of new classes during coarse training.
Approach:	They propose a method that uses a cluster-based prototype loss to learn group-wise discriminative representations of coarse-grained classes and a mixture prototype loss for learning the representations.
Outcome:	The proposed method shows superior performance over baseline methods on in-domain and cross-domain settings with various target granularity.

Copied to clipboard

Vidit Jain, Mukund Rungta, Yuchen Zhuang, Yue Yu, Zeyu Wang, Mu Gao, Jeffrey Skolnick, Chao Zhang

Rectified Sparse Attention for Efficient Long-Sequence Generation (2026.findings-acl)

Challenge:	Hierarchical text classification is a complex subtask under multi-label text classification . the relevance of document sections can vary based on the hierarchy level, necessitating a dynamic document representation.
Approach:	They propose a text-generation-based framework that uses language models to encode dynamic text representations.
Outcome:	The proposed framework surpasses existing methods while handling data and mitigating class imbalance.

Copied to clipboard

Yutao Sun, Tianzhu Ye, Li Dong, Yuqing Xia, Jian Chen, Yizhao Gao, Shijie Cao, Jianyong Wang, Furu Wei

RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction (2025.findings-emnlp)

Challenge:	Recent sparse decoding methods improve efficiency but suffer from KV cache misalignment, resulting in performance degradation.
Approach:	They propose a method that combines block-sparse attention with periodic dense rectification to bound error accumulation and preserve alignment with the pretraining distribution.
Outcome:	Experiments on math reasoning, language modeling, and retrieval tasks show that ReSA achieves near-lossless generation quality with significantly improved efficiency.

Copied to clipboard

Jinbo Su, Lingzhe Gao, Wei Li, Shihao Liu, Haojie Lei, Xinyi Wang, Yuanzhao Guo, Ke Wang, Daiting Shi, Dawei Yin

Benchmarking and Learning Real-World Customer Service Dialogue (2026.acl-long)

Challenge:	Large language models (LLMs) exhibit remarkable capabilities across many tasks, but face critical challenges in the CSC scenario: (1) poor generalization to rare entities in open-domain searches; and (2) failure to adapt to temporal entity variations due to static parameters, resulting in serious over-correction issues.
Approach:	They propose a Chinese Spelling Check system with RAG and multi-task learning that integrates dynamic knowledge retrieval and entity-centric RAG to address rare entities.
Outcome:	The proposed system outperforms existing baselines in the CSC task and achieves a maximum improvement of +9.92% on the search scenario benchmark and +3.2% on the general-domain dataset.

Copied to clipboard

Tianhong Gao, Jundong Shen, Jiapeng Wang, Bei Shi, Ying Ju, Junfeng Yao, Huiyu Yu

SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue (2026.findings-acl)

Challenge:	Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) focus on task completion and tool correctness.
Approach:	They propose a benchmark-to-optimization loop that bridges offline gains to deployment . they propose OlaMind, which distills reusable reasoning patterns from expert dialogues .
Outcome:	The proposed benchmark surpasses GPT-5.2 and Gemini 3 Pro on OlaBench . it delivers an average +23.67% issue resolution and -6.6% human transfer rate versus baseline .

Copied to clipboard

Yuqin Dai, Ning Gao, Wei Zhang, Jie Wang, null Luozichen, Ruiyuan Wu, Jinpeng Wang, Chaozheng Wang

Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding (2026.acl-long)

Challenge:	Large Language Models have demonstrated remarkable capabilities in open-domain dialogues, but their performance in service dialogues remains suboptimal.
Approach:	They propose a framework that enables agents to learn effective strategies without large-scale human annotations.
Outcome:	The proposed framework decouples user modeling into two components that provide adaptive training scenarios rather than acting as an unfair adversary.

Copied to clipboard

Wenqing Hou, Hongkui Tu, Ye Wang, Yue Zhang, Yuying Liu, Dong Zhu, Liqun Gao, Bin Zhou

Label-Aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition (N18-1)

Challenge:	Existing methods for identifying harmful memes rely on modal alignment or black-box classifiers . BPDMoE-Hate provides visual explanations for viewpoint selection and hierarchical structuring .
Approach:	They propose a framework that conceptualizes harmful meme detection as a process of "viewpoint decoupling and hierarchical fusion" they propose BPDMoE-Hate, which generates adversarial binary perspectives via VLMs and incorporates an adaptive viewpoint gating to facilitate viewpoint selection.
Outcome:	The proposed framework surpasses existing methods in performance and provides visual explanations for viewpoint selection and hierarchical structuring.

Copied to clipboard

Zhenghui Wang, Yanru Qu, Liheng Chen, Jian Shen, Weinan Zhang, Shaodian Zhang, Yimei Gao, Gen Gu, Ken Chen, Yong Yu

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models (2026.acl-long)

Challenge:	NER is a fundamental problem for medical text mining because of the difference of specialties and cost of human annotation.
Approach:	They propose a label-aware double transfer learning framework for medical NER from electronic medical records.
Outcome:	The proposed framework improves accuracy over strong baselines on 12 cross-specialty NER tasks.

Copied to clipboard

Zirui Song, Qian Jiang, Mingxuan Cui, Mingzhe Li, Lang Gao, Zeyu Zhang, Zixiang Xu, Yanbo Wang, Guangxian Ouyang, Zhenhao Chen, Xiuying Chen

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

Challenge:	a recent study evaluated large audio-language models against jailbreak attacks . a new benchmark is being developed to evaluate LAM safety against jailbreaking attacks based on temporal and semantic nature of speech .
Approach:	They propose a benchmark to evaluate LAM jailbreak vulnerabilities in adversarial audio prompts . they use a dataset of 1,495 adversarials to evaluate their performance .
Outcome:	The proposed benchmark evaluates state-of-the-art LAMs against jailbreak attacks . it demonstrates that even small, semantically preserved perturbations can reduce safety .

Copied to clipboard

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

DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models (2023.emnlp-main)

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

Copied to clipboard

Chengcheng Han, Xiaowei Du, Che Zhang, Yixin Lian, Xiang Li, Ming Gao, Baoyuan Wang

Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems (2021.naacl-demos)

Challenge:	Chain-of-Thought prompting has improved the reasoning capabilities of Large Language Models (LLMs) but it is ineffective or detrimental to the performance on reasoning tasks in Smaller Language Model (SLMs) with less than 10 billion parameters.
Approach:	They propose a Dialogue-guided Chain-of-Thought method to improve the reasoning capabilities of Large Language Models (LLMs) by generating intermediate reasoning steps in a dialogue format to guide the model to the final answer.
Outcome:	The proposed method can achieve significant performance gains over state-of-the-art competitors on four arithmetic reasoning datasets.

Copied to clipboard

Anish Acharya, Suranjit Adhikari, Sanchit Agarwal, Vincent Auvray, Nehal Belgamwar, Arijit Biswas, Shubhra Chandra, Tagyoung Chung, Maryam Fazel-Zarandi, Raefer Gabriel, Shuyang Gao, Rahul Goel, Dilek Hakkani-Tur, Jan Jezabek, Abhay Jha, Jiun-Yu Kao, Prakash Krishnan, Peter Ku, Anuj Goyal, Chien-Wei Lin, Qing Liu, Arindam Mandal, Angeliki Metallinou, Vishal Naik, Yi Pan, Shachi Paul, Vittorio Perera, Abhishek Sethi, Minmin Shen, Nikko Strom, Eddie Wang

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

Challenge:	Traditional goal-oriented dialogue systems require annotations which are hard to obtain for every new domain, limiting scalability.
Approach:	They propose a data-driven approach to building goal-oriented dialogue systems . they use a seed dialogue simulator to generate annotated conversations instead of collecting annotations .
Outcome:	The proposed system improves turn-level action signature prediction accuracy by 50% . the system is scalable, extensible and data efficient .

Copied to clipboard

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

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

Towards a Better Understanding of Label Smoothing in Neural Machine Translation (2020.aacl-main)

Copied to clipboard

Yingbo Gao, Weiyue Wang, Christian Herold, Zijian Yang, Hermann Ney

Predicting and Using Target Length in Neural Machine Translation (2020.aacl-main)

Challenge:	In recent years, Neural Network (NN) models bring steady and concrete improvements on the task of Machine Translation (MT).
Approach:	They propose to penalize over-confident outputs and regularize the model so that its outputs do not diverge too much from some prior distribution.
Outcome:	The proposed method is well-motivated and can improve the performance of strong neural machine translation systems.

Copied to clipboard

Zijian Yang, Yingbo Gao, Weiyue Wang, Hermann Ney

McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models (2025.findings-acl)

Challenge:	Current NMT systems do not model the length of the output explicitly . length normalization is a common technique used in the beam search of NMT to enable a fair comparison of partial hypotheses with different lengths.
Approach:	They propose to use length prediction as an auxiliary task to obtain length information from the encoder.
Outcome:	The proposed sub-network improves over the baseline system and the predicted length can be used as an alternative to length normalization during decoding.

Copied to clipboard

Tian Lan, Xiangdong Su, Xu Liu, Ruirui Wang, Ke Chang, Jiang Li, Guanglai Gao

NICE: Neural Image Commenting with Empathy (2021.findings-emnlp)

Challenge:	Existing datasets on bias evaluation for large language models focus on English and North American culture and are limited to one task.
Approach:	They propose to evaluate Chinese language models' biases from multiple perspectives using a multi-task Chinese Bias Evaluation Benchmark.
Outcome:	The proposed model covers 12, 82 subcategories and 5 evaluation tasks covering a wide range of categories and content diversity.

Copied to clipboard

Kezhen Chen, Qiuyuan Huang, Daniel McDuff, Xiang Gao, Hamid Palangi, Jianfeng Wang, Kenneth Forbus, Jianfeng Gao

Visual Data in NLP

Challenge:	Emotion and empathy are examples of human qualities lacking in many human-machine interactions.
Approach:	They propose to generate images with human-generated comments with enhanced emotion and empathy while minimizing inappropriate or offensive outputs.
Outcome:	The proposed model generates more human-like and engaging image comments on two images with human-generated comments and human annotations while minimizing inappropriate or offensive outputs.

Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)

Copied to clipboard

Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji

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

Challenge:	Despite of significant achievements in improving instruction-following capabilities of large language models, the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.
Approach:	They construct multi-turn instruction with 1.1K high-quality multi-turned conversations using the human-in-the-loop approach and examine their capabilities.
Outcome:	The proposed model shows that it is difficult to integrate multiple turns and balance competing objectives when instructions intersect or conflict.

Copied to clipboard

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

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.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

Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai

Evaluating Factuality in Cross-lingual Summarization (2023.findings-acl)

Challenge:	RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach:	They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome:	The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.

Copied to clipboard

Mingqi Gao, Wenqing Wang, Xiaojun Wan, Yuemei Xu

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Challenge:	Existing evaluation metrics for monolingual summarization require translation to evaluate the factuality of cross-lingual summmarization.
Approach:	They propose to analyze cross-lingual factuality by collecting annotations and generated summaries from models at summary level and sentence level.
Outcome:	The proposed dataset shows that over 50% of generated summaries contain factual errors with different characteristics from monolingual summarization.

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuning (2025.findings-emnlp)

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Jizhi Zhang, Chongming Gao, Wentao Shi, Xin Chen, Jingang Wang, Xunliang Cai, Fuli Feng

Challenge:	a recent study highlights unpaired feedback as a key challenge for long-term LLM-based recommenders . unpaired user feedback is crucial for improving LLMs in dynamic user environments, authors say .
Approach:	They propose a framework that incorporates unpaired feedback into LLMs to improve long-term recommendation performance.
Outcome:	The proposed framework improves long-term recommendation performance by incorporating unpaired feedback without requiring paired supervision.

Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing (2025.naacl-long)

Copied to clipboard

Huanqian Wang, Yang Yue, Rui Lu, Jingxin Shi, Andrew Zhao, Shenzhi Wang, Shiji Song, Gao Huang

Challenge:	Current approaches for detoxification or preventing jailbreaking involve fine-tuning billions of parameters through gradient descent with substantial computational cost.
Approach:	They propose to use supervised fine-tuning and Reinforcement Learning from human feedback to modify LLMs' behavior by directly editing a small subset of parameters.
Outcome:	Experiments show that editing a small subset of parameters can modulate specific behaviors of LLMs, such as detoxification and resistance to jailbreak, with only inference-level computational resources.

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning (2025.acl-long)

Copied to clipboard

Jin Jiang, Yuchen Yan, Yang Liu, Jianing Wang, Shuai Peng, Xunliang Cai, Yixin Cao, Mengdi Zhang, Liangcai Gao

Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)

Challenge:	LogicPro is a data synthesis method that uses LeetCode-style algorithm problems and their corresponding Program solutions to generate complex logic data.
Approach:	They propose a new method which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize complex logic data in text format.
Outcome:	The proposed method outperforms existing models for BBH27, LogicBench, DROP, AR-LSAT, and GSM8K, and a wide range of reasoning datasets.

Copied to clipboard

Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang

LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation? (2024.naacl-long)

Challenge:	Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains.
Approach:	They propose several strategies for deploying RAG that balance performance and efficiency.
Outcome:	The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy.

Copied to clipboard

Yuchi Wang, Shuhuai Ren, Rundong Gao, Linli Yao, Qingyan Guo, Kaikai An, Jianhong Bai, Xu Sun

Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study (2025.naacl-long)

Challenge:	Existing models for text-to-image generation have been underperforming in image-totext generation tasks.
Approach:	They propose a framework that uses a split BERT to create a dedicated latent space for captions and integrates a regularization module to manage varying text lengths.
Outcome:	The proposed framework achieves state-of-the-art performance on the MS COCO dataset with 38.2 BLEU@4 and 126.2 CIDEr .

Copied to clipboard

Menglong Cui, Pengzhi Gao, Wei Liu, Jian Luan, Bin Wang

Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains (2020.emnlp-main)

Challenge:	Large language models (LLMs) have shown continuously improving multilingual capabilities.
Approach:	They evaluate the ability of open LLMs to handle multilingual machine translation tasks using a parallel-first monolingual-second data mixing strategy.
Outcome:	The proposed model outperforms state-of-the-art models and achieves competitive performance with Google Translate and GPT-4-turbo.

Copied to clipboard

Weijie Yu, Chen Xu, Jun Xu, Liang Pang, Xiaopeng Gao, Xiaozhao Wang, Ji-Rong Wen

Representation Learning

Challenge:	Asymmetrical text matching is a fundamental problem in information retrieval and natural language processing.
Approach:	They propose a method that regularizes features vectors projected from different domains . WD-Match can be used to improve different text matching methods .
Outcome:	The proposed method outperforms existing methods and benchmarks on four datasets.

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

Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)

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

Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization (2025.naacl-long)

Challenge:	Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning.
Approach:	They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning.
Outcome:	The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness.

Copied to clipboard

Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin, Ming Gao

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Challenge:	Existing approaches to optimize RAG generators fail to align with RAG requirements thoroughly.
Approach:	They propose a method for optimizing the RAG generator from multiple preference perspectives to align with RAG requirements comprehensively.
Outcome:	The proposed method improves the performance of RAG generators by incorporating retrieved documents into the prompt.

Copied to clipboard

Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models (2026.acl-long)

Challenge:	Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach:	They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome:	The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.

Copied to clipboard

Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Bowen Yu, Fei Huang, Junyang Lin

Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)

Challenge:	Recent studies observe a phenomenon where reward models achieve high accuracy on static datasets but fail to generalize effectively during RLHF.
Approach:	They propose a method that combines rationale consistency with outcome accuracy to improve performance on RM-Bench and JudgeBench.
Outcome:	The proposed method surpasses baselines on RM-Bench and JudgeBench by an average of 5% and improves creative writing tasks by 7%.

Copied to clipboard

Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo

Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses (2026.acl-long)

Challenge:	Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity.
Approach:	They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability.
Outcome:	The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability.

Copied to clipboard

Chongyuan Dai, Yaling Shen, Zihan Gao, Jia Li, Yishun Jiang, Yaxiong Wang, Liu Liu, Zongyuan Ge, Jinpeng Hu

Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other (2024.findings-naacl)

Challenge:	Culture is a fundamental determinant of human affective processing and affective perceptions are often limited by declarative knowledge or established societal customs.
Approach:	They propose a multimodal benchmark that leverages LLM-generated provisional labels to isolate cross-cultural emotional distinctions.
Outcome:	The proposed benchmark captures cross-cultural emotional distinctions and derives reliable ground-truth annotations through human evaluation.

Copied to clipboard

Yifei Gao, Jie Ou, Lei Wang, Yuting Xiao, Xiangzhiyuan Xiangzhiyuan, Ruiting Dai, Jun Cheng

Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning (2025.coling-main)

Challenge:	Emergent Large Language Models (LLMs) use extraordinary performance and powerful deduction capacity to discern from traditional language models.
Approach:	They propose a method that uses weights to compensate quantization error and learnable singular value incremental (LSI) LSI is a technique that helps weights compensate each other conditioned on activation.
Outcome:	The proposed method achieves state-of-the-art performance in diverse quantization settings, no matter in weight-only, weight-activation or extremely low bit scenarios.

Copied to clipboard

Cunda Wang, Weihua Wang, Qiuyu Liang, Feilong Bao, Guanglai Gao

Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise (2025.emnlp-main)

Challenge:	Entity alignment (EA) aims to match identical entities across knowledge graphs (KGs) Graph neural network-based entity alignment methods have achieved promising results in Euclidean space, but KGs often contain complex local and hierarchical structures, which are hard to represent in a single space.
Approach:	They propose a method which unifies dual-space embedding to preserve the intrinsic structure of KGs.
Outcome:	The proposed method achieves state-of-the-art in structure-based EA on benchmark datasets.

Copied to clipboard

Hanyin Wang, Chufan Gao, Qiping Xu, Bolun Liu, Guleid Hussein, Hariprasad Reddy Korsapati, Mohamad El Labban, Kingsley Iheasirim, Mohamed Hassan, Gokhan Anil, Brian Bartlett, Jimeng Sun

F²Bench: An Open-ended Fairness Evaluation Benchmark for LLMs with Factuality Considerations (2025.emnlp-main)

Challenge:	Currently, no automated, scalable method exists to evaluate the quality of LLM-generated clinical notes, leaving manual evaluation the gold standard.
Approach:	They propose a framework for training PRMs to deliver step-level reward signals for LLM-generated clinical notes.
Outcome:	The proposed framework outperforms reasoning and non-reasoning models on key evaluations and selects physician-preferred clinical notes with 56.2% accuracy.

Copied to clipboard

Tian Lan, Jiang Li, Yemin Wang, Xu Liu, Xiangdong Su, Guanglai Gao

Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge (2022.emnlp-main)

Challenge:	Existing fairness evaluation benchmarks for large language models rely on closed-ended evaluation formats that overlook factuality considerations rooted in historical, social, physiological, and cultural contexts.
Approach:	They propose an open-ended fairness evaluation benchmark for large language models . they incorporate factuality considerations and multi-turn reasoning into the benchmark .
Outcome:	The proposed benchmark incorporates factual grounding and text generation to better reflect the complexities of real-world model usage.

Copied to clipboard

Longxu Dou, Yan Gao, Xuqi Liu, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Min-Yen Kan, Jian-Guang Lou

Programming Languages in NLP

Challenge:	Existing approaches to text-to-SQL require domain knowledge to parse expert questions into SQL queries.
Approach:	They propose a framework to leverage domain knowledge during parsing by building a new benchmark KnowSQL with domain-specific questions.
Outcome:	The proposed framework improves the performance of the proposed benchmark by 28.2%.

AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction (2026.findings-acl)

Copied to clipboard

Pollawat Hongwimol, Haoning Shang, Chutong Wang, Zhichao Wan, Yi Gao, Yuanming Li, Lin Gui, Wenhao Sun, Cheng Yu

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective (2022.emnlp-main)

Challenge:	Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain.
Approach:	They propose a multi-agent Large Language Model framework that constructs a Product-attribute Knowledge Graph from multimodal product content.
Outcome:	The proposed framework achieves 0.953 WKE for product types, 0.724 WKEs for attribute keys, and 0.531 edge-level accuracy for value assertions after canonicalization on a large real-world marketplace catalog dataset from Lazada (Alibaba).

Copied to clipboard

Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, Tetsuya Sakai

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models (2025.acl-long)

Challenge:	Existing approaches to zero-shot learning are format-agnostic and can address new learning tasks without additional training.
Approach:	They propose a new paradigm for zero-shot learning that is format agnostic and compatible with any format and applicable to a list of language tasks.
Outcome:	The proposed model shows state-of-the-art performance on several benchmarks and produces satisfactory results on tasks such as text classification and commonsense reasoning.

Copied to clipboard

Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang

Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues (2026.findings-acl)

Challenge:	Existing methods for offsite-tuning of large language models require high computational costs and lack theoretical analysis.
Approach:	They propose an offsite-tuning approach that selectively applies compression techniques such as rank compression and channel pruning to preserve the gradients of fine-tuned adapters while ensuring privacy.
Outcome:	The proposed method surpasses existing OT methods in privacy protection and model performance.

Copied to clipboard

Zory Zhang, Pinyuan Feng, Bingyang Wang, Tianwei Zhao, Suyang Yu, Qingying Gao, Hokin Deng, Ziqiao Ma, Yijiang Li, Dezhi Luo

TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification (2021.emnlp-main)

Challenge:	Where someone looks is a nonverbal communication cue that children and adults readily use.
Approach:	They used 1,360 real-world photos to construct evaluation stimuli for Vision-Language Models (VLMs) they found a substantial performance gap between VLMs and humans .
Outcome:	The proposed model outperforms existing models in predicting gaze direction using head orientation rather than eye appearance.

Copied to clipboard

Chengyu Wang, Jianing Wang, Minghui Qiu, Jun Huang, Ming Gao

HyperIDP: Customizing Temporal Hypergraph Neural Networks for Multi-Scale Information Diffusion Prediction (2025.coling-main)

Challenge:	Recent studies show that prompts improve performance of large pre-trained language models for few-shot text classification.
Approach:	They propose a prompt-based framework for few-shot learning that captures cross-task transferable knowledge and uses two de-biasing techniques to make it more task-agnostic and unbiased .
Outcome:	The proposed framework outperforms strong baselines over multiple NLP tasks and datasets.

Copied to clipboard

Haowei Xu, Chao Gao, Xianghua Li, Zhen Wang

Enhancing Neural Topic Model with Multi-Level Supervisions from Seed Words (2023.findings-acl)

Challenge:	Existing studies on information diffusion prediction have focused on both macroscopic and microscopic scales.
Approach:	They propose a hypergraph-based model that manages both macroscopic and microscopic diffusion predictions.
Outcome:	The proposed model outperforms baseline models on both macroscopic and microscopic tasks.

Copied to clipboard

Yang Lin, Xin Gao, Xu Chu, Yasha Wang, Junfeng Zhao, Chao Chen

DecompileBench: A Comprehensive Benchmark for Evaluating Decompilers in Real-World Scenarios (2025.findings-acl)

Challenge:	Existing topic seed words are difficult to incorporate into topic models due to the semantic diversity of natural language.
Approach:	They propose a neural topic model enhanced with supervisions from seed words on word and document levels.
Outcome:	The proposed model outperforms the state-of-the-art seeded topic models in terms of topic quality and classification accuracy.

Copied to clipboard

Zeyu Gao, Yuxin Cui, Hao Wang, Siliang Qin, Yuanda Wang, Zhang Bolun, Chao Zhang

Challenge:	Existing approaches focus on syntactic correctness through synthetic micro-benchmarks or subjective human ratings, despite semantic fidelity and usability.
Approach:	They propose a framework that enables effective evaluation of decompilers in reverse engineering workflows . they compare six industrial-strength decompils and six recent LLM-powered approaches .
Outcome:	The proposed framework outperforms commercial tools in code understandability despite lower functionality correctness . it shows that it can transform human-centric reverse engineering workflows .

Improving Consistency for Text Summarization with Energy Functions (2023.findings-emnlp)

Copied to clipboard

Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang

Summarization

Challenge:	Current abstractive summarization models generate inconsistent content due to the inherently noisy dataset and the discrepancy between maximum likelihood estimation based training objectives and consistency measurements.
Approach:	They propose a new consistency taxonomy that categorizes inconsistent content into faithfulness, factuality, and self-supportiveness.
Outcome:	Experiments on XSUM and CNN/DM datasets show that EnergySum mitigates the trade-off between accuracy and consistency.

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

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

MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)

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

Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios (2025.emnlp-main)

Challenge:	Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths.
Approach:	They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO.
Outcome:	The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages.

Copied to clipboard

Yunkai Dang, Mengxi Gao, Yibo Yan, Xin Zou, Yanggan Gu, Jungang Li, Jingyu Wang, Peijie Jiang, Aiwei Liu, Jia Liu, Xuming Hu

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)

Challenge:	Existing studies have focused mainly on visual–textual misalignment, leaving largely unexplored the MLLMs’ ability to preserve an original correct answer when confronted with misleading information.
Approach:	They propose a two-stage evaluation pipeline to quantify the response uncertainty phenomenon by eliciting each model’s original response on unperturbed inputs and injecting explicit (false-answer hints) and implicit (contextual contradictions) misleading instructions.
Outcome:	The proposed model overturns a correct answer in 65% of cases after receiving a single deceptive cue.

Copied to clipboard

Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen

CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models (2025.findings-naacl)

Challenge:	Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities.
Approach:	They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance.
Outcome:	The proposed method achieves a superior balance between downstream learning and general capability retention.

Copied to clipboard

Shangda Wu, Yashan Wang, Ruibin Yuan, Guo Zhancheng, Xu Tan, Ge Zhang, Monan Zhou, Jing Chen, Xuefeng Mu, Yuejie Gao, Yuanliang Dong, Jiafeng Liu, Xiaobing Li, Feng Yu, Maosong Sun

From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora (2025.emnlp-main)

Challenge:	Current music information retrieval systems struggle to meet linguistic diversity challenges . current systems struggle with text queries in non-English languages .
Approach:	They propose a music information retrieval system that supports both ABC notation and MIDI . CLaMP 2 includes a multilingual text encoder and a multiple-modal music encoder .
Outcome:	The proposed system achieves state-of-the-art results in multilingual semantic search and music classification across modalities.

Copied to clipboard

Yingli Shen, Wen Lai, Shuo Wang, Ge Gao, Kangyang Luo, Alexander Fraser, Maosong Sun

Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations (2021.findings-emnlp)

Challenge:	Experiments show that models trained on multi-way parallel data outperform those trained on unaligned data.
Approach:	They propose a large-scale, high-quality multi-way parallel corpus based on TED Talks that spans 113 languages with up to 50 languages aligned in parallel.
Outcome:	The proposed model outperforms models trained on unaligned multilingual data on six multilingual benchmarks.

Copied to clipboard

Jun Gao, Yuhan Liu, Haolin Deng, Wei Wang, Yu Cao, Jiachen Du, Ruifeng Xu

Using Customer Service Dialogues for Satisfaction Analysis with Context-Assisted Multiple Instance Learning (D19-1)

Challenge:	Existing approaches to empathetic response generation ignore the emotion cause . existing dialogue systems lack emotion understanding and empathy .
Approach:	They propose a framework that integrates emotion cause information into empathetic response generation by predicting context emotion labels and sequence of emotion cause-oriented labels.
Outcome:	The proposed framework improves empathetic response generation by incorporating emotion cause information into the model.

Copied to clipboard

Kaisong Song, Lidong Bing, Wei Gao, Jun Lin, Lujun Zhao, Jiancheng Wang, Changlong Sun, Xiaozhong Liu, Qiong Zhang

HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference (2023.findings-emnlp)

Challenge:	Existing studies fail to provide comprehensive service satisfaction analysis . Existing models fail to include satisfaction polarity classification and sentimental utterance identification .
Approach:	They propose a model that predicts customer sentiments and aggregates them into service satisfaction polarity.
Outcome:	The proposed model predicts customer sentiments and aggregates them into service satisfaction polarity and reasoning clues.

Copied to clipboard

Haoyu Wang, Yaqing Wang, Tianci Liu, Tuo Zhao, Jing Gao

Knowledge-Guided Paraphrase Identification (2021.findings-emnlp)

Challenge:	Existing methods to exit pre-trained language models suffer from the limitation that they have to sequentially traverse through all layers prior to the selected exit layer, which degrades their performance.
Approach:	They propose a homotopic and adaptive layer skipping fine-tuning method that adaptively selects the layers to skip based on a predefined budget.
Outcome:	The proposed method outperforms all state-of-the-art baselines on the GLUE benchmark and shows that it is highly efficient.

Copied to clipboard

Haoyu Wang, Fenglong Ma, Yaqing Wang, Jing Gao

MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints (2026.findings-acl)

Challenge:	Existing methods for paraphrase identification (PI) are limited due to lack of professional knowledge.
Approach:	They propose to leverage Wikipedia knowledge to accurately identify paraphrases by mining outline knowledge of given sentences from Wikipedia.
Outcome:	The proposed framework outperforms state-of-the-art models on two public datasets: PARADE and clinicalSTS2019.

Copied to clipboard

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

LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines (2026.findings-acl)

Challenge:	Existing supervised neural methods are underexplored for coreference resolution, especially in incremental clustering.
Approach:	They propose a dual-threshold incremental clustering approach based on a lightweight Transformer.
Outcome:	Experiments on common benchmarks show that MEIC-DT achieves highly competitive coreference performance under stringent memory constraints.

Copied to clipboard

Jiechao Gao, Rohan Kumar Yadav, Yuangang Li, Yuandong Pan, Jie Wang, Ying Liu, Michael Lepech

Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment (2023.acl-long)

Challenge:	Pretrained language models (PLMs) provide strong semantic representations but are costly and opaque.
Approach:	They propose a framework that transfers pretrained language models into symbolic form and integrates them into symbolic models.
Outcome:	The proposed framework improves interpretability and accuracy across multiple text classification tasks while remaining fully symbolic and efficient.

Copied to clipboard

Tianshu Yu, Haoyu Gao, Ting-En Lin, Min Yang, Yuchuan Wu, Wentao Ma, Chao Wang, Fei Huang, Yongbin Li

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning (2024.emnlp-main)

Challenge:	Existing speech-text pre-training methods are limited to one or two specific tasks, despite their success in speech-language processing tasks.
Approach:	They propose a temporal position prediction task to capture the speech-text alignment . they use a textual dialog pre-training task to generalize a response selection task .
Outcome:	The proposed model is superior in learning speech-text alignment and multi-turn dialog context.

Copied to clipboard

Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang

DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? (2024.findings-emnlp)

Challenge:	Recent advances in open-source Large Language Models (LLMs) have achieved notable successes in natural language processing.
Approach:	They propose a Parameter Efficient Fine-Tuning paradigm for improved fine-tuning and parameter efficiency in multi-task learning.
Outcome:	The proposed model outperforms existing methods on multi-task learning while reducing training costs by over 80% without losing general capability.

Copied to clipboard

Zhouhong Gu, Lin Zhang, Xiaoxuan Zhu, Jiangjie Chen, Wenhao Huang, Yikai Zhang, Shusen Wang, Zheyu Ye, Yan Gao, Hongwei Feng, Yanghua Xiao

Boundary Detection with BERT for Span-level Emotion Cause Analysis (2021.findings-acl)

Challenge:	Existing LLMs' abilities to detect evidence in long contexts are far inferior to humans.
Approach:	They propose a benchmark to assess LLMs' abilities in evidence and multi-step commonsense reasoning within a long context.
Outcome:	The proposed method improves the performance of LLMs in evidence detection and commonsense reasoning.

Copied to clipboard

Xiangju Li, Wei Gao, Shi Feng, Yifei Zhang, Daling Wang

BloomEval: A Bloom’s Cognitive Taxonomy-Based Benchmark for Evaluating LRMs via Cognitive Hierarchy Trace (2026.findings-acl)

Challenge:	Emotion cause analysis (ECA) is an emerging topic in natural language processing, which aims to identify the reasons behind a given emotion.
Approach:	They propose to detect the precise boundaries of text spans conveying accurate emotion causes from the given context by a sequence labeling and position identification problem.
Outcome:	The proposed methods outperform existing models on two benchmark datasets on the emotion cause analysis task.

Copied to clipboard

Zhiyi Duan, Lei Gao, Jiangshan Guan, Qi Wang, Rui Liu

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models (2025.findings-emnlp)

Challenge:	Existing benchmarks for Large Reasoning Models rely on answer correctness, but fail to assess the structural coherence and cognitive soundness of the reasoning process itself.
Approach:	They propose a framework that maps a model's reasoning trajectory onto hierarchical cognitive levels and an annotation pipeline to ensure a scalable yet reliable annotation pipeline.
Outcome:	The proposed framework detects hierarchy jumps, breaks, and overthinking errors and enables scalable yet reliable annotation.

Copied to clipboard

Weihang Wang, Xinhao Li, Ziyue Wang, Yan Pang, Jielei Zhang, Peiyi Li, Qiang Zhang, Longwen Gao

CHROMIC: Chronological Reasoning Across Multi-Panel Comics (2026.eacl-long)

Challenge:	Existing benchmarks focus on coarse-grained hallucination detection and fail to capture hallucinics . vision encoders exhibit unique hallucinian characteristics, but suboptimal of simple feature fusion.
Approach:	They propose a visual encoder that employs different training paradigms to instill inductive biases in visual encoded models.
Outcome:	The proposed system reduces hallucinations and improves model performance.

Copied to clipboard

Bingxuan Hou, Jiayi Lin, Chenyang Zhang, Dapeng Yin, Shuyue Zhu, Qingqing Hong, Mengna Gao, Junli Wang

LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming (2023.acl-long)

Challenge:	Large-scale vision–language models have achieved remarkable progress on various reasoning tasks, but most studies focus on natural photographic images and pay limited attention to multi-panel visual narratives such as comics.
Approach:	They propose a benchmark dataset for chronological reasoning in multi-panel comics that covers six types of reasoning questions and spans both Western and Japanese comic styles.
Outcome:	The proposed dataset covers six types of reasoning questions and spans both Western and Japanese comic styles.

Copied to clipboard

Jingsheng Gao, Yixin Lian, Ziyi Zhou, Yuzhuo Fu, Baoyuan Wang

Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement (2024.findings-acl)

Challenge:	a recent study shows that open-domain dialogue systems are not able to perform well in fast-growing scenarios such as live streaming due to the domain gap between online-post constructed data and those required in downstream conversational tasks.
Approach:	They propose to train a conversational agent based on large social media datasets with multiple domains to improve response in live streaming scenarios.
Outcome:	The proposed model improves response modeling and addressee recognition in live open-domain scenarios.

Copied to clipboard

Wenxin Mao, Ruiqi Wang, Jiyu Guo, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu

Language Adaptation of Large Language Models: An Empirical Study on LLaMA2 (2025.coling-main)

Challenge:	Existing prompt engineering methods exploit database content and execution feedback to improve text-to-sql performance.
Approach:	They propose a framework for large language model-based text-to-sql task that exploits database content and execution feedback to improve execution accuracy.
Outcome:	The proposed framework improves execution accuracy and usability by 12.41% and 5.38% on four widely used benchmarks.

Copied to clipboard

Shumin Wang, Yuexiang Xie, Bolin Ding, Jinyang Gao, Yanyong Zhang

Composition-based Heterogeneous Graph Multi-channel Attention Network for Multi-aspect Multi-sentiment Classification (2022.coling-1)

Challenge:	Popularity of Large Language Models (LLMs) has seen a skyrocketing increase in recent years.
Approach:	They present a systematic review of the language adaptation process for Large Language Models including vocabulary expansion, continued pre-training, and instruction fine-tuning.
Outcome:	The proposed model is based on empirical studies conducted on LLaMA2 and discussions on various settings affecting the model's capabilities.

Copied to clipboard

Hao Niu, Yun Xiong, Jian Gao, Zhongchen Miao, Xiaosu Wang, Hongrun Ren, Yao Zhang, Yangyong Zhu

GR1: Reinforcement-Enhanced LLM for Geoscience Reasoning (2026.findings-acl)

Challenge:	Existing methods for Aspect-based sentiment analysis (ABSA) focus on aspect terms with the same sentiment polarity . current methods focus on sentences with only one aspect term or multiple aspect terms .
Approach:	They propose a novel method to model inter-aspect relationships and aspect-context relationships simultaneously using a heterogeneous graph.
Outcome:	The proposed method can predict sentiments towards the given aspect term in a sentence . it can provide more detailed predictions compared with sentence-level sentiment analysis.

Copied to clipboard

Yule Xie, Jiaxin Ding, Cheng Deng, Shiqing Gao, Junran Zhang, Sibo Zhang, Zeyuan Wang, Ke Wu, Xin Ding, Luoyi Fu, Meng Jin, Xinbing Wang

Unsupervised Deep Structured Semantic Models for Commonsense Reasoning (N19-1)

Challenge:	Recent advances in large language models have demonstrated RL's substantial capacity to enhance multi-step reasoning beyond what supervised instruction tuning achieves.
Approach:	They propose a framework that converts multimodal questions into descriptive text . they propose RL-enhanced geoscience reasoning that can be fine-tuned to a text-only level .
Outcome:	The proposed framework improves accuracy and accuracy on multimodal questions while preserving answerability and difficulty.

Copied to clipboard

Shuohang Wang, Sheng Zhang, Yelong Shen, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Jing Jiang

Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression (2024.acl-long)

Challenge:	Existing methods for commonsense reasoning rely on human-crafted features and knowledge bases, but unsupervised learning is not feasible due to the lack of labeled training data or comprehensive knowledge bases.
Approach:	They propose two unsupervised models based on the Deep Structured Semantic Models framework to tackle two commonsense reasoning tasks: Winograd Schema Challenge (WSC) and Pronoun Disambiguation (PDP).
Outcome:	The proposed models capture contextual information in the sentence and co-reference information between pronouns and nouns, and achieve significant improvement over previous state-of-the-art approaches.

Copied to clipboard

Peiyu Liu, Ze-Feng Gao, Xin Zhao, Yipeng Ma, Tao Wang, Ji-Rong Wen

Are Your LLMs Capable of Stable Reasoning? (2025.findings-acl)

Challenge:	Existing methods to compress KV cache compromise precision or require extra data for calibration, limiting their practicality in LLM deployment.
Approach:	They propose a low-bit quantization technique based on tensor decomposition to effectively compress KV cache.
Outcome:	The proposed method reduces memory footprint and performance by 75% . it is compared with existing methods that compromise precision or require extra data for calibration .

Copied to clipboard

Junnan Liu, Hongwei Liu, Linchen Xiao, Ziyi Wang, Kuikun Liu, Songyang Gao, Wenwei Zhang, Songyang Zhang, Kai Chen

StruNRAG: Evaluation of OCR-Induced Structural Noise on RAG Robustness (2026.findings-acl)

Challenge:	Existing evaluation protocols and metrics do not capture the full spectrum of LLM capabilities, especially in complex reasoning tasks.
Approach:	They propose a new evaluation metric that continuously assesses model performance across multiple sampling attempts, quantifying both the model’s potential capabilities and operational consistency.
Outcome:	The proposed evaluation metric measures model performance across multiple sampling attempts and provides comprehensive insights into their potential capabilities and operational consistency.

Copied to clipboard

Mengna Gao, Dapeng Yin, Shuyue Zhu, Bingxuan Hou, Zhanpeng Ni, Junli Wang

EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues (2025.naacl-long)

Challenge:	Existing evaluations of RAG systems ignore structural noise, authors say . complex layouts can cause OCR failures and disrupt semantic flow of text . advanced LLMs demonstrate robustness against local noise, but struggle to maintain reasoning capabilities under severe structural disruption that fragments global context.
Approach:	They propose a benchmark to evaluate RAG robustness against OCR-induced structural perturbations.
Outcome:	The proposed benchmark systematically injects three categories of real-world structural noise into a bilingual dataset of 2,132 question-answer pairs . results show that advanced LLMs demonstrate robustness against local noise, but struggle to maintain reasoning capabilities under severe structural disruption .

Copied to clipboard

Qiming Feng, Qiujie Xie, Xiaolong Wang, Qingqiu Li, Yuejie Zhang, Rui Feng, Tao Zhang, Shang Gao

DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection (2022.emnlp-main)

Challenge:	EmoCharacter evaluates emotional fidelity of role-playing agents in dialogues . current evaluations focus on personality fidelity, tone imitation, and knowledge consistency .
Approach:	They propose a benchmark to assess emotional fidelity of role-playing agents in dialogues using large language models.
Outcome:	The proposed benchmark measures emotional fidelity of role-playing agents and the characters they portray.

Copied to clipboard

Yongkang Liu, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

Yongzhen Wang, Xiaozhong Liu, Zheng Gao

Challenge:	Existing retrieval-based dialogue systems suffer from slow inference or huge number of parameters.
Approach:	They propose a lightweight fully convolutional architecture for response selection using convolution.
Outcome:	The proposed architecture extracts matching features of context and response from 3D views.

Copied to clipboard

Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction (2025.findings-emnlp)

Challenge:	Existing approaches to automatic related work summarization rely on human-engineered features.
Approach:	They propose a neural data-driven attention mechanism to measure contextual relevance within full texts and a heterogeneous bibliography graph simultaneously.
Outcome:	The proposed approach achieves significant improvement over a typical seq2seq summarization baseline and five classical summarizing baselines.

Copied to clipboard

Maya Kruse, Shiyue Hu, Nicholas Derby, Yifu Wu, Samantha Stonbraker, Bingsheng Yao, Dakuo Wang, Elizabeth M. Goldberg, Yanjun Gao

PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models (2025.findings-emnlp)

Challenge:	Recent advances in large language models have shown potential in clinical text summarization, but their ability to handle long patient trajectories with multi-modal data spread across time remains underexplored.
Approach:	They evaluate open-source large language models, their Retrieval Augmented Generation variants and chain-of-thought prompting on long-context clinical summarization and prediction.
Outcome:	The proposed models can synthesize structured and unstructured EHR data while reasoning over temporal coherence.

Copied to clipboard

Yuanhe Zhang, Xinyue Wang, Haoran Gao, Zhenhong Zhou, Fanyu Meng, Yuyao Zhang, Sen Su

Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition (2026.findings-eacl)

Challenge:	Existing work lacks mitigation strategies against resource consumption attacks . existing work does not provide mitigation strategies for real-world LLM deployments .
Approach:	They propose a pluggable and dynamic doS-Defense framework which employs a two-stage approach to defend against resource consumption attacks from both the input and output sides.
Outcome:	The proposed framework significantly mitigates resource consumption attacks, improving users’ access capacity by up to 500% during adversarial load.

Copied to clipboard

Zheng Hui, Xiaokai Wei, Yexi Jiang, Kevin Gao, Chen Wang, Se-eun Yoon, Rachit Pareek, Michelle Gong

TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills (2024.lrec-main)

Challenge:	Existing systems for conversational recommender systems (CRS) have strong results in movies, but games present distinct challenges . MATCHA framework provides specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking, and stronger safety.
Approach:	They propose a framework for conversational recommender systems that assigns specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking and risk control.
Outcome:	MATCHA outperforms baselines on real user request dataset, improves Hit@5 by 20%, reduces popularity bias by 24%, and achieves 97.9% adversarial defense.

Copied to clipboard

Qiushi Sun, Nuo Chen, Jianing Wang, Ming Gao, Xiang Li

UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions (2025.findings-acl)

Challenge:	Existing methods to fine-tune code intelligence models to individual tasks are costly and require large data sets.
Approach:	They propose a Transferable fine-tuning strategy for Code representation learning that uses a tunable prefix encoder to capture cross-task and cross-language transferable knowledge and apply it to downstream adaptation.
Outcome:	The proposed method can lead to superior performance on code-related tasks and encourage mutual reinforcement.

Copied to clipboard

Xunzhi Wang, Zhuowei Zhang, Gaonan Chen, Qiongyu Li, Bitong Luo, Zhixin Han, Haotian Wang, Zhiyu Li, Hang Gao, Mengting Hu

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance (2026.findings-acl)

Challenge:	Existing methods for benchmarking the uncertainty of large language models face challenges . existing methods require internal model access, additional training, or high computational costs .
Approach:	They propose a new benchmark for evaluating the uncertainty of large language models based on confidence intervals . UBench encompasses 11,978 multiple choice questions spanning knowledge, language, understanding, and reasoning capabilities.
Outcome:	The proposed method outperforms existing methods for benchmarking the uncertainty of large language models.

Copied to clipboard

Hao Zhang, Zhenjia Li, Yifan Gao, Xi Xiao, Heng Zhang, Shuyang Zhang, null Xiaoxincc, Bo Huang, Yuhang Wu, Tianyang Wang, Hao Xu

A Novel Two-step Fine-tuning Framework for Transfer Learning in Low-Resource Neural Machine Translation (2024.findings-naacl)

Challenge:	Low-Rank Adaptation (LoRA) assumes a uniform rank r for each incremental matrix, not accounting for the varying significance of weight matrices across modules and layers.
Approach:	They propose a framework that allows for faster convergence of low-rank adaptive models . they use a hypernetwork to prune the outputs of the hypernetworks to generate parameters .
Outcome:	The proposed framework accelerates convergence of AdaLoRA by leveraging a hypernetwork.

Copied to clipboard

Yuan Gao, Feng Hou, Ruili Wang

Towards Universal Debiasing for Language Models-based Tabular Data Generation (2025.findings-emnlp)

Challenge:	Existing transfer learning methods for neural machine translation use a well-trained translation model to initialize a child model with corresponding datasets.
Approach:	They propose a two-step fine-tuning framework for transfer learning in low-resource neural machine translation that adjusts the parent model to fit the child language by using the child source data.
Outcome:	The proposed framework improves on five low-resource translations on high-resolution languages.

Copied to clipboard

Tianchun Li, Tianci Liu, Xingchen Wang, Rongzhe Wei, Pan Li, Lu Su, Jing Gao

ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge (2022.findings-emnlp)

Challenge:	Existing large language models have exacerbated fairness issues in tabular data generation . inherent historical biases in tabulated data cause LLMs to exacerbate fairness problems .
Approach:	They propose a universal debiasing framework that minimizes group-level dependencies . it leverages the autoregressive structure and analytic sampling distributions of LLM-based tabular data generators .
Outcome:	The proposed framework minimizes group-level dependencies while reducing mutual information between advantaged and protected attributes.

Copied to clipboard

Tingting Liu, Chengyu Wang, Xiangru Zhu, Lei Li, Minghui Qiu, Jun Huang, Ming Gao, Yanghua Xiao

CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments (2026.acl-long)

Challenge:	Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images.
Approach:	They propose a transformer-based Chinese text-to-image synthesizer for high-resolution image generation that incorporates linguistic and relational knowledge facts into the model to ensure better performance without the usage of ultra-large models.
Outcome:	The proposed model outperforms existing models in Chinese with linguistic and relational knowledge facts.

Copied to clipboard

Haotian Xu, Yue Hu, Zhengqiu Zhu, Chen Gao, Ziyou Wang, Junreng Rao, Wenhao Lu, Weishi Li, Quanjun Yin, Yong Li

Lˆ2GC:Lorentzian Linear Graph Convolutional Networks for Node Classification (2024.lrec-main)

Challenge:	Existing benchmarks focus on indoor or street settings, overlooking challenges of open-ended urban spaces.
Approach:	They propose a benchmark to probe cross-view spatial reasoning capabilities of current VLMs in urban settings.
Outcome:	The citycube benchmark examines the performance of current vision-language models in urban environments.

Copied to clipboard

Qiuyu Liang, Weihua Wang, Feilong Bao, Guanglai Gao

KAT: A Knowledge Augmented Transformer for Vision-and-Language (2022.naacl-main)

Challenge:	Existing linear GCNs perform neural network operations in Euclidean space, which do not capture tree-like hierarchical structure of graphs.
Approach:	They propose a Lorentzian linear GCN framework that maps features into hyperbolic space and performs a feature transformation to capture the underlying tree-like structure of data.
Outcome:	The proposed framework achieves state-of-the-art accuracy on standard citation networks datasets and 81.3% on PubMed datasets.

Copied to clipboard

Liangke Gui, Borui Wang, Qiuyuan Huang, Alexander Hauptmann, Yonatan Bisk, Jianfeng Gao

ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models (2025.findings-acl)

Challenge:	Existing methods for knowledge retrieval and answer prediction have left open questions about the quality and relevance of the retrieved knowledge and how the reasoning processes over implicit and explicit knowledge should be integrated.
Approach:	They propose a Knowledge Augmented Transformer which integrates both implicit and explicit knowledge in an encoder-decoder architecture while simultaneously reasoning over both knowledge sources during answer generation.
Outcome:	The proposed model achieves a strong state-of-the-art (+6% absolute) on the open-domain multimodal task of OK-VQA.

Copied to clipboard

Hao Chen, Haoze Li, Zhiqing Xiao, Lirong Gao, Qi Zhang, Xiaomeng Hu, Ningtao Wang, Xing Fu, Junbo Zhao

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation (2024.emnlp-main)

Challenge:	Prior research has focused on optimizing general-purpose large language models to downstream tasks . however, these approaches inherently introduce data dependency, which hinders generalization and reusability.
Approach:	They propose an algorithm that localizes the most task-sensitive attention heads and prunes by restricting attention training updates to these heads, thereby reducing alignment costs.
Outcome:	The proposed algorithm achieves 2% performance improvement over baselines on three tasks while localizing the most task-sensitive attention heads.

Copied to clipboard

Xiaoze Liu, Ting Sun, Tianyang Xu, Feijie Wu, Cunxiang Wang, Xiaoqian Wang, Jing Gao

Live-Aid: A Large-Scale Dialogue Dataset and Benchmark for Interleaved Multi-party Interactions in Live Streaming (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have transformed machine learning but have raised significant legal concerns due to their potential to produce text that infringes on copyrights.
Approach:	They propose a lightweight, real-time defense mechanism to prevent the generation of copyrighted text by evaluating methods and testing attack strategies.
Outcome:	The proposed defense significantly reduces the volume of copyrighted text generated by LLMs by effectively refusing malicious requests.

Copied to clipboard

Yiming Lei, Yize Fan, Zeming Liu, Jiaji Dong, Hui Qiu, Haitao Leng, Qingjie Liu, Kehai Chen, Tingting Gao, Yunhong Wang

SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems (2025.findings-acl)

Challenge:	Existing Multimodal Large Language Models struggle with dynamic interactions due to the scarcity of high-quality interleaved data.
Approach:	They propose a large-scale interleaved live interaction Chinese dataset with human-annotated video responses.
Outcome:	The proposed model can be used to evaluate live interactions in Chinese over 1,100 hours and 80,037 dialogue turns.

Copied to clipboard

Ziyu Guo, Renrui Zhang, Hao Chen, Jialin Gao, Dongzhi Jiang, Jiaze Wang, Pheng-Ann Heng

Virtual Compiler Is All You Need For Assembly Code Search (2024.acl-long)

Challenge:	SciVerse is a multi-modal scientific evaluation benchmark to assess large multi-models . it examines the scientific knowledge comprehension, multi-mod content interpretation and Chain-of-Thought reasoning . authors examine the scientific proficiency of LMMs in scientific domains based on their work .
Approach:	They propose a multi-modal scientific evaluation benchmark to thoroughly assess Large Multi-modal Models across 5,735 test instances in five different versions.
Outcome:	The proposed evaluation reveals critical limitations in LMMs' scientific proficiency and provides new insights into future developments.

Copied to clipboard

Zeyu Gao, Hao Wang, Yuanda Wang, Chao Zhang

Programming Languages in NLP

Challenge:	Using a large dataset, we find that assembly code search is a significant task for reverse engineers.
Approach:	They propose to train a Large Language Model (LLM) to emulate a general compiler.
Outcome:	The proposed model surpasses the baseline by 26%.

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (2024.emnlp-main)

Copied to clipboard

Tianyang Xu, Shujin Wu, Shizhe Diao, Xiaoze Liu, Xingyao Wang, Yangyi Chen, Jing Gao

Huatuo-26M, a Large-scale Chinese Medical QA Dataset (2025.findings-naacl)

Challenge:	Existing approaches to elicit confidence from large language models are limited to binary or inaccurate group-level confidence estimates.
Approach:	They propose a training framework that teaches LLMs to express more fine-grained confidence estimates.
Outcome:	The proposed training framework reduces the confidence calibration error and maintains the performance of the model.

Copied to clipboard

Xidong Wang, Jianquan Li, Shunian Chen, Yuxuan Zhu, Xiangbo Wu, Zhiyi Zhang, Xiaolong Xu, Junying Chen, Jie Fu, Xiang Wan, Anningzhe Gao, Benyou Wang

Question Answering

Challenge:	Large Language Models are a powerful tool for medical research, but the data is a bottleneck.
Approach:	They propose to use the largest ever medical Question Answering dataset with 26 Million QA pairs as a fine-tuning data for training large language models.
Outcome:	The proposed dataset demonstrates that it can be used to train large language models and improves zero-shot performance on other datasets.

Bayesian Calibration of Win Rate Estimation with LLM Evaluators (2024.emnlp-main)

Copied to clipboard

Yicheng Gao, Gonghan Xu, Zhe Wang, Arman Cohan

Demystifying Data Organization for Enhanced LLM Training (2026.acl-long)

Challenge:	Recent advances in large language models (LLMs) show the potential of using LLMs as evaluators for text quality evaluation.
Approach:	They propose two methods to improve the accuracy of LLM evaluators by Bayesian inference.
Outcome:	The proposed methods improve the accuracy of the win rate estimation using LLMs . the proposed methods are based on six datasets covering story generation, summarization, and instruction following tasks .

Copied to clipboard

Yalun Dai, Yangyu Huang, Tongshen Yang, Yonghan Wang, Xin Zhang, Wenshan Wu, Qihao Zhao, Hao Li, Yuanyuan Gao, Kim-Hui Yap, Scarlett Li

Towards Objective Fine-tuning: How LLMs’ Prior Knowledge Causes Potential Poor Calibration? (2025.acl-long)

Challenge:	Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation.
Approach:	They propose to reuse pre-computed sample-level scores originally generated for data efficiency and introduce two new data ordering methods to improve LLM training.
Outcome:	The proposed methods improve the stability and performance of LLM training.

Copied to clipboard

Ziming Wang, Zeyu Shi, Haoyi Zhou, Shiqi Gao, Qingyun Sun, Jianxin Li

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

Challenge:	Large Language Models (LLMs) have enabled powerful domain-specific applications through supervised fine-tuning.
Approach:	They propose a cognition-aware framework that applies targeted learning strategies according to the model’s prior knowledge to improve calibration.
Outcome:	The proposed framework significantly improves calibration while maintaining performance, achieving an average 57% reduction in ECE compared to standard fine-tuning in Llama3-8B.

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

SVD-GCL: A Noise-Augmented Hybrid Graph Contrastive Learning Framework for Recommendation (2025.coling-main)

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

Liping Wang, Shichao Li, Hui Wang, Yuyan Gao, Mingyao Wei

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

Challenge:	Recent advances in graph neural networks have made it difficult to capture user preferences.
Approach:	They propose a graph contrastive learning recommendation model based on noise augmentation that integrates truncated singular value decomposition in the feature engineering stage.
Outcome:	The proposed model reduces dimensionality and denoises the original data.

Copied to clipboard

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

Soft Orthogonal Low-Rank Adaptation for Knowledge Sharing in Large Language Model Continual Learning (2026.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

Yitong Wang, Xue Han, WenChun Gao, Qian Hu, Jiahui Wang, Ziqing Wang, Lijun Mei, Junlan Feng

Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models (2023.findings-acl)

Challenge:	Existing methods for continual learning (CL) are designed to mitigate catastrophic forgetting while neglecting knowledge sharing across tasks.
Approach:	They propose a framework that facilitates knowledge transfer while mitigating catastrophic forgetting by assigning task-specific parameter subspaces to new tasks . they then leverage attribution scores to evaluate task similarity and employ soft orthogonality between task- specific subspace .
Outcome:	The proposed framework facilitates knowledge transfer while mitigating catastrophic forgetting.

Copied to clipboard

Borui Wang, Qiuyuan Huang, Budhaditya Deb, Aaron Halfaker, Liqun Shao, Daniel McDuff, Ahmed Hassan Awadallah, Dragomir Radev, Jianfeng Gao

MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria (2025.naacl-long)

Challenge:	Existing pre-trained language models that ignore the logical structures underlying natural language text often lack the ability to capture and encode key logical information in the input sequences.
Approach:	They propose to construct logic-aware input embeddings for transformer language models through logic detection, logic mapping and hierarchical logical projections and then develop a new modeling paradigm that can upgrade existing transformer language model into logical transformers to boost their performance.
Outcome:	The proposed model can achieve superior performance on four important and challenging tasks.

Copied to clipboard

Wentao Ge, Shunian Chen, Hardy Chen, Nuo Chen, Junying Chen, Zhihong Chen, Wenya Xie, Shuo Yan, ChenghaoZhu ChenghaoZhu, Ziyue Lin, Dingjie Song, Xidong Wang, Anningzhe Gao, Zhang Zhiyi, Jianquan Li, Xiang Wan, Benyou Wang

MoDification: Mixture of Depths Made Easy (2025.naacl-long)

Challenge:	Existing evaluation methodologies for multimodal large language models are limited in evaluating objective queries without considering real-world user experiences.
Approach:	They propose to evaluate multimodal large language models with per-sample criteria using potent MLLM as the judge.
Outcome:	The proposed evaluation paradigm shows that it can be used to evaluate multimodal large language models with per-sample criteria.

Copied to clipboard

Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song

WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement (2026.acl-long)

Challenge:	Long-context efficiency is a trending topic in large language model (LLM) serving.
Approach:	They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory.
Outcome:	The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications.

Copied to clipboard

Fangyuan Li, Pengfei Li, Shijie Wang, Junqi Gao, Jianxing Liu, Biqing Qi, Yuqiang Li

Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026.findings-acl)

Challenge:	Existing methods for self-improvement of large language models with verifiable rewards (RLVR) can drift over iterations, while corpus-grounded approaches rely on curated data environments.
Approach:	They propose a Web-grounded Iterative Self-play Tree framework for domain-targeted reasoning improvement that learns directly from the open-web without requiring any pre-arranged domain corpus.
Outcome:	The proposed framework outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines and is domain-steerable.

Copied to clipboard

Fengran Mo, Yifan Gao, Sha Li, Hansi Zeng, Xin Liu, Zhaoxuan Tan, Xian Li, Jianshu Chen, Dakuo Wang, Meng Jiang

InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes Under Herd Behavior (2025.acl-long)

Challenge:	Existing studies focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions.
Approach:	They propose a conversational agent that interleaves search and reasoning across turns and provides tailored rewards towards evolving user goals.
Outcome:	The proposed agent interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals.

Copied to clipboard

Huisheng Wang, Zhuoshi Pan, Hangjing Zhang, Mingxiao Liu, Hanqing Gao, H. Vicky Zhao

Concept Pointer Network for Abstractive Summarization (D19-1)

Challenge:	relying on authentic data for Supervised Fine-Tuning (SFT) is costly and expensive.
Approach:	They propose a framework that constructs high-quality SFT datasets by leveraging theoretical solutions to similar and simple optimal investment problems rather than the complex scenarios.
Outcome:	The proposed framework achieves faster parameter convergence than using real-user data, suggesting superior learning efficiency.

Copied to clipboard

Wenbo Wang, Yang Gao, Heyan Huang, Yuxiang Zhou

Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation (2026.acl-long)

Challenge:	Abstractive summarization (ABS) has gained overwhelming success owing to a tremendous development of sequence-to-sequence models and its variants.
Approach:	They propose a concept pointer network that leverages knowledge-based, context-aware conceptualizations to derive an extended set of candidate concepts and then points to the most appropriate choice using both the concept set and original source text.
Outcome:	The proposed model improves on the DUC-2004 and Gigaword datasets and human evaluation of its abstractive abilities supports the quality of the summaries produced.

Copied to clipboard

Huizi Cui, Huan Ma, Qilin Wang, Yuhang Gao, Changqing Zhang

CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference (2024.emnlp-main)

Challenge:	Existing uncertainty quantification methods depend on computationally expensive multiple sampling or internal parameters, which prevents real-time estimation and fails to capture information implicit in the black-box reasoning process.
Approach:	They propose a distribution-aligned adjudication architecture to guide a lightweight proxy model to learn the high-quality regions of the output distribution of the black-box LLM.
Outcome:	Extensive experiments show that a proxy model even with 1% of the target LLM’s size can achieve reliable uncertainty quantification.

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Siqi Wang, Gao Zuchen, Fei Mi, Lanqing Hong

Boosting Language Models Reasoning with Chain-of-Knowledge Prompting (2024.acl-long)

Challenge:	Existing studies have not noticed the safety risks of large language models . authors evaluated 1,400 questions in multi-turn dialogue coreference .
Approach:	They are the first to evaluate LLM safety in multi-turn dialogue coreference . they created a dataset of 1,400 questions and tested five open-source models .
Outcome:	The study shows that model safety decreases in multi-turn dialogue coreference scenarios . the highest success rate was with the LLaMA2-Chat-7b model, while the lowest was with mistral-7B-Instruct model .

Copied to clipboard

Jianing Wang, Qiushi Sun, Xiang Li, Ming Gao

MDTeamGPT: Mitigating Context Collapse and Enabling Self-Evolution in Medical Multi-Agent Reasoning (2026.findings-acl)

Challenge:	Recent studies have shown that Chain-of-Thought (CoT) prompting can be effective on complex reasoning tasks but generates unfaithful and unfactual reasoning chains.
Approach:	They propose a chain-of-knowledge prompting that elicits Large Language Models to generate explicit pieces of knowledge evidence in the form of structure triple.
Outcome:	The proposed method improves commonsense, factual, symbolic, and arithmetic reasoning tasks by estimating the reliability of the reasoning chains in terms of factuality and faithfulness.

Copied to clipboard

Kai Chen, Xinfeng Li, Tianpei Yang, Hewei Wang, Guang Yang, Jing Huo, Yang Gao

Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding (2023.findings-emnlp)

Challenge:	Long, multi-round, multirole interaction trajectories lead to severe information dilution and context window overload, triggering context collapse which destabilizes reasoning.
Approach:	They propose a multi-agent framework that compresses and reorganizes multi-round consensus.
Outcome:	The proposed framework outperforms baselines across text-based and multimodal tasks while demonstrating superior diagnostic performance and stability in complex clinical scenarios.

Copied to clipboard

Jianing Wang, Qiushi Sun, Nuo Chen, Chengyu Wang, Jun Huang, Ming Gao, Xiang Li

Learning to Edit: Aligning LLMs with Knowledge Editing (2024.acl-long)

Challenge:	Existing methods for pre-trained language models rely on noisy data, which can be expensive if all parameters are updated.
Approach:	They propose a self-training framework that incorporates Monte Carlo dropouts into the model and judiciously selects reliable pseudo-labeled examples based on confidence and certainty.
Outcome:	The proposed framework improves performance and efficiency over multiple tasks over multiple datasets.

Copied to clipboard

Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang

Challenge:	Existing knowledge editing techniques rely on memorizing updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions.
Approach:	They propose a Learning to Edit framework that equips LLMs with the ability to apply updated knowledge to input questions through a two-phase process .
Outcome:	The proposed framework outperforms existing methods in knowledge editing tasks and compares it with four benchmarks and two LLM architectures.

Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models (2026.acl-long)

Copied to clipboard

Jinrui Wang, Zhenfeng Gao, Wendan Wang, Huili Wang, Zichen Qin, Linjie Zhu, Hongke Fu, Shangguang Wang, Tao Qi

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Challenge:	Existing methods assess model memorization of key semantic concepts within a video but do not provide reliable evidence that a specific video was used during training.
Approach:	They propose a black-box MIA framework that can provide reliable evidence of specific video data usage for training multimodal large language models.
Outcome:	The proposed framework can provide reliable evidence of specific video data usage for training multimodal large language models.

Copied to clipboard

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach:	They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome:	The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

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

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

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

A LSTM Approach with Sub-Word Embeddings for Mongolian Phrase Break Prediction (C18-1)

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

Rui Liu, Feilong Bao, Guanglai Gao, Hui Zhang, Yonghe Wang

Learning to Maximize Mutual Information for Chain-of-Thought Distillation (2024.findings-acl)

Challenge:	Existing word embedding methods for Mongolian PB prediction are expensive and time-consuming.
Approach:	They propose to use Mongolian word embedding to build a robust Mongolian PB prediction model . they encode sub-word units and feed it to LSTM to decode the best corresponding PB label .
Outcome:	The proposed model outperforms traditional model using manual features and achieves 7.49% gain.

Copied to clipboard

Xin Chen, Hanxian Huang, Yanjun Gao, Yi Wang, Jishen Zhao, Ke Ding

Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding (2022.emnlp-main)

Challenge:	Knowledge distillation is a technique of transferring knowledge from large, complex models to smaller ones.
Approach:	They propose a method utilizing chain-of-thought distillation to transfer knowledge from large, complex models to smaller ones by maximizing mutual information of the representation features of the two tasks.
Outcome:	The proposed method outperforms the state-of-the-art knowledge distillation method on four datasets.

Copied to clipboard

Jianing Wang, Wenkang Huang, Minghui Qiu, Qiuhui Shi, Hongbin Wang, Xiang Li, Ming Gao

Not All Citations Are Equal:Entropy-Guided Citation Selection for Noise-Resistant Medical LLM (2026.findings-acl)

Challenge:	Existing knowledge-enhanced pre-trained language models (PLMs) introduce redundant factual knowledge from knowledge bases and require complex modules.
Approach:	They propose a knowledge prompting-based PLM framework that incorporates factual knowledge into PLMs.
Outcome:	The proposed framework can be flexibly combined with existing mainstream PLMs.

Copied to clipboard

Minyu Gao, Hanlin Xiao, Ruoyu Wang, Shuai Yang, YeXuan Zhang, Xin Wu, Xingyu Liu

SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation (2024.findings-emnlp)

Challenge:	Large language models have demonstrated extensive potential in medical applications . however, their practical deployment in healthcare faces significant challenges .
Approach:	They propose a training-free multi-turn reasoning framework and a post-training methodology that provides external knowledge support for large language models.
Outcome:	The proposed framework elicits internal thought, external thought, and fusion thought, with an entropy-based reward that encourages selective citation of beneficial external knowledge while penalizing noisy citations.

Copied to clipboard

Minda Hu, Licheng Zong, Hongru Wang, Jingyan Zhou, Jingjing Li, Yichen Gao, Kam-Fai Wong, Yu Li, Irwin King

ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding (2022.coling-1)

Challenge:	Existing retrieval-augmented approaches to large language models face performance limitations due to the lack of publicly available training data.
Approach:	They propose a plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search based on Monte Carlo Tree Search and a self-rewarding paradigm to address these limitations.
Outcome:	The proposed method improves the performance of the BM25 retriever and surpasses the baseline of self-reflection in both efficiency and scalability.

Copied to clipboard

Xing Wu, Chaochen Gao, Liangjun Zang, Jizhong Han, Zhongyuan Wang, Songlin Hu

EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction (2022.naacl-main)

Challenge:	a new method for learning unsupervised sentence embeddings is proposed . unsup-SimCSE is biased because of the length information encoded into the sentence embeds .
Approach:	They propose a new unsupervised sentence embedding method that uses dropout to obtain positive pairs from a pre-trained Transformer encoder.
Outcome:	The proposed method outperforms the state-of-the-art unsup-SimCSE on a STS task.

Copied to clipboard

Benfeng Xu, Quan Wang, Yajuan Lyu, Yabing Shi, Yong Zhu, Jie Gao, Zhendong Mao

Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation (P19-1)

Challenge:	Existing studies only explore entity representations, but propose a novel triple perspective for relation extraction.
Approach:	They propose to explicitly introduce relation representation and jointly represent it with entities to identify valid triples.
Outcome:	The proposed method is based on ablations and document-level relation extraction and joint entity and relation extraction.

Copied to clipboard

Cunxiang Wang, Shuailong Liang, Yue Zhang, Xiaonan Li, Tian Gao

HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation (2022.acl-long)

Challenge:	Existing benchmarks measure common sense knowledge indirectly or without reasoning.
Approach:	They propose a benchmark to test whether a system can differentiate natural language statements that make sense from those that do not make sense.
Outcome:	The proposed benchmarks show that models trained on large corpora perform better than humans on some benchmarks.

Copied to clipboard

Zhoujun Cheng, Haoyu Dong, Zhiruo Wang, Ran Jia, Jiaqi Guo, Yan Gao, Shi Han, Jian-Guang Lou, Dongmei Zhang

Learning “O” Helps for Learning More: Handling the Unlabeled Entity Problem for Class-incremental NER (2023.acl-long)

Challenge:	Existing studies on table reasoning focus on flat tables and hierarchical tables . a new dataset, HiTab, aims to examine numerical reasoning over hierarchic tables based on hierarchically structured tables - a strong challenge for existing baselines and a valuable benchmark for future research.
Approach:	They propose a hierarchical question answering and natural language generation dataset to study hierarchic tables.
Outcome:	The proposed model shows that it is effective in QA and natural language generation over hierarchical tables.

Copied to clipboard

Ruotian Ma, Xuanting Chen, Zhang Lin, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yun Wen Chen

TRAC: Token-level Reward Assignment for Coherent Abstractive Summarization (2026.findings-acl)

Challenge:	Existing Named Entity Recognition systems are typically trained on a large-scale dataset with predefined entity classes, then deployed for entity recognition on the test data without further adaptation or refinement.
Approach:	They propose a representation learning method that adaptively detects entity clusters in "O" and two effective distance-based relabeling strategies for better learning the old classes.
Outcome:	The proposed method achieves 10.62% improvement over the baseline methods.

Copied to clipboard

null 陈宣齐, null 容梓莹, Xinfeng Liao, Lianxi Wang, Ying Gao, Shengyi Jiang

Summarization

Challenge:	Large Language Models (LLMs) have achieved remarkable success in text summarization, but maintaining logical coherence and contextual consistency remains a pervasive challenge in long-form generation.
Approach:	They propose a framework that introduces a token-level reward function by integrating relative sentence gain, inter-sentence attention, and a Gaussian length penalty.
Outcome:	The proposed model outperforms the sequence-level baseline by 11.05% in fluency and 10.61% in Relevance.

TTM-RE: Memory-Augmented Document-Level Relation Extraction (2024.acl-long)

Copied to clipboard

Chufan Gao, Xuan Wang, Jimeng Sun

Transformer-Based Direct Hidden Markov Model for Machine Translation (2021.acl-srw)

Challenge:	Existing methods for document-level relation extraction are ineffective in exploiting the full potential of large amounts of training data with varied noise levels.
Approach:	They propose a novel approach that integrates a trainable memory module with a noisy-robust loss function that accounts for the positive-unlabeled setting to unlock the full potential of large-scale noisy training data.
Outcome:	The proposed model outperforms existing methods on a ReDocRED benchmark dataset with an absolute F1 score improvement of over 3%.

Copied to clipboard

Weiyue Wang, Zijian Yang, Yingbo Gao, Hermann Ney

ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom (2025.emnlp-main)

Challenge:	Recent studies have found that word alignments produced by the multi-head cross-attention weights are poor.
Approach:	They propose to introduce the hidden Markov model to the transformer architecture and introduce alignment components while keeping the system monolithic.
Outcome:	The proposed model outperforms the baseline model but is slower in training and decoding.

Copied to clipboard

Jingqi Zhou, Sheng Wang, Jingwei Dong, Kai Liu, Lei Li, Jiahui Gao, Jiyue Jiang, Lingpeng Kong, Chuan Wu

Graph of Trace: Visualizing Execution Traces of Scientific Agents (2026.acl-demo)

Challenge:	Large vision-language models often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.
Approach:	They propose a visual reasoning framework that decouples vision-reasoning capabilities and multi-run proactive perception.
Outcome:	The proposed framework outperforms existing models on benchmarks for open-source and closed-source models with 13.2% performance gain.

Copied to clipboard

Tianci Gao, Haoxuan Li, Jian He Li, Tianxiang Zhao, Shi Runze, Weiran Wang, Zezhao Wu, Lu Mi

FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs (2025.findings-acl)

Challenge:	Scientific AI agents can perform complex research tasks, but these unfolded workflows are difficult for humans to inspect and review, limiting interpretable, controllable and effective human–AI collaboration.
Approach:	They propose a monitoring and visualization framework that records fine-grained execution events and organizes them into a directed graph that makes agent workflows explicit as they proceed.
Outcome:	The proposed framework records intermediate steps (e.g. tool calls and code executions) and renders them as real-time updated visual traces that expose workflow structure.

Copied to clipboard

Zengyi Gao, Yukun Cao, Hairu Wang, Ao Ke, Yuan Feng, S Kevin Zhou, Xike Xie

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)

Challenge:	Existing methods for retrieval-augmented generation struggle with a trade-off between flexibility and retrieval quality.
Approach:	They propose a flexible modular KG-RAG framework that uses query text instead of KGs . they propose to use query text to infer the structural information of reasoning paths .
Outcome:	The proposed method achieves state-of-the-art performance with high efficiency and low resource consumption.

Copied to clipboard

Siyuan Gan, Jiaheng Liu, Boyan Wang, Tianpei Yang, Runqing Miao, Yuyao Zhang, Fanyu Meng, Junlan Feng, Linjian Meng, Jing Huo, Yang Gao

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA (2025.emnlp-main)

Challenge:	Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Approach:	They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Outcome:	The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy.

Copied to clipboard

Zhao Xinjie, Fan Gao, Xingyu Song, Yingjian Chen, Rui Yang, Yanran Fu, Yuyang Wang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics (2025.findings-emnlp)

Challenge:	Multi-hop question answering (QA) is a central challenge in natural language processing . early mistakes can cause errors and undermine the final result, authors say .
Approach:	They propose a reversible multi-agent reasoning framework that backtracks to earlier valid states when conflicts arise.
Outcome:	Empirical evaluation shows that the framework improves on forward-only benchmarks by 6% . the approach enables agents to backtrack to valid states when conflicts arise .

Copied to clipboard

Sheng Jin, Haoming Wang, Zhiqi Gao, Yongbo Yang, Bao Chunjia, Chengliang Wang

Challenge:	Large language models (LLMs) based Agents are increasingly pivotal in simulating complex human systems and interactions.
Approach:	They propose an AI-Agent School system that leverages agents for simulating educational dynamics.
Outcome:	The proposed system can simulate complex educational dynamics in simulated schools.

Context-Aware Conversation Thread Detection in Multi-Party Chat (D19-1)

Copied to clipboard

Ming Tan, Dakuo Wang, Yupeng Gao, Haoyu Wang, Saloni Potdar, Xiaoxiao Guo, Shiyu Chang, Mo Yu

Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer (2022.emnlp-main)

Challenge:	In multi-party chat, it is common for multiple conversations to occur concurrently . a new model that automatically disentangles conversation threads is proposed .
Approach:	They propose a Context-Aware Thread Detection model that automatically disentangles conversation threads in chat logs.
Outcome:	The proposed model outperforms state-of-the-art models on four real-world chat logs.

Copied to clipboard

Zhengbao Jiang, Luyu Gao, Zhiruo Wang, Jun Araki, Haibo Ding, Jamie Callan, Graham Neubig

Know What I don’t Know: Handling Ambiguous and Unknown Questions for Text-to-SQL (2023.findings-acl)

Challenge:	eschewing separate architecture and training for knowledge-intensive tasks is cumbersome . end-to-end training only based on supervision from the end task is awkward .
Approach:	They propose a single Transformer that performs retrieval as attention and end-to-end training solely based on supervision from the end QA task.
Outcome:	The proposed model outperforms state-of-the-art retrievers and readers on in-domain datasets.

Copied to clipboard

Bing Wang, Yan Gao, Zhoujun Li, Jian-Guang Lou

Programming Languages in NLP

Challenge:	Existing text-to-SQL parsers generate a plausible SQL query for arbitrary user questions, thereby failing to handle problematic user questions.
Approach:	They propose a weakly supervised DTE model for error detection, localization, and explanation.
Outcome:	The proposed model achieves the best result on real-world examples and generated examples compared with baselines.

CapOnImage: Context-driven Dense-Captioning on Image (2022.emnlp-main)

Copied to clipboard

Yiqi Gao, Xinglin Hou, Yuanmeng Zhang, Tiezheng Ge, Yuning Jiang, Peng Wang

Raw Pointer Rewriting with LLMs for Translating C to Safer Rust (2026.findings-acl)

Challenge:	Existing image captioning systems generate narrative captions for images, which are spatially detached from the image in presentation.
Approach:	They propose a task called captioning on image which generatesense captions at different locations of the image based on contextual information.
Outcome:	The proposed model achieves the best results in both captioning accuracy and diversity aspects.

Copied to clipboard

Yifei Gao, Chengpeng Wang, Pengxiang Huang, Xuwei Liu, Mingwei Zheng, Xiangyu Zhang

User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems (2025.acl-industry)

Challenge:	C2Rust is a system programming language that enforces strict memory and type safety guarantees.
Approach:	They propose a raw pointer rewriting technique that lifts raw pointers in individual functions to appropriate Rust data structures.
Outcome:	The proposed technique eliminates 18.57% of local raw pointers and improves memory safety on 28 real-world C projects.

Copied to clipboard

Jianling Wang, Yifan Liu, Yinghao Sun, Xuejian Ma, Yueqi Wang, He Ma, Zhengyang Su, Minmin Chen, Mingyan Gao, Onkar Dalal, Ed H. Chi, Lichan Hong, Ningren Han, Haokai Lu

FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)

Challenge:	Large Language Models (LLMs) can be used to broaden user experiences beyond established preferences and reinforce feedback loops.
Approach:	They propose a hierarchical approach that combines hierarchic planning with LLM inference-time scaling to improve recommendation relevancy without compromising novelty.
Outcome:	The proposed approach shows significant gains in both user satisfaction and exploration diversity.

Copied to clipboard

Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen

Subgoal Discovery for Hierarchical Dialogue Policy Learning (D18-1)

Challenge:	Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks.
Approach:	They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings.
Outcome:	The proposed framework achieves the strongest overall performance across all models.

Copied to clipboard

Da Tang, Xiujun Li, Jianfeng Gao, Chong Wang, Lihong Li, Tony Jebara

LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models (2026.acl-industry)

Challenge:	Existing methods to develop dialogue agents for complex tasks require sparse reward signals.
Approach:	They propose a divide-and-conquer approach that exploits the hidden structure of a task . they use subgoals to divide a goal-oriented task into simpler subgoal sets .
Outcome:	The proposed approach performs competitively against state-of-the-art methods that require human-defined subgoals.

Copied to clipboard

Tianchun Li, Haochen Liu, Vishwa Pardeshi, Xingchen Wang, Tianci Liu, Huijun Zhao, Wei Fan, Jing Gao

Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems (2022.findings-acl)

Challenge:	Small language models (SLMs) are promising for real-world deployment but struggle with high-stakes legal reasoning tasks.
Approach:	They propose a diagnostic-driven synthesis framework that extracts and refines reasoning trajectories from a capable teacher via fine-grained prompting and a self-reflective verification is employed to adaptively select the most effective data for the SLM student.
Outcome:	The proposed framework extracts and refines reasoning trajectories from a capable teacher via fine-grained prompting, then a self-reflective verification is employed to adaptively select the most effective data for the student.

Copied to clipboard

Yi-Lin Tuan, Sajjad Beygi, Maryam Fazel-Zarandi, Qiaozi Gao, Alessandra Cervone, William Yang Wang

Self-Evolving GPT: A Lifelong Autonomous Experiential Learner (2024.acl-long)

Challenge:	Existing systems that require extensive labor to process user requests are limited in their reasoning capabilities and require extensive manual effort to design.
Approach:	They propose a method that allows a transformer model to walk on a large-scale knowledge graph to generate responses by reasoning over differentiable knowledge graphs.
Outcome:	The proposed method allows a transformer model to walk on a large-scale knowledge graph to generate responses.

Copied to clipboard

Jinglong Gao, Xiao Ding, Yiming Cui, Jianbai Zhao, Hepeng Wang, Ting Liu, Bing Qin

Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering (2025.acl-long)

Challenge:	Existing approaches to provide LLMs with textual task-solving experience rely on manual efforts to acquire and apply such experience for each task.
Approach:	They propose a lifelong autonomous experiential learning framework based on LLMs that learns and accumulates experience through experience transfer and induction.
Outcome:	The proposed framework performs reliably in each intermediate step and improves GPT-3.5 and GPT-4 on widely used NLP datasets.

Copied to clipboard

Shuzheng Si, Haozhe Zhao, Gang Chen, Cheng Gao, Yuzhuo Bai, Zhitong Wang, Kaikai An, Kangyang Luo, Chen Qian, Fanchao Qi, Baobao Chang, Maosong Sun

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Challenge:	Existing studies show that training LLMs on data containing unfamiliar knowledge during instruction tuning can encourage hallucinations.
Approach:	They propose a framework that measures how familiar the LLM is with instruction data and introduce an expert-aligned reward model to ensure the quality of selected samples.
Outcome:	The proposed framework reduces hallucinations while maintaining a competitive ability to follow instructions.

Copied to clipboard

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination (2026.acl-long)

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Copied to clipboard

Lirong Gao, Zeqing Wang, Yuyan Cai, Jiayi Deng, Yanmei Gu, Yiming Zhang, Jia Zhou, Yanfei Zhang, Junbo Zhao

UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces (2025.acl-long)

Challenge:	Existing benchmarks assess basic knowledge breadth or lexical understanding, failing to capture higher-order skills that are central to historical research.
Approach:	They propose a benchmark anchored in the Chinese Imperial Examination system that assesses historical knowledge and lexical understanding.
Outcome:	The new benchmark aims to assess the ability of LLMs to process historical materials and documents.

Copied to clipboard

Baining Zhao, Jianjie Fang, Zichao Dai, Ziyou Wang, Jirong Zha, Weichen Zhang, Chen Gao, Yue Wang, Jinqiang Cui, Xinlei Chen, Yong Li

RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval (2022.findings-emnlp)

Challenge:	Large multimodal models exhibit remarkable intelligence, yet their embodied cognitive abilities during motion in open-ended urban aerial spaces remain to be explored.
Approach:	They propose a benchmark to evaluate whether large multimodal models can process continuous first-person visual observations like humans.
Outcome:	The proposed model can process first-person visual observations like humans, enabling recall, perception, reasoning, and navigation.

Copied to clipboard

Xing Wu, Chaochen Gao, Zijia Lin, Zhongyuan Wang, Jizhong Han, Songlin Hu

Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation (2022.naacl-main)

Challenge:	sparse sampling of videos suffers from inter-modal redundancy and visual redundancies . et al., 2021) proposes to sparsestly sample frames from videos to alleviate temporal redundance .
Approach:	They propose to use sparse sampling to alleviate temporal redundancy in videos . they propose to penalize high-redundant video patches and text tokens .
Outcome:	The proposed method improves on four benchmark datasets.

Copied to clipboard

Pengzhi Gao, Zhongjun He, Hua Wu, Haifeng Wang

XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection (2024.findings-acl)

Challenge:	BLEU scores of 31.16 for ende and 38.37 for deen on the IWSLT14 dataset, 30.78 for entde, 35.15 for de en and 27.17 for zhen .
Approach:	They propose a bidirectional pretraining and unidirectional finetuning procedure to boost NMT performance.
Outcome:	The proposed method achieves strong translation performance across five datasets.

Copied to clipboard

Yuanhang Yang, Shiyi Qi, Wenchao Gu, Chaozheng Wang, Cuiyun Gao, Zenglin Xu

Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning (2023.findings-emnlp)

Challenge:	XMoE leverages small experts and a threshold-based router to selectively engage only essential parameters.
Approach:	They propose a novel MoE that leverages small experts to selectively engage only essential parameters.
Outcome:	The proposed model can reduce computation load at MoE layers by over 50% without sacrificing performance.

Copied to clipboard

Yougang Lyu, Jitai Hao, Zihan Wang, Kai Zhao, Shen Gao, Pengjie Ren, Zhumin Chen, Fang Wang, Zhaochun Ren

Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)

Challenge:	Existing methods for predicting judgment results for multiple defendants are ineffective.
Approach:	They propose a method to predict the judgment results for each defendant in multi-defendant cases . they formalize the multi-diffendant judgment process as hierarchical reasoning chains .
Outcome:	The proposed method can predict the judgment results for multiple defendants in multi-defendant cases.

Copied to clipboard

Tianqi Wang, Lei Chen, Xiaodan Zhu, Younghun Lee, Jing Gao

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025.acl-long)

Challenge:	Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision.
Approach:	They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible.
Outcome:	The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task.

Copied to clipboard

Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, Yuxing Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng

Is Compound Aspect-Based Sentiment Analysis Addressed by LLMs? (2024.findings-emnlp)

Challenge:	Long-context modeling is crucial for next-generation language models, but high computational cost of standard attention mechanisms poses significant computational challenges.
Approach:	They propose a natively trained Sparse Attention mechanism that integrates algorithms with hardware-aligned optimizations to achieve efficient long-context modeling.
Outcome:	The proposed model maintains or exceeds Full Attention models across general benchmarks, long-context tasks, and instruction-based reasoning.

Copied to clipboard

Yinhao Bai, Zhixin Han, Yuhua Zhao, Hang Gao, Zhuowei Zhang, Xunzhi Wang, Mengting Hu

Split and Merge: Aligning Position Biases in LLM-based Evaluators (2024.emnlp-main)

Challenge:	Aspect-based sentiment analysis (ABSA) aims to predict aspect-based elements from text . large language models (LLMs) have impressive abilities in handling human instructions .
Approach:	They propose a framework to evaluate LLMs' ability to handle complex ABSA tasks . they use constrained prompts to automatically organize the returned predictions .
Outcome:	The proposed framework outperforms supervised methods in some cases, but it is still lacking in other areas.

Copied to clipboard

Zongjie Li, Chaozheng Wang, Pingchuan Ma, Daoyuan Wu, Shuai Wang, Cuiyun Gao, Yang Liu

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)

Challenge:	Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems.
Approach:	They propose an alignment-based system that calibrates position bias in a lightweight yet effective manner by taking into account both length and semantics and combining them into a single prompt.
Outcome:	Extensive experiments with six LLMs on 11,520 answer pairs show that PORTIA significantly improves consistency and consistency rates with humans.

Copied to clipboard

Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song

MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (2026.acl-long)

Challenge:	Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges .
Approach:	They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions.
Outcome:	The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset .

Copied to clipboard

Quyu Kong, Xu Zhang, Zhenyu Yang, Nolan Gao, Chen Liu, Panrong Tong, Chenglin Cai, Hanzhang Zhou, Jianan Zhang, Liangyu Chen, Zhidan Liu, Steven Hoi, Yue Wang

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection (2026.acl-long)

Challenge:	AndroidWorld is the dominant mobile GUI agent evaluation benchmark, but its success rates are low . despite reproducible emulator environment, it lacks key application categories such as e-commerce and enterprise communication.
Approach:	They propose a benchmark for mobile GUI agents that reflects real-world usage through long-horizon, cross-application workflows.
Outcome:	The proposed framework achieves over 90% success rates, while AndroidWorld is the dominant benchmark.

Copied to clipboard

Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen

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

Challenge:	Personalized MGT detection remains largely underexplored due to personalization challenges . large language models (LLMs) can imitate personal writing styles, but they can generate fake news and misinformation.
Approach:	They propose a benchmark to evaluate detector robustness under personalization . they attribute this limitation to a feature-inversion trap that flips the effect in personalized contexts .
Outcome:	The proposed framework predicts detector robustness under personalization with an 85% correlation to actual results.

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

OTExtSum: Extractive Text Summarisation with Optimal Transport (2022.findings-naacl)

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

Peggy Tang, Kun Hu, Rui Yan, Lei Zhang, Junbin Gao, Zhiyong Wang

Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation (2020.findings-emnlp)

Challenge:	Extractive text summarisation aims to select salient sentences from a document to form a short yet informative summary.
Approach:	They propose to formulate extractive text summarisation as an Optimal Transport (OT) problem and use it to obtain an optimal summary that minimises the transportation cost to a given document.
Outcome:	The proposed method outperforms state-of-the-art methods and learning-based methods on multiNews, PubMed, BillSum, and CNN/DM datasets.

Copied to clipboard

Luyu Gao, Xinyi Wang, Graham Neubig

Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization (2023.emnlp-industry)

Challenge:	Multilingual data is more beneficial for NMT models that translate from the LRL to a target language than those that translate into the LLLs.
Approach:	They propose a decoder that embeds character n-grams into NMT models that translate from an LRL to a target language.
Outcome:	The proposed decoder improves the performance of NMT models that translate from an LRL to a target language.

Copied to clipboard

Pengzhi Gao, Liwen Zhang, Zhongjun He, Hua Wu, Haifeng Wang

CEDAR: A Chinese Evaluation Dataset for Computational Argumentation (2026.acl-long)

Challenge:	Experimental results on multilingual similarity search and bitext mining tasks show the effectiveness of our approach.
Approach:	They propose a multilingual sentence representation model that aligns different languages in a shared representation space.
Outcome:	The proposed model performs better than LASER3 on similarity searches and bitext mining tasks.

Copied to clipboard

Tian Lan, Jiang Li, Rong Yan, Feilong Bao, Weihua Wang, Guanglai Gao, Xiangdong Su

Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation (2025.acl-industry)

Challenge:	Existing debate datasets neglect important labels for argument mining, generation, and evaluation.
Approach:	They propose a Chinese Evaluation Dataset for Computational Argumentation that includes key arguments and key rhetorical figures, debater roles, modal words, debate results and transcripts.
Outcome:	The proposed dataset covers 600 debates about 318 topics from Chinese debate competitions.

Copied to clipboard

Shuxian Bi, Chongming Gao, Wenjie Wang, Yueqi Mou, Chenxu Wang, Tang Biao, Peng Yan, Fuli Feng

Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling (2024.findings-acl)

Challenge:	Existing methods fail to reconcile click-through rate (CTR) optimization with topic expansion.
Approach:	They propose a query generation framework that aligns click-through rate and topic expansion goals through an online DPO paradigm.
Outcome:	The proposed approach achieves significant CTR gains (+2.3%) and higher human-rated query quality compared to state-of-the-art methods.

Copied to clipboard

Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang

Challenge:	Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents.
Approach:	They propose a cognitive framework that incorporates first-order and second-order perspective transitions into LLMs to enhance their ability to identify and counteract deceptive information.
Outcome:	The proposed framework enhances LLMs’ ability to identify and counteract deceptive information without extra fine-tuning and data.

Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation (2025.coling-main)

Copied to clipboard

Weihua Wang, Qiuyu Liang, Feilong Bao, Guanglai Gao

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models (2024.findings-emnlp)

Challenge:	Existing knowledge graph embedding models measure the plausibility of triplets either through semantic matching or distance scoring functions.
Approach:	They propose to combine semantic matching with entity’s geometric distance to better measure the plausibility of triplets.
Outcome:	The proposed model outperforms existing models on well-known knowledge graph completion benchmark datasets.

Copied to clipboard

Shitian Zhao, Renrui Zhang, Xu Luo, Yan Wang, Shanghang Zhang, Peng Gao

Entropy-based Exploration Conduction for Multi-step Reasoning (2025.findings-acl)

Challenge:	Existing multi-modal language models with different architectures, parameter sizes, training datasets, and pipelines exhibit varying strengths across different tasks.
Approach:	They propose a framework for fusing heterogeneous models off-the-shell, which they call likelihood composition, and introduce basic operations to compose multiple models’ likelihood distribution when doing a multi-choice visual-question-answering task.
Outcome:	The proposed framework can be used to fusing heterogeneous models off-the-shell.

Copied to clipboard

Jinghan Zhang, Xiting Wang, Fengran Mo, Yeyang Zhou, Wanfu Gao, Kunpeng Liu

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Challenge:	Existing methods to automatically decide the depth of exploration of the reasoning procedure lead to high cost and a lack of flexibility.
Approach:	They propose a method that dynamically adjusts the exploration depth during multi-step reasoning by monitoring LLM’s output entropy and variance entropic.
Outcome:	The proposed method captures the uncertainty of the current step and the fluctuation of uncertainty across consecutive reasoning steps and then selects whether to deepen, expand, or stop exploration according to the probability.

Copied to clipboard

Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory (2025.acl-long)

Challenge:	Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach:	They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome:	The proposed framework outperforms baseline methods in real-time and in real applications.

Copied to clipboard

Wei Song, Zhenya Huang, Cheng Cheng, Weibo Gao, Bihan Xu, GuanHao Zhao, Fei Wang, Runze Wu

Linguistic Theories

Challenge:	Large language models have demonstrated exceptional performance across a wide range of tasks . however, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance and cost.
Approach:	They propose a multi-LLM routing framework that efficiently routes user queries to the most suitable LLM.
Outcome:	The proposed framework outperforms baseline methods in terms of effectiveness and interpretability.

Macedon: Minimizing Representation Coding Rate Reduction for Cross-Lingual Natural Language Understanding (2023.findings-emnlp)

Copied to clipboard

Haoyu Wang, Yaqing Wang, Huaxiu Yao, Jing Gao

Guiding AMR Parsing with Reverse Graph Linearization (2023.findings-emnlp)

Challenge:	Existing approaches to learn cross-lingual models require limited data to perform cross-linguistic tasks.
Approach:	They propose a method to remove language-associated information via minimizing representation coding rate reduction.
Outcome:	The proposed model outperforms state-of-the-art models on cross-lingual tasks.

Copied to clipboard

Bofei Gao, Liang Chen, Peiyi Wang, Zhifang Sui, Baobao Chang

UNIMO-2: End-to-End Unified Vision-Language Grounded Learning (2022.findings-acl)

Challenge:	Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a sentence.
Approach:	They propose a new framework that allows for reversed linearization of AMR graphs . they propose to combine sequence-to-sequence approaches with a linearized graph .
Outcome:	The proposed framework outperforms the best AMR parser by 0.8 and 0.5 Smatch scores on the AMR 2.0 and AMR 3.0 datasets.

Copied to clipboard

Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, Haifeng Wang

Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification (2023.acl-long)

Challenge:	Existing methods for vision-language pre-training can only learn from aligned image-caption data and rely heavily on expensive regional features.
Approach:	They propose an end-to-end unified-modal pre-training framework for joint learning . they propose to conduct grounded learning on both images and texts via a sharing grounded space .
Outcome:	The proposed model improves visual and visual semantic alignment on images and texts.

Copied to clipboard

Ke Ji, Yixin Lian, Jingsheng Gao, Baoyuan Wang

KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering (2022.emnlp-main)

Challenge:	Existing work on the hierarchical text classification problem is limited due to the complexity of label hierarchy and intensive labeling cost.
Approach:	They propose a path-based few-shot setting and a strict path-basic evaluation metric to further explore few- shot HTC tasks.
Outcome:	The proposed framework outperforms those who inject hierarchy through graph encoders on three popular HTC datasets under the few-shot setting.

Copied to clipboard

Jianing Wang, Chengyu Wang, Minghui Qiu, Qiuhui Shi, Hongbin Wang, Jun Huang, Ming Gao

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection (2025.acl-long)

Challenge:	Extractive Question Answering (EQA) is one of the most essential tasks in Machine Reading Comprehension (MRC).
Approach:	They propose a framework that transforms extractive question answering into a non-autoregressive Masked Language Modeling (MLM) generation problem.
Outcome:	The proposed framework outperforms state-of-the-art approaches in few-shot learning scenarios by a large margin.

Copied to clipboard

Mingyu Derek Ma, Yanna Ding, Zijie Huang, Jianxi Gao, Yizhou Sun, Wei Wang

Challenge:	Existing work has been using decoding-free candidate selection methods to obtain candidate probability from initial output logits over vocabulary.
Approach:	They propose to evaluate a set of tasks using decoding-free candidate selection methods on a comprehensive set of questions.
Outcome:	The proposed methods are evaluated on a set of tasks including five multiple-choice QA tasks with a small candidate pool and four clinical decision tasks with 10k+ options.

Combating Label Sparsity in Short Text Topic Modeling via Nearest Neighbor Augmentation (2024.findings-acl)

Copied to clipboard

Yang Lin, Xinyu Ma, Xin Gao, Ruiqing Li, Yasha Wang, Xu Chu

From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning (2024.findings-acl)

Challenge:	Existing topic models suffer from poor performance when applied to short text contents due to the limited length of a single topic.
Approach:	They propose a neural short text topic model that augments reconstruction labels with k-nearest documents to complement relevant but unobserved words.
Outcome:	The proposed model outperforms the state-of-the-art models on multiple public short-text datasets and can derive high-quality topics and document representations.

Copied to clipboard

Feng Zhang, Wei Chen, Fei Ding, Meng Gao, Tengjiao Wang, Jiahui Yao, Jiabin Zheng

AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant (2022.findings-emnlp)

Challenge:	Existing studies fine-tune discriminative models on specific defined intent classes, preventing them from being directly adopted to new intent domains.
Approach:	They propose to use a pre-trained generative intent model to detect new intents from different domains with no parameter updates.
Outcome:	The proposed model outperforms baselines that need further fine-tuning or domain-specific samples.

Copied to clipboard

Weixian Lei, Difei Gao, Yuxuan Wang, Dongxing Mao, Zihan Liang, Lingmin Ran, Mike Zheng Shou

AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)

Challenge:	Currently, personal AI assistants on the phone and AR glasses can assist our daily life in addressing our questions like "how to adjust the date for this watch?"
Approach:	They propose a task that asks a question about affordance of items in our daily life . they construct a dataset that contains 3.2k multimodal questions on 1.6k video segments .
Outcome:	The proposed task outperforms baseline methods while still having room for improvement in the future.

Copied to clipboard

Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E

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

Challenge:	AEGIS examines whether current models can effectively audit AI-generated images in academic papers.
Approach:	They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics.
Outcome:	AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis.

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.

Code Reffix: A Benchmark for Reflection-Guided Code Repair with Large Language Models (2026.findings-acl)

Copied to clipboard

Zaiyuan Di, Jianting Chen, Yunxiao Yang, Xiaoying Gao, Li Yang, Zhihao Wang, Yang Xiang

Enhancing Machine Translation with Self-Supervised Preference Data (2025.acl-long)

Challenge:	Existing benchmarks focus on the repair generation capability of LLMs, lacking fine-grained evaluation of reflection.
Approach:	They propose a benchmark with oracle reflections and a dual-task protocol to decouple evaluation of reflection from repair.
Outcome:	The proposed benchmarks show that underperforming reflection capabilities remain a bottleneck for code repair.

Copied to clipboard

Haoxiang Sun, Ruize Gao, Pei Zhang, Baosong Yang, Rui Wang

FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph (2023.acl-industry)

Challenge:	Current approaches to constructing preference data rely on human annotations.
Approach:	They propose a framework which efficiently constructs translation preference data for iterative training.
Outcome:	The proposed framework improves translation preference data on large language models.

Copied to clipboard

Xiaodan Wang, Chengyu Wang, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, Ming Gao

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models (2025.coling-main)

Challenge:	Recent advances in visual-language pre-trained (VLP) models have greatly improved cross-modal retrieval performance . however, the fine-grained interactions between objects from different modalities are far from well-established . e-commerce domain lacks sufficient training data and fine-granular cross-modulal knowledge .
Approach:	They propose a visual-language pre-trained (VLP) image-text retrieval model that integrates cross-modal knowledge into the model to improve performance.
Outcome:	The proposed model improves performance on e-commerce image-text retrieval task by a large margin.

Copied to clipboard

Zihui Wu, Haichang Gao, Jianping He, Ping Wang

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)

Challenge:	Large language models (LLMs) have remarkable capabilities, but their security implications have been overlooked.
Approach:	They propose a “jailbreak function” attack method that exploits alignment discrepancies, user coercion, and the absence of rigorous safety filters.
Outcome:	The proposed attack exploits alignment discrepancies, user coercion, and the absence of rigorous safety filters on six state-of-the-art LLMs.

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

SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)

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

Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang

TIGEr: Text-to-Image Grounding for Image Caption Evaluation (D19-1)

Challenge:	Large language models (LLMs) have many advantages but they also pose significant safety risks.
Approach:	They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions .
Outcome:	The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets.

Copied to clipboard

Ming Jiang, Qiuyuan Huang, Lei Zhang, Xin Wang, Pengchuan Zhang, Zhe Gan, Jana Diesner, Jianfeng Gao

TemplateGEC: Improving Grammatical Error Correction with Detection Template (2023.acl-long)

Challenge:	Existing metrics based on text-level comparisons fail to assess the quality of captions produced by machines.
Approach:	They propose to use a machine-learned text-image grounding model to measure the accuracy of machine-generated captions and their correlation with human judgments.
Outcome:	The proposed metric has higher consistency with human judgments and is more accurate than existing metrics.

Copied to clipboard

Yinghao Li, Xuebo Liu, Shuo Wang, Peiyuan Gong, Derek F. Wong, Yang Gao, Heyan Huang, Min Zhang

Syntactic Text Processing

Challenge:	Existing methods for grammatical error correction (GEC) have been developed.
Approach:	They propose a method which integrates the detection labels from a Seq2Edit model to construct a template as the input.
Outcome:	The proposed method can perform human-in-the-loop error correction tasks.

Towards Adapting Open-Source Large Language Models for Expert-Level Clinical Note Generation (2025.findings-acl)

Copied to clipboard

Hanyin Wang, Chufan Gao, Bolun Liu, Qiping Xu, Guleid Hussein, Mohamad El Labban, Kingsley Iheasirim, Hariprasad Reddy Korsapati, Chuck Outcalt, Jimeng Sun

Mixup Decoding for Diverse Machine Translation (2021.findings-emnlp)

Challenge:	Proprietary Large Language Models (LLMs) have demonstrated promising capabilities in clinical text summarization tasks.
Approach:	They propose a domain- and task-specific adaptation process for an open-source LLaMA-2 model . LLama-2 can generate high-quality clinical notes from outpatient patient-doctor dialogues .
Outcome:	The proposed model can generate clinical notes comparable to those authored by physicians.

Copied to clipboard

Jicheng Li, Pengzhi Gao, Xuanfu Wu, Yang Feng, Zhongjun He, Hua Wu, Haifeng Wang

Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization (2023.findings-acl)

Challenge:	Existing methods for generating multiple translations for source and target languages neglect the one-to-many mapping between the source and the target languages.
Approach:	They propose a method to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding.
Outcome:	Experiments on WMT’16 en-ro, WMT'14 en de, and WMT ‘17 zh-en show that the proposed method outperforms all previous diverse machine translation methods.

Copied to clipboard

Pengzhi Gao, Liwen Zhang, Zhongjun He, Hua Wu, Haifeng Wang

GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling (2025.findings-acl)

Challenge:	Existing methods to improve zero-shot translation performance by learning language-agnostic representations and maximizing cross-lingual transfer have been proposed.
Approach:	They propose a cross-lingual consistency regularization to bridge the representation gap between different languages and boost zero-shot translation performance.
Outcome:	The proposed model improves translation performance on low-resource and high-res benchmarks and closes the sentence representation gap and aligns the representation space.

Copied to clipboard

Hao Fang, Yuejie Zhang, Rui Feng, Yingwen Wang, Qing Wang, Wen He, Xiaobo Zhang, Tao Zhang, Shang Gao

WebSynthesis: World Model-Guided Monte Carlo Tree Search for Efficient WebAgent Trajectory Synthesis (2026.acl-long)

Challenge:	Document-level relation extraction (DocRE) solves problems of document quality . number of entities and entity-pair relations increases, causing incomplete annotations .
Approach:	a framework that reduces the problem space using a graph-enhanced Transformer-based model is proposed . GLiM leverages large language models for reasoning to reduce the problem-space .
Outcome:	GLiM boosts average recall and F1 scores on biomedical datasets . compared with existing models, GLim outperforms existing models on biomedicine benchmarks compared to existing models .

Copied to clipboard

Yifei Gao, Junhong Ye, Yifan Yang, Jiaqi Wang, Yi Zhang, Zhang Ruichen, Jitao Sang

SynthAgent: Adapting Web Agents with Synthetic Supervision (2026.acl-long)

Challenge:	Recent advances in large language models have enabled increasingly capable web agents . however, training such agents at scale still relies on high-quality interaction trajectories that are difficult to obtain at scale.
Approach:	They propose a framework for scalable trajectory synthesis that simulates state transitions without network dependencies and integrates Monte Carlo Tree Search to enable reversible exploration over the simulated state space.
Outcome:	Experiments on WebArena, WebVoyager, and Mind2Web-Online show that agents trained exclusively on synthesized trajectories outperform those trained on real-world data.

Copied to clipboard

Zhaoyang Wang, Yiming Liang, Xuchao Zhang, Qianhui Wu, Siwei Han, Anson Bastos, Rujia Wang, Chetan Bansal, Baolin Peng, Jianfeng Gao, Saravan Rajmohan, Huaxiu Yao

InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment (2024.findings-acl)

Challenge:	Existing studies have focused on synthetic supervision but have encountered data quality issues.
Approach:	They propose a fully synthetic supervision framework that aims at improving data quality via dual refinement of both tasks and trajectories.
Outcome:	The proposed framework outperforms existing methods on standardized benchmarks and shows promising results on a standardized test.

Copied to clipboard

Jianing Wang, Junda Wu, Yupeng Hou, Yao Liu, Ming Gao, Julian McAuley

Proactive Guidance of Multi-Turn Conversation in Industrial Search (2025.acl-industry)

Challenge:	Existing large language models (LLMs) can solve graph reasoning and generation tasks with parameter updates without sacrificing performance.
Approach:	They propose a structured format verbalizer to unify all graph data into a universal code-like format, which can simply represent the graph without any external graph-specific encoders.
Outcome:	The proposed framework outperforms GPT-4 and LLaMA2 in graph reasoning and generation tasks by more than 13% and 38%, respectively.

Copied to clipboard

Xiaoyu Li, Xiao Li, Li Gao, Yiding Liu, Xiaoyang Wang, Shuaiqiang Wang, Junfeng Wang, Dawei Yin

FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have advanced multi-turn conversation systems, emphasizing the need for proactive guidance to enhance users’ interactions.
Approach:	They propose a goal-adaptive supervised fine-tuning framework that generates proactive guidance for users to click for the next turn of the conversation.
Outcome:	The proposed framework achieves 86.10% accuracy in offline evaluation (+23.95% over baseline) and 25.28% CTR in online deployment (149.06% relative improvement).

Copied to clipboard

Hengxing Cai, Jinhan Dong, Jingjun Tan, Jingcheng Deng, Sihang Li, Zhifeng Gao, Haidong Wang, Zicheng Su, Agachai Sumalee, Renxin Zhong

SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation (2026.findings-acl)

Challenge:	Existing methods for vision-and-language navigation struggle with insufficient multimodal fusion, weak generalization, and poor interpretability.
Approach:	They propose a framework for UAV vision-and-language navigation that integrates natural language instructions with visual observations to improve multimodal fusion and interpretability.
Outcome:	The proposed framework achieves state-of-the-art performance across all scenarios, with a 9.22% higher success rate than the strongest baseline in unseen environments.

Copied to clipboard

Gengyang Li, Wang Cai, Yifeng Gao, Yunfang Wu

Is Your LLM Outdated? A Deep Look at Temporal Generalization (2025.naacl-long)

Challenge:	Large language models (LLMs) achieve strong reasoning with Chain-of-Thought prompting, but long and redundant traces substantially increase inference cost.
Approach:	They propose a training-free and plug-and-play decoding method that reduces CoT overhead without modifying model weights.
Outcome:	Experiments on GSM8K, MMLU, GPQA, and BBH show that SyncThink achieves 62.00% average Top@1 accuracy using 656 generated tokens and 28.68s latency, compared to 61.22%, 2141 tokens, and 92.01s for full CoT decoding.

Copied to clipboard

ChenghaoZhu ChenghaoZhu, Nuo Chen, Yufei Gao, Yunyi Zhang, Prayag Tiwari, Benyou Wang

Challenge:	Existing methods to evaluate large language models are limited due to their inherent dynamic nature and the inherent dynamicity of language and information.
Approach:	They introduce a new evaluation framework that employs fresh text and event prediction for assessing LLMs’ temporal adaptability.
Outcome:	The proposed framework shows significant temporal biases and a decline in performance over time.

Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)

Copied to clipboard

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li

LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating (2025.acl-long)

Challenge:	Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate .
Approach:	They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module.
Outcome:	The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks .

Copied to clipboard

Chao Deng, Jiale Yuan, Pi Bu, Peijie Wang, Zhong-Zhi Li, Jian Xu, Xiao-Hui Li, Yuan Gao, Jun Song, Bo Zheng, Cheng-Lin Liu

Controllable Memorization in LLMs via Weight Pruning (2025.emnlp-main)

Challenge:	Existing document understanding benchmarks only handle a small number of pages . existing models are limited to handling only a limited number of documents .
Approach:	They propose a long document understanding benchmark that integrates three primary tasks and 20 sub-tasks based on different primary tasks.
Outcome:	The proposed model outperforms existing benchmarks on open-source and closed-source models . the model outpersforms other models on more than 33,000 pages of documents .

Copied to clipboard

Chenjie Ni, Zhepeng Wang, Runxue Bao, Shangqian Gao, Yanfu Zhang

Challenge:	Existing studies have focused on mitigating memorization, but the deliberate control of memorisation has been underexplored.
Approach:	They propose a gradient-based weight pruning framework to control memorization rates in large language models by fine-grained control over pruning parameters.
Outcome:	The proposed framework enables models to suppress or enhance memorization based on application-specific requirements.

Word Form Matters: LLMs’ Semantic Reconstruction under Typoglycemia (2025.findings-acl)

Copied to clipboard

Chenxi Wang, Tianle Gu, Zhongyu Wei, Lang Gao, Zirui Song, Xiuying Chen

Challenge:	Typoglycemia is a phenomenon where people can read words even when the middle letters of the words are scrambled.
Approach:	They propose a reliable metric to quantify the degree of semantic reconstruction and validate its effectiveness.
Outcome:	The proposed metric quantifies the degree of semantic reconstruction and validates its effectiveness.

Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances (2024.acl-long)

Copied to clipboard

Hanlei Zhang, Hua Xu, Fei Long, Xin Wang, Kai Gao

New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs (2026.acl-long)

Challenge:	Existing methods for semantics discovery focus on text, video, and audio, failing to leverage the rich multimodal information in the real world.
Approach:	They propose a method to construct augmentation views for multimodal data and use them to perform pre-training to establish well-initialized representations for subsequent clustering.
Outcome:	The proposed method improves on benchmark multimodal intent and dialogue act datasets by 2-6% over state-of-the-art methods.

Copied to clipboard

Shiyao Cui, QingLin Zhang, Di Wang, Yida Lu, Zhexin Zhang, Jinhua Gao, Jinglin Yang, Min He, Han Qiu, Minlie Huang

Universal Prompt Optimizer for Safe Text-to-Image Generation (2024.naacl-long)

Challenge:	Neologisms can foster new linguistic consensus by stabilizing shared meanings and usage in common communicative norms.
Approach:	They propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms . they propose 'SeTox' framework that integrates real-time web context for naeologim detection .
Outcome:	The proposed framework outperforms large-scale models in detecting neologism toxicity.

Copied to clipboard

Zongyu Wu, Hongcheng Gao, Yueze Wang, Xiang Zhang, Suhang Wang

An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation (2024.naacl-long)

Challenge:	Existing studies based on image checker, model fine-tuning and embedding blocking are impractical in real-world applications.
Approach:	They propose a novel reward function measuring toxicity and text alignment of generated images and train the optimizer through Proximal Policy Optimization.
Outcome:	The proposed model reduces the likelihood of various models in generating inappropriate images, with no significant impact on text alignment.

Copied to clipboard

Pengzhi Gao, Ruiqing Zhang, Zhongjun He, Hua Wu, Haifeng Wang

Pass-Tuning: Towards Structure-Aware Parameter-Efficient Tuning for Code Representation Learning (2023.findings-emnlp)

Challenge:	Existing methods for speech-to-text translation (ST) have achieved impressive supervised and zero-shot performance.
Approach:	They propose to use consistency regularization methods to boost end-to-end (E2E) speech-totext translation (ST) by regularizing the intra-modal consistency instead of the modality gap.
Outcome:	The proposed training strategies achieve state-of-the-art (SOTA) performance in most translation directions.

Copied to clipboard

Nuo Chen, Qiushi Sun, Jianing Wang, Xiang Li, Ming Gao

AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning (2022.emnlp-main)

Challenge:	Code pre-trained models have been proposed and widely applied in the domain of code intelligence.
Approach:	They propose a method that uses a plug-and-play graph neural network module as a tunable prefix to exploit structural information of source code.
Outcome:	The proposed method exploits structural information of source code and could replace full fine-tuning.

Copied to clipboard

Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao

Human-Agent Collaborative Paper-to-Page Crafting (2026.findings-acl)

Challenge:	Standard fine-tuning of large pre-trained language models requires updating hundreds of millions to billions of parameters and storing a large copy of the PLM weights for every task.
Approach:	They propose a parameter-efficient fine-tuning technique where small trainable components are injected into the PLM and updated during fine-uning.
Outcome:	The proposed method outperforms SOTA parameter-efficient fine-tuning and full model fine-uning on GLUE development set with RoBERTa-large encoder.

Copied to clipboard

Qianli Ma, Siyu Wang, Chen Yilin, Yinhao Tang, Yixiang Yang, Chang Guo, Bingjie Gao, Zhening Xing, Yanan Sun, Zhipeng Zhang

Challenge:	Existing approaches to create project pages from academic papers have focused on static slides and posters, but the dynamic nature of webpages remains an unaddressed challenge.
Approach:	They propose a novel multi-agent system that deconstructs paper-to-page creation into a coarse-to fine pipeline from narrative planning to multimodal content generation and interactive rendering.
Outcome:	The proposed system generates high-quality, visually appealing pages in under 15 minutes for less than $0.1 .

Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learning (2025.findings-acl)

Copied to clipboard

Bofei Gao, Yejie Wang, Yibo Miao, Ruoyu Wu, Feifan Song, Longhui Yu, Tianyu Liu, Baobao Chang

AdaptFlow: Adaptive Workflow Optimization via Meta-Learning (2025.findings-emnlp)

Challenge:	Long-CoT reasoning and reinforcement learning are demonstrating remarkable performance and scalability, however, there is a lack of systematic guidelines for obtaining a better initial policy model.
Approach:	They propose a systematic guideline and a novel Re-RFT method to obtain more efficient reasoning patterns from different initial models.
Outcome:	The proposed method surpasses DeepSeek-R1-Distill-Qwen-14B model by 4.6%, demonstrating its effectiveness and superiority.

Copied to clipboard

Runchuan Zhu, Bowen Jiang, Lingrui Mei, Fangkai Yang, Lu Wang, Haoxiang Gao, Fengshuo Bai, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics (2025.acl-long)

Challenge:	Existing approaches to large language models rely on static templates or manual workflows.
Approach:	AdaptFlow is a language-based meta-learning framework inspired by model-agnostic meta- learning.
Outcome:	AdaptFlow outperforms manual and automated workflows on question answering, code generation and mathematical reasoning benchmarks.

Copied to clipboard

Wenrui Xu, Dalin Lyu, Weihang Wang, Jie Feng, Chen Gao, Yong Li

OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)

Challenge:	Existing studies assessing the spatial abilities of VLMs lack a solid theoretical foundation and lack measurable data.
Approach:	They propose a psychometric framework defining five basic spatial abilities in Visual Language Models.
Outcome:	The proposed framework defines five basic spatial abilities in Visual Language Models (VLMs) it provides a comprehensive evaluation benchmark and methodological perspective for embodied AI development .

Copied to clipboard

He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou

Clear Up Confusion: Iterative Differential Generation for Fine-grained Intent Detection with Contrastive Feedback (2025.coling-main)

Challenge:	a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say .
Approach:	They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible .
Outcome:	The proposed framework achieves state-of-the-art performance among open-source projects.

Copied to clipboard

Feng Zhang, Wei Chen, Meng Gao, Fei Ding, Tengjiao Wang, Jiahui Yao, Jiabin Zheng

SCOTT: Self-Consistent Chain-of-Thought Distillation (2023.acl-long)

Challenge:	Recent studies on fine-grained intent detection have focused on collecting large-scale and high-quality samples via crowdsourcing resulting in data scarcity.
Approach:	They propose an iterative differential generation framework with contrastive feedback to generate high-quality pseudo samples and accurately capture the crucial nuances in target class distribution.
Outcome:	The proposed framework generates high-quality pseudo samples and captures crucial nuances in target class distribution.

Copied to clipboard

Peifeng Wang, Zhengyang Wang, Zheng Li, Yifan Gao, Bing Yin, Xiang Ren

Tunable LLM-based Proactive Recommendation Agent (2025.acl-long)

Challenge:	Large language models (LMs) generate free-text rationales for their predictions via chain-of-thought prompting, but there is little guarantee that the generated rationale is consistent with LM’s predictions or faithfully justify the decisions.
Approach:	They propose a faithful knowledge distillation method to learn a small, self-consistent CoT model from a larger teacher model by contrastive decoding.
Outcome:	The proposed method yields comparable performance but is less faithful than baselines.

Copied to clipboard

Mingze Wang, Chongming Gao, Wenjie Wang, Yangyang Li, Fuli Feng

Challenge:	Current methods focus on catering to existing user interests, leading to polarized recommendation distributions.
Approach:	They propose an LLM-based Actor-Critic Agent framework to cultivate latent interests through multi-step recommendations.
Outcome:	The proposed framework optimizes long-term rewards and dynamically evolves with user feedback.

DialogueTRM: Exploring Multi-Modal Emotional Dynamics in a Conversation (2021.findings-emnlp)

Copied to clipboard

Yuzhao Mao, Guang Liu, Xiaojie Wang, Weiguo Gao, Xuan Li

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)

Challenge:	Existing studies focus on the self and inter-personal dependencies in multi-modal conversations, but they ignore the temporal and spatial dependencies.
Approach:	They propose a Dialogue Transformer for simultaneously modeling the intra-modal and inter-modal emotion dynamics.
Outcome:	The proposed models outperform the state-of-the-art on three benchmark datasets.

Copied to clipboard

Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios (2024.findings-acl)

Challenge:	Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL).
Approach:	They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.
Outcome:	The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.

Copied to clipboard

Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, Qun Liu

ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design (2026.findings-acl)

Challenge:	Existing benchmarks focus on simple synthesized queries that do not reflect real-world complexity, thereby offering limited perspectives in evaluating tool utilization.
Approach:	They propose a benchmark to evaluate LLMs’ ability in tool utilization within real-world scenarios.
Outcome:	The proposed benchmark improves LLMs’ ability in tool utilization within real-world scenarios and eliminates the restriction of pre-defined toolset.

Copied to clipboard

Yutang Ge, Guojiang Zhao, Sihang Li, Zheng Cheng, Zifeng Zhao, Hanchen Xia, Guolin Ke, Linfeng Zhang, Zhifeng Gao, Yu Guang Wang

Challenge:	Recent deep generative models have already shown encouraging * Equal contribution.
Approach:	They propose to use generic instruction-tuned LLMs as direct text-to-sequence generators to achieve this goal.
Outcome:	Recent studies show that reflection improves sequence quality and alignment while maintaining competitive foldability.

Lock on Target! Precision Unlearning via Directional Control (2025.findings-emnlp)

Copied to clipboard

Yuntao Wen, Ruixiang Feng, Feng Guo, Yifan Wang, Ran Le, Yang Song, Shen Gao, Shuo Shang

Challenge:	Existing methods for unlearning harmful, sensitive, or outdated knowledge suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting degrades the model’s general capabilities.
Approach:	They propose a method that identifies and leverages a targeted "unlearning direction" in the model's parameter space and selectively updates along this direction.
Outcome:	Experiments show that the proposed method achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities.

CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis (2025.findings-acl)

Copied to clipboard

Junying Chen, Chi Gui, Anningzhe Gao, Ke Ji, Xidong Wang, Xiang Wan, Benyou Wang

IoTMigrator: LLM-driven Embedded IoT Code Migration across Different OSes for Cloud-device Integration (2025.findings-emnlp)

Challenge:	Existing large language models (LLMs) are proving to be effective in medical automatic diagnosis, but their interpretability remains unaddressed.
Approach:	They propose to use a "Chain-of-Diagnosis" approach to enhance the interpretability of medical automatic diagnosis by outputting the disease confidence distribution.
Outcome:	The proposed model outperforms other LLMs on automatic diagnostic tasks across three real-world benchmarks and provides interpretability while ensuring controllability in diagnostic rigor.

Copied to clipboard

null Yq, Kaijie Gong, Yi Gao, Hao Wang, Wei Dong

Challenge:	Neither outline-based code generation nor common code translation techniques can adequately address this challenge, despite their prevalence in existing systems.
Approach:	They have developed an algorithm that employs a multi-agent pipeline to handle embedded code migration under the TSL paradigm.
Outcome:	The proposed algorithm outperforms the baseline by 50.5% for pass rate and 13.0% for completeness across all tasks in RIOT and Zephyr.

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service (2025.acl-long)

Copied to clipboard

Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei Ye, Kuofeng Gao, Yi Huang, Yuan Yao

Smoothed Contrastive Learning for Unsupervised Sentence Embedding (2022.coling-1)

Challenge:	Existing studies evaluate efficiency robustness of vision-language models under unrealistic assumptions, requiring access to model architecture and parameters.
Approach:	They propose a novel approach to evaluate VLM efficiency robustness in a realistic black-box setting.
Outcome:	The proposed approach generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%.

Copied to clipboard

Xing Wu, Chaochen Gao, Yipeng Su, Jizhong Han, Zhongyuan Wang, Songlin Hu

ToMELP: A Theory-of-Mind Benchmark for Route-Controlled Persuasion under the Elaboration Likelihood Model (2026.findings-acl)

Challenge:	Unsupervised contrastive sentence embedding models use InfoNCE loss function . increasing batch size leads to performance degradation when it exceeds threshold .
Approach:	They propose a simple smoothing strategy upon the InfoNCE loss function to reduce the number of false-negative pairs in a batch without increasing the batch size.
Outcome:	The proposed smoothing strategy improves unsupervised SimCSE on semantic similarity tasks.

Copied to clipboard

Ruirui Wang, Haoran Zhang, Tian Lan, Zehua Duo, Jiang Li, Guanglai Gao, Xiangdong Su

Linguistics & Cognitive NLP

Challenge:	Theory of Mind (ToM) is widely regarded as central to effective persuasion, yet existing evaluations fail to capture the infer–apply loop that arises in real-world dialogue.
Approach:	They propose a benchmark that conditions on the audience persona p and the Elaboration Likelihood Model (ELM) route r within persuasive conversations.
Outcome:	The proposed model can model the interlocutor's mental states over multiple turns and adapt strategy and tone accordingly.

SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages (2024.emnlp-main)

Copied to clipboard

Holy Lovenia, Rahmad Mahendra, Salsabil Akbar, Lester James Miranda, Jennifer Santoso, Elyanah Aco, Akhdan Fadhilah, Jonibek Mansurov, Joseph Marvin Imperial, Onno Kampman, Joel Moniz, Muhammad Habibi, Frederikus Hudi, Jann Montalan, Ryan Hadiwijaya, Joanito Lopo, William Nixon, Börje Karlsson, James Jaya, Ryandito Diandaru, Yuze Gao, Patrick Irawan, Bin Wang, Jan Christian Blaise Cruz, Chenxi Whitehouse, Ivan Parmonangan, Maria Khelli, Wenyu Zhang, Lucky Susanto, Reynard Ryanda, Sonny Hermawan, Dan Velasco, Muhammad Kautsar, Willy Hendria, Yasmin Moslem, Noah Flynn, Muhammad Adilazuarda, Haochen Li, Johanes Lee, R. Damanhuri, Shuo Sun, Muhammad Qorib, Amirbek Djanibekov, Wei Qi Leong, Quyet V. Do, Niklas Muennighoff, Tanrada Pansuwan, Ilham Firdausi Putra, Yan Xu, Tai Chia, Ayu Purwarianti, Sebastian Ruder, William Tjhi, Peerat Limkonchotiwat, Alham Aji, Sedrick Keh, Genta Winata, Ruochen Zhang, Fajri Koto, Zheng Xin Yong, Samuel Cahyawijaya

SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding (2026.findings-acl)

Challenge:	Southeast Asia (SEA) is home to over 1,300 indigenous languages and 671 million people . prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA .
Approach:	They propose to provide a resource center that provides standardized corpora in nearly 1,000 SEA languages across three modalities.
Outcome:	a new benchmark assesses the quality of AI models on 36 SEA languages across 13 tasks . the results highlight the importance of SEA as a culturally diverse region .

Copied to clipboard

Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, Xin Liu, Yifan Gao, Changlong Yu, Chen Luo, Yang Li, Zheng Li, Qingyu Yin, Bing Yin, Yangqiu Song

Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models (2024.lrec-main)

Challenge:	Existing models fail to capture and model customer intention effectively because of insufficient information exploitation and only apparent information like descriptions and titles are used.
Approach:	They propose to exploit existing session data to capture and model intention in E-commerce product purchase sessions using a multimodal benchmark.
Outcome:	The proposed framework can bridge the gap between intention understanding in simplified research cases like co-buy intention and more complex yet practical scenarios like session history.

Copied to clipboard

Oana Ignat, Zhijing Jin, Artem Abzaliev, Laura Biester, Santiago Castro, Naihao Deng, Xinyi Gao, Aylin Ece Gunal, Jacky He, Ashkan Kazemi, Muhammad Khalifa, Namho Koh, Andrew Lee, Siyang Liu, Do June Min, Shinka Mori, Joan C. Nwatu, Veronica Perez-Rosas, Siqi Shen, Zekun Wang, Winston Wu, Rada Mihalcea

FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery (2023.findings-acl)

Challenge:	Recent advances in large language models have led to misleading public discourse that “it’s all been solved.”
Approach:	They identify 14 research areas encompassing 45 research directions that require new research and are not directly solvable by LLMs.
Outcome:	The research areas identified are 45 research directions that require new research and are not directly solvable by LLMs.

Copied to clipboard

Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin

Commonsense Reasoning

Challenge:	Existing intention-based studies on recommendation tasks are limited and use models to implicitly model the intention memberships.
Approach:	They propose a framework that leverages the generation power of large language models and human-in-the-loop annotation to semi-automatically construct the intention knowledge graph.
Outcome:	The proposed framework can model e-commerce knowledge and have many potential applications.

Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment (2025.emnlp-main)

Copied to clipboard

Tong Zhang, Kuofeng Gao, Jiawang Bai, Leo Yu Zhang, Xin Yin, Zonghui Wang, Shouling Ji, Wenzhi Chen

Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering (2022.acl-long)

Challenge:	Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are vulnerable to data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet.
Approach:	They propose an Optimal Transport-based framework to reconstruct image-caption pairs and propose an optimal transport-based distance measure to re-assign new captions based on the proposed optimal transport distance.
Outcome:	The proposed framework reduces the attack success rates of poisoning attacks to 0% in most cases.

Copied to clipboard

Jun Gao, Wei Wang, Changlong Yu, Huan Zhao, Wilfred Ng, Ruifeng Xu

Distilling Causal Effect of Data in Continual Few-shot Relation Learning (2024.lrec-main)

Challenge:	Existing work exploits easily accessible co-occurrence information of events to learn event representations.
Approach:	They propose a weakly supervised contrastive learning method and a prototype-based clustering method for event representation learning.
Outcome:	The proposed framework outperforms baselines on Hard Similarity and Transitive Sentence Similarity tasks.

Copied to clipboard

Weihang Ye, Peng Zhang, Jing Zhang, Hui Gao, Moyao Wang

Characteristic AI Agents via Large Language Models (2024.lrec-main)

Challenge:	Existing methods for learning relational patterns from data are prone to catastrophic forgetting issues due to limited number of samples and continual training mode.
Approach:	They propose a unified causal framework for CFRL to restore causal effects from old data . they establish two additional causal paths from old to predictions by colliding with old data separately in the old feature space.
Outcome:	The proposed method is superior to existing state-of-the-art methods in CFRL task settings.

Copied to clipboard

Xi Wang, Hongliang Dai, Shen Gao, Piji Li

SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters (2026.acl-long)

Challenge:	Commercial products have been devoted to creating character-driven chatbots using large language models, but academic research in this area remains relatively scarce.
Approach:	They investigate the performance of LLMs in constructing characteristic AI agents by simulating real-life individuals across different settings.
Outcome:	The proposed benchmark compared LLMs with real-life individuals in different settings and includes evaluation metrics.

Copied to clipboard

Wenhao Gao, Tianlong Wang, Wei Jia, Linhao Zhang, Aiwei Liu, Miao Fan, Zhou Xiao

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language (2025.findings-acl)

Challenge:	Prompt-based in-context learning and parameter fine-tuning are dominant paradigms for incorporating external information into large language models, but they incur high inference costs or require expensive retraining.
Approach:	They propose to convert prompts into temporary adapter weights to bridge this gap by converting prompts to temporary adapters.
Outcome:	The proposed model outperforms baselines on long-context language modeling and downstream NLU and summarization benchmarks while significantly reducing memory footprint and latency.

Copied to clipboard

Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao, Ruoyu Li, Yong Jiang

When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario (2023.findings-acl)

Challenge:	Existing methods to bypass security defenses of large language models (LLMs) are not effective, but QueryAttack can be jailbroken.
Approach:	They propose a framework to examine generalizability of safety alignment by translating malicious queries into structured non-natural query languages.
Outcome:	The proposed framework can achieve high attack success rates and jailbreak various defense methods on mainstream LLMs.

Copied to clipboard

Chengcheng Han, Liqing Cui, Renyu Zhu, Jianing Wang, Nuo Chen, Qiushi Sun, Xiang Li, Ming Gao

Bridging Kernel Drivers and Virtual Device Models with LLM-Powered Automation (2026.acl-demo)

Challenge:	Large pre-trained language models (PLMs) are expensive and may not be open-sourced due to commercial considerations and potential risks of misuse.
Approach:	They propose to introduce gradient descent into black-box tuning scenario . they propose a method which integrates gradient descent and derivative-free optimization .
Outcome:	The proposed method achieves significant performance gains over previous state-of-the-art methods.

Copied to clipboard

Mingyu Wang, Bin Yu, Wenjian Lu, Zhi Wang, Gao Kefeng, Cheng Wen, Xu Lu, Cong Tian

LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners (2022.findings-naacl)

Challenge:	Linux kernel device drivers are tightly coupled with hardware, making them difficult to execute and test without physical devices.
Approach:	They present a tool that generates QEMU-based virtual devices directly from Linux driver source code.
Outcome:	The proposed tool generates QEMU-based virtual devices directly from Linux driver source code.

Copied to clipboard

Yaqing Wang, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Awadallah, Jianfeng Gao

TDCSA: LLM-Guided Top-Down Approach for Robust Citation Sentiment Analysis (2025.findings-acl)

Challenge:	LiST is an efficient method for fine-tuning large pre-trained language models in few-shot learning settings.
Approach:	They propose a method for efficient fine-tuning of large pre-trained language models in few-shot settings using self-training and meta-learning.
Outcome:	The proposed method outperforms GPT-3 in-context learning by 33% on few-shot tasks.

Copied to clipboard

Fan Gao, Jieyang Peng, Xiaoming Tao, Wang Youzheng

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models (2025.acl-long)

Challenge:	Citation Sentiment Analysis (CSA) is a key part of academic influence and knowledge diffusion.
Approach:	They propose a top-down framework that leverages LLMs’ semantic understanding capabilities to enhance PLM-based Citation Sentiment Analysis.
Outcome:	The proposed framework outperforms existing methods while maintaining robustness to quadruple quality variations.

Copied to clipboard

Mengzhao Chen, Wenqi Shao, Peng Xu, Jiahao Wang, Peng Gao, Kaipeng Zhang, Ping Luo

VenusFactory: An Integrated System for Protein Engineering with Data Retrieval and Language Model Fine-Tuning (2025.acl-demo)

Challenge:	Quantization-aware training (QAT) is a low-bit training solution that requires substantial training resources.
Approach:	They propose an algorithm that reduces memory consumption by low-bit representations with minimal accuracy loss.
Outcome:	EfficientQAT achieves 2-bit Llama-2-70B model on single GPU in 41 hours . compared to previous methods, it obtains model with less than 3 points accuracy degradation .

Copied to clipboard

Yang Tan, Chen Liu, Jingyuan Gao, Wu Banghao, Mingchen Li, Ruilin Wang, Lingrong Zhang, Huiqun Yu, Guisheng Fan, Liang Hong, Bingxin Zhou

Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs (2025.findings-acl)

Challenge:	Pre-trained protein language models have been used in protein engineering, but their adoption is limited due to data collection, task benchmarking, and application challenges.
Approach:	They propose a versatile engine that integrates biological data retrieval, standardized task benchmarking, and modular fine-tuning of PLMs.
Outcome:	The proposed engine integrates biological data retrieval, task benchmarking, and modular fine-tuning of PLMs.

Copied to clipboard

Zixiao Wang, Duzhen Zhang, Ishita Agarwal, Shen Gao, Le Song, Xiuying Chen

KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models (2024.acl-long)

Challenge:	Existing approaches to persona simulation large language models (LLMs) focus on learning basic biographical information, or using limited role-play dialogue datasets to capture a character’s responses.
Approach:	They propose to train characters using a linguistic structure and a style-tuning mechanism that allows a general linguistic style expert to collaborate with other task-specific experts to better understand their thoughts.
Outcome:	The proposed model outperforms baselines on linguistic accuracy and opinion comprehension on three tasks for Lu Xun's essay collection.

Copied to clipboard

Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Wei Ye, Jindong Wang, Xing Xie, Yue Zhang, Shikun Zhang

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization (2023.acl-long)

Challenge:	Existing methods to detect contaminated texts focus on quantifying contamination status instead of accurately gauging model performance.
Approach:	They propose a Knowledge-grounded Interactive Evaluation framework which incorporates an LLM-powered “interactor” role for the first time to accomplish a dynamic contamination-resilient evaluation.
Outcome:	The proposed framework is based on a question in a standard LLM benchmark and can be used to evaluate models in real-world conversations.

Copied to clipboard

SongYang Gao, Shihan Dou, Yan Liu, Xiao Wang, Qi Zhang, Zhongyu Wei, Jin Ma, Ying Shan

Transferring General Multimodal Pretrained Models to Text Recognition (2023.findings-acl)

Challenge:	Existing adversarial training methods require multi-step gradient ascents or word substitutions to obtain adversarials, which impairs the effectiveness of adversariarial training.
Approach:	They propose a procedure for instead adversarial training with only clean data that estimates the adversarials loss by perturbing the input data’s probability distribution rather than their embeddings.
Outcome:	The proposed procedure reduces time consumption by up to 70% compared to current best-performing adversarial training methods.

Copied to clipboard

Junyang Lin, Xuancheng Ren, Yichang Zhang, Gao Liu, Peng Wang, An Yang, Chang Zhou

Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models (P19-1)

Challenge:	Existing methods for text recognition rely on large-scale pretraining on human-annotated or synthetic data.
Approach:	They propose a method to transfer multimodal pretrained models to text recognition using image captioning.
Outcome:	The proposed method outperforms the baselines and achieves state-of-the-art performance in the Chinese text recognition benchmark.

Copied to clipboard

Dinghan Shen, Asli Celikyilmaz, Yizhe Zhang, Liqun Chen, Xin Wang, Jianfeng Gao, Lawrence Carin

Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions (2026.findings-acl)

Challenge:	Variational autoencoders (VAEs) have received much attention as an end-to-end architecture for text generation with latent variables.
Approach:	They propose to leverage several multi-level structures to learn a variational autoencoder model for generating long, and coherent text.
Outcome:	The proposed model produces more coherent and less repetitive long text compared to baselines and mitigates posterior collapse issue.

Copied to clipboard

Zhongbin Guo, Zhen Yang, Yushan Li, Xinyue Zhang, Wenyu Gao, Jiacheng Wang, Chengzhi Li, Xiangrui Liu, Ping Jian

HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)

Challenge:	Existing advances in Spatial Intelligence rely on vision-Language Models . however, a critical question remains: does spatial understanding originate from visual encoders?
Approach:	They propose to evaluate the SI performance of Large Language Models without pixel-level input.
Outcome:	The proposed benchmark challenges large language models to perform symbolic reasoning rather than visual pattern matching.

Copied to clipboard

Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang, Jun Gao, Shuai Huang, Yueping Kang, Yuanli Guo, Hongwei Feng, Yanghua Xiao

Linguistics & Cognitive NLP

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs).
Approach:	They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.
Outcome:	The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters.

Improving Continual Pre-training Through Seamless Data Packing (2025.findings-acl)

Copied to clipboard

Ruicheng Yin, Xuan Gao, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang

FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models (2024.emnlp-demo)

Challenge:	Empirical evaluations across various model architectures and corpus domains demonstrate the effectiveness of our method, outperforming baselines in 99% of all settings.
Approach:	They propose a method that uses a sliding window technique to pack data before continual pre-training to preserve contextual information and enhance model performance.
Outcome:	Empirical evaluations across various model architectures and corpus domains demonstrate the effectiveness of the proposed method outperforming baselines in 99% of settings.

Copied to clipboard

Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Zhengran Zeng, Wei Ye, Jindong Wang, Yue Zhang, Shikun Zhang

Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling (2023.emnlp-main)

Challenge:	Large language models (LLMs) have revolutionized natural language processing with impressive performance across various tasks.
Approach:	They propose a framework for automated evaluations of large language models . they open-source their code at https://github.com/WisdomShell/FreeEval .
Outcome:	The framework is open-source and can be used to develop and validate new evaluation methods.

Copied to clipboard

Yuanhang Yang, Shiyi Qi, Chuanyi Liu, Qifan Wang, Cuiyun Gao, Zenglin Xu

Challenge:	Recent studies suggest that transformer-based models perform cross-attention over input pairs, leading to computational cost.
Approach:	They propose a lightweight cross-attention mechanism that performs query encoding only once while modeling the query-candidate interaction in parallel.
Outcome:	The proposed model speeds up sentence pairing by over 113x while achieving comparable performance as the more expensive models.

Contrastive Multi-document Question Generation (2021.eacl-main)

Copied to clipboard

Woon Sang Cho, Yizhe Zhang, Sudha Rao, Asli Celikyilmaz, Chenyan Xiong, Jianfeng Gao, Mengdi Wang, Bill Dolan

Navigating the OverKill in Large Language Models (2024.acl-long)

Challenge:	Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents, but a naive model trained only using the targeted document set may generate too generic questions that cover a larger scope than delineated by the document set.
Approach:	They propose a contrastive learning strategy where given ‘positive’ and ‘negative’ sets of documents, generate a question that is closely related to the ‘positive' set but far away from the ‘negative' set.
Outcome:	The proposed model significantly outperforms several strong baselines, as measured by automatic metrics and human evaluation.

Copied to clipboard

Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin

Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry (2026.acl-long)

Challenge:	Recent studies have highlighted a tendency among large language models to refuse to answer benign queries.
Approach:	They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding.
Outcome:	The proposed approach reduces the refusal rate by 20% while having little impact on safety.

Copied to clipboard

Jiang Li, Tian Lan, Shanshan Wang, Dongxing Zhang, Dianqing Lin, Guanglai Gao, Derek F. Wong, Xiangdong Su

Challenge:	a recent study shows that large language models can generate text, but they can also fabricate large amounts of false or misleading content.
Approach:	They propose a benchmark to detect LLM-generated classical Chinese poetry . they compare 12 different AI detectors to find out whether a poem is authored by AI .
Outcome:	The proposed benchmark compared 12 AI detectors with a dataset of 30,664 Chinese poems . the results highlight the limitations of current Chinese text detectors .

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

InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings (2022.findings-emnlp)

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

Xing Wu, Chaochen Gao, Zijia Lin, Jizhong Han, Zhongyuan Wang, Songlin Hu

ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation (2026.acl-long)

Challenge:	Existing studies on contrastive learning for sentence embeddings are weak . researchers have started to use contrastive training to learn better unsupervised sentences.
Approach:	They propose an information-aggregated contrastive learning framework for learning unsupervised sentence embeddings.
Outcome:	The proposed framework outperforms SimCSE on several benchmark datasets w.r.t the semantic text similarity task.

Copied to clipboard

Zhuoyue Gao, Xiaohui Wang, Xiaocui Yang, Wen Zhang, Daling Wang, Shi Feng, Yifei Zhang