Papers by Jia Zheng

VLA-Mark: A cross modal watermark for large vision-language alignment models (2025.emnlp-main)

Challenge:	Context faithfulness is essential for reliable reasoning in context-dependent scenarios.
Approach:	They propose a method that identifies and fine-tunes context-faithful experts . they propose 'context-faither fine- tuning' which selectively fine- tunes them .
Outcome:	The proposed method identifies experts with specialization in context utilization and improves context grounding.

Copied to clipboard

Shuliang Liu, Zheng Qi, Jesse Jiaxi Xu, Yibo Yan, Junyan Zhang, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu

Robustness in NLP

Challenge:	Existing text watermarking methods disrupt visual-textual alignment, leaving semantic-critical concepts vulnerable.
Approach:	They propose a vision-aligned framework that embeds detectable watermarks into outputs . they combine localized patch affinity, global semantic coherence, contextual attention patterns .
Outcome:	The proposed framework shows lower PPL and higher BLEU than conventional methods with near-perfect detection (98.8% AUC).

MTA:A Merge-then-Adapt Framework for Personalized Large Language Models (2026.acl-long)

Copied to clipboard

Xiaopeng Li, Yuanjin Zheng, Wanyu Wang, Wenlin Zhang, Pengyue Jia, Yingyi Zhang, Haiying He, Mengyang Ma, Yiqi Wang, Maolin Wang, Xuetao Wei, Xiangyu Zhao

SHARP: Search-Based Adversarial Attack for Structured Prediction (2022.findings-naacl)

Challenge:	Personalized Large Language Models (PLLMs) aim to align outputs with individual user preferences . current methods of fine-tuning a separate module for each user are unscalable .
Approach:	They propose a Merge-then-Adapt framework for Personalized Large Language Models . they construct a shared Meta-LoRA bank and propose an Adaptive LoRA Fusion stage .
Outcome:	The proposed framework outperforms existing SOTA methods on the LaMP benchmark.

Copied to clipboard

Liwen Zhang, Zixia Jia, Wenjuan Han, Zilong Zheng, Kewei Tu

Robustness in NLP

Challenge:	SHARP is a new attack method for structured prediction models that solves several challenges.
Approach:	They propose a black-box adversarial attack method that uses a search-based optimization problem to attack adversarials.
Outcome:	The proposed method performs more potent attack than pioneer arts on two structured prediction tasks.

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Copied to clipboard

Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang

TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning (2025.findings-acl)

Challenge:	Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach:	They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome:	The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.

Copied to clipboard

Mingyu Zheng, Zhifan Feng, Jia Wang, Lanrui Wang, Zheng Lin, Hao Yang, Weiping Wang

RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)

Challenge:	Existing methods for table instruction tuning are limited due to limited data diversity and lack of data quality.
Approach:	They propose a weakness-guided data synthesis framework for table instruction tuning that explores the vast input space of table understanding tasks and then iterates through the input space.
Outcome:	The proposed framework boosts the average accuracy of Llama3.1-8B-instruct by 11.62% with 27K GPT-4o synthetic data and outperforms state-of-the-art data synthesis baselines which use more training data.

Copied to clipboard

Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang

Text Generation

Challenge:	Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains, but their ability to replicate complex, multi-panel visualizations remains largely unassessed.
Approach:	They propose a large-scale benchmark to evaluate chart generation from large- scale raw data and assess iterative code refinement in a multi-turn conversational setting.
Outcome:	The new benchmark evaluates 14 leading VLMs on real-world data and shows they struggle with complex plot structures and authentic data.

Adaptive Preference Optimization with Uncertainty-aware Utility Anchor (2025.findings-emnlp)

Copied to clipboard

Xiaobo Wang, Zixia Jia, Jiaqi Li, Qi Liu, Zilong Zheng

Green & Sustainable NLP

Challenge:	Offline preference optimization methods are efficient for large language models (LLMs) alignment.
Approach:	They propose an offline preference optimization framework that estimates uncertainties from preference data . the method enables training even in scenarios where the data is unpaired .
Outcome:	The proposed method enables training even in scenarios where the data is unpaired .

LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments (2024.findings-acl)

Copied to clipboard

Zixia Jia, Mengmeng Wang, Baichen Tong, Song-Chun Zhu, Zilong Zheng

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023.findings-emnlp)

Challenge:	Recent advances in Large Language Models (LLMs) have shown inspiring achievements in constructing autonomous agents that rely on language descriptions as inputs.
Approach:	They propose a flexible and simulation-free testbed that simulates 6 representative embodied tasks in textual embodies.
Outcome:	The proposed testbed offers adaptability to diverse environments without multiple simulation engines and allows easy customization of communication and action strategies.

Copied to clipboard

Zhiheng Xi, Senjie Jin, Yuhao Zhou, Rui Zheng, Songyang Gao, Jia Liu, Tao Gui, Qi Zhang, Xuanjing Huang

Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Challenge:	Existing prompting methods have been used to enhance multistep reasoning capabilities of large language models, but they have overlooked the potential of formulating higher-quality problems.
Approach:	They propose a method that starts from the problem side and refines problems to be more comprehensible and solvable for models.
Outcome:	The proposed method achieves notable and consistent effectiveness on five reasoning benchmarks across different models.

Copied to clipboard

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

Modularized Interaction Network for Named Entity Recognition (2021.acl-long)

Challenge:	MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach:	They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome:	The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).

Copied to clipboard

Fei Li, Zheng Wang, Siu Cheung Hui, Lejian Liao, Dandan Song, Jing Xu, Guoxiu He, Meihuizi Jia

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning (2026.findings-acl)

Challenge:	Named Entity Recognition (NER) models focus on word-level information, while segment-based models focus only on word level information.
Approach:	They propose a Modularized Interaction Network (MIN) model which utilizes both word-level information and segment-level dependencies.
Outcome:	The proposed model outperforms the current state-of-the-art models on three NER benchmark datasets.

Copied to clipboard

Zheng Li, Qingxiu Dong, Jingyuan Ma, Di Zhang, Kai Jia, Zhifang Sui

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection (2025.findings-acl)

Challenge:	Recent large reasoning models have shown exceptional performance on various tasks, but they consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency.
Approach:	They propose a self-adaptive reasoning strategy that automatically allocates budgets according to problem complexity and introduces GRPO for reinforcement learning to reduce output length.
Outcome:	The proposed model achieves an average response length compression of 61% on math reasoning tasks while maintaining accuracy.

Copied to clipboard

Jiaqi Li, Xinyi Dong, Yang Liu, Zhizhuo Yang, Quansen Wang, Xiaobo Wang, Song-Chun Zhu, Zixia Jia, Zilong Zheng

Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO (2026.acl-long)

Challenge:	ReflectEvo-460k is a large-scale, comprehensive, self-generated reflection dataset with broadened instructions and diverse multi-domain tasks.
Approach:	They propose a pipeline that iteratively generates self-reflection for self-training and a large-scale reflection dataset with broadened instructions and diverse multi-domain tasks.
Outcome:	The proposed pipeline improves Llama-3 reasoning ability by up to 71.2% and Mistral by upto 44.4%.

Copied to clipboard

Jinquan Zheng, Jia Yuan, Jiacheng Yao, Chenyang Gu, Pujun Zheng, Guoxiu He

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation (2024.emnlp-main)

Challenge:	Existing inference-time debiasing ignores that the same question should yield consistent answers across permutations.
Approach:	They propose a permutation-aware group-relative policy optimization which enforces permutations-consistent semantic reasoning.
Outcome:	The proposed model outperforms strong baselines across seven benchmarks while maintaining high overall performance.

Copied to clipboard

Ruotong Pan, Boxi Cao, Hongyu Lin, Xianpei Han, Jia Zheng, Sirui Wang, Xunliang Cai, Le Sun

Information Retrieval

Challenge:	Existing RAG paradigms suffer from the impact of flawed information introduced during the retrieval phrase, thereby diminishing the reliability and correctness of the generated output.
Approach:	They propose a framework that empowers models to discern and process information based on its credibility.
Outcome:	The proposed framework outperforms existing models with retrieval augmentation and exhibits robustness despite increasing noise in the context.

All That Glitters is Not Gold: Improving Robust Retrieval-Augmented Language Models with Fact-Centric Preference Alignment (2025.findings-acl)

Copied to clipboard

Jia Hao, Chunhong Zhang, Jiarun Liu, Haiyu Zhao, Zhiqiang Zhan, Zheng Hu

Robustness in NLP

Challenge:	Existing methods to learn adaptive retrieval for noisy documents lack prior filtering and may lead to the loss of crucial information.
Approach:	They propose a method to improve retrieval performance without prior filtering . they use LLMs self-generated synthetic data as training data without manual annotation .
Outcome:	The proposed method performs positive document mining based on factual consistency and uses LLMs self-generated synthetic data as training data without manual annotation.

Logits-Based Finetuning (2025.emnlp-main)

Copied to clipboard

Jingyao Li, Senqiao Yang, Sitong Wu, Han Shi, Chuanyang Zheng, Hong Xu, Jiaya Jia

Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction (2025.findings-naacl)

Challenge:	Existing methods for developing compact and efficient large language models lack token-level dependencies and linguistic diversity.
Approach:	They propose a logits-based fine-tuning framework that integrates supervised learning and knowledge distillation to build enriched training targets using teacher logits and ground truth labels.
Outcome:	The proposed method outperforms existing methods on a large-scale logits dataset and a series of science-focused models.

Copied to clipboard

ShengbinYue ShengbinYue, Ting Huang, Zheng Jia, Siyuan Wang, Shujun Liu, Yun Song, Xuanjing Huang, Zhongyu Wei

QuickLLaMA: Query-aware Inference Acceleration for Large Language Models (2025.coling-main)

Challenge:	Large Language Models (LLMs) have advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios.
Approach:	They propose a Multi-agent Legal Simulation Driver to generate synthetic data by simulating interactive legal scenarios.
Outcome:	The proposed framework ensures consistency of legal attributes between participants and introduces a supervisory mechanism to align participants’ characters and behaviors as well as addressing distractions.

Copied to clipboard

Jingyao Li, Han Shi, Sitong Wu, Chuanyang Zheng, Zhenguo Li, Xin Jiang, Hong Xu, Jiaya Jia

MMUIE: Massive Multi-Domain Universal Information Extraction for Long Documents (2026.findings-eacl)

Challenge:	Large Language Models (LLMs) struggle with capturing long-distance dependencies within sequences to deeply understand semantics.
Approach:	They propose a system that captures relevant information within a fixed window size and provides precise answers to queries.
Outcome:	The proposed system can read Harry Potter within 30s and accurately answer the questions.

Copied to clipboard

Shuyi Zhang, Zhenbin Chen, Shuting Li, Kewei Tu, Li Jing, Zixia Jia, Zilong Zheng

Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments (2026.acl-long)

Challenge:	Existing document-level information extraction systems operate at the sentence level or within narrow domains due to annotation constraints.
Approach:	They propose a large-scale universal dataset for multi-domain, document-level information extraction from long texts.
Outcome:	The proposed dataset integrates traditional knowledge bases with large language models to extract fine-grained entities, aliases, and relation triples across 34 domains.

Copied to clipboard

Zheng Jia, Shengbin Yue, Wei Chen, Siyuan Wang, Yidong Liu, Zejun Li, Yun Song, Zhongyu Wei

Challenge:	Existing benchmarks for legal intelligence are limited to static evaluation paradigms or simplified scenarios.
Approach:	They introduce J1-ENVS, the first interactive and dynamic legal environment tailored for LLM-based agents.
Outcome:	The proposed framework assesses task performance and procedural compliance across legal proficiency levels.

Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels (2024.acl-long)

Copied to clipboard

Zixia Jia, Junpeng Li, Shichuan Zhang, Anji Liu, Zilong Zheng

Varying Sentence Representations via Condition-Specified Routers (2024.emnlp-main)

Challenge:	Existing supervised learning methods rely on human annotations, but multi-label tasks pose challenges due to the specific domain knowledge and large class sets.
Approach:	They propose a framework that can be used to annotate a subset of positive classes from a multi-label dataset.
Outcome:	The proposed framework is generalized and effective across multiple tasks.

Copied to clipboard

Ziyong Lin, Quansen Wang, Zixia Jia, Zilong Zheng

Semantic Text Processing

Challenge:	Existing sentences cannot account for different aspects of semantic similarity between two sentences.
Approach:	They propose a transformer-style framework that generates conditioned sentences . they propose 'conditional' STS, which measures similarity between two sentences based on condition sentences - a task that requires a sentence embedding model capable of generating distinct representations for the same sentence under different conditions.
Outcome:	The proposed framework is superior to existing models on two condition sentences . it can generate conditioned sentences while maintaining model parameters and computational efficiency .

Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization (2022.acl-long)

Copied to clipboard

Ruipeng Jia, Xingxing Zhang, Yanan Cao, Zheng Lin, Shi Wang, Furu Wei

Text Generation

Challenge:	Existing methods to translate sentences to other languages using heuristics are challenging.
Approach:	They propose a model that learns hierarchical weights for different sets of labels and applies them to other languages to translate them.
Outcome:	The proposed model can translate English datasets to other languages and obtain different sets of labels again using heuristics.

The Linguistic Connectivities Within Large Language Models (2025.findings-acl)

Copied to clipboard

Dan Wang, Boxi Cao, Ning Bian, Xuanang Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Le Sun, Shanshan Jiang, Bin Dong, Xianpei Han

Semantic Text Processing

Challenge:	Recent studies have discovered notable disparities in their performance across different languages.
Approach:	They conduct a systematic investigation into the behaviors of large language models across 27 different languages on 3 different scenarios and reveals a Linguistic Map correlates with the richness of available resources and linguistic family relations.
Outcome:	The proposed model demonstrates that there are significant disparities in performance across languages across 27 different languages on 3 different scenarios.

READoc: A Unified Benchmark for Realistic Document Structured Extraction (2025.findings-acl)

Copied to clipboard

Zichao Li, Aizier Abulaiti, Yaojie Lu, Xuanang Chen, Jia Zheng, Hongyu Lin, Xianpei Han, Shanshan Jiang, Bin Dong, Le Sun

Deep Differential Amplifier for Extractive Summarization (2021.acl-long)

Challenge:	Document Structured Extraction (DSE) is a field of document structure analysis that aims to extract structured content from raw documents.
Approach:	They propose a benchmark to evaluate document structured extraction systems by converting unstructured PDFs into semantically rich Markdown.
Outcome:	The proposed benchmark is based on 3,576 diverse and real-world documents from arXiv, GitHub, and Zenodo.

Copied to clipboard

Ruipeng Jia, Yanan Cao, Fang Fang, Yuchen Zhou, Zheng Fang, Yanbing Liu, Shi Wang

Text Generation

Challenge:	Existing approaches to extract summary from document with a disproportionate ratio of selected and unselected sentences are far from human performance.
Approach:	They propose a model that rebalances sentence-level extractive summarization by amplifying the semantic difference between each sentence and all other sentences and applying the residual unit as the second item of the differential amplifier to deepen the architecture.
Outcome:	The proposed model performs competitively against state-of-the-art methods on two benchmark datasets.

Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models (2026.findings-acl)

Copied to clipboard

Weiwei Qi, Zefeng Wu, Tianhang Zheng, Zikang Zhang, Xiaojun Jia, Zhan Qin, Kui Ren

Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field (2023.acl-long)

Challenge:	Existing safety-related methodologies for large language models are lacking . despite advances in safety alignment techniques, safeguarding LLMs during adaptation to various tasks remains a challenge.
Approach:	They propose a framework to quantify how different parameters affect LLM safety . they propose two targeted intervention paradigms for safety enhancement and preservation .
Outcome:	The proposed framework reveals safety-critical patterns across different LLM architectures.

Copied to clipboard

Zixia Jia, Zhaohui Yan, Wenjuan Han, Zilong Zheng, Kewei Tu

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

Challenge:	Existing approaches to joint Information Extraction (IE) neglect cross-instance or cross-task dependencies.
Approach:	They propose a joint IE framework that formulates joint 'conditional random field' to model cross-instance interactions . they incorporate a high-order neural decoder that is unfolded from a mean-field variational inference method .
Outcome:	The proposed approach improves on three IE tasks compared with baseline and prior work.

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

Information Retrieval

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.

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models (2026.eacl-long)

Copied to clipboard

Qiao Liang, Yanjiang Liu, Weixiang Zhou, Ben He, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun, Yingfei Sun

Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models (2023.emnlp-main)

Challenge:	Existing research treats MLLMs as unified systems optimized through end-to-end training, but the impact of vision encoder’s prior knowledge is seldom investigated.
Approach:	They propose a metric to quantify the effect of prior knowledge on MLLM performance by integrating prior knowledge at the vision encoder level into a training framework.
Outcome:	The proposed training framework incorporates prior knowledge at the vision encoder level, and significantly boosts visual understanding capabilities of MLLMs.

Copied to clipboard

Junpeng Li, Zixia Jia, Zilong Zheng

A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models (2025.findings-acl)

Challenge:	Document-level Relation Extraction (DocRE) is a task that aims to extract relations from a long context.
Approach:	They propose an automated annotation method that integrates an LLM and a natural language inference module to generate relation triples.
Outcome:	The proposed method can extract relations from document-level relation datasets with minimal human effort.

Copied to clipboard

Shuliang Liu, Hongyi Liu, Aiwei Liu, Duan Bingchen, Zheng Qi, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, Xuming Hu

Responsible & Trustworthy NLP

Challenge:	Existing methods for detection of misinformation generated by large language models fail to mitigate societal risks . authors propose a paradigm shift from passive detection to anticipatory mitigation strategies . existing defenses remain reactionary in an era demanding proactive defense, authors say .
Approach:	They propose a three-pillar approach to prevent misinformation by fortifying integrity of training data and inference reliability by embedding self-corrective mechanisms during reasoning.
Outcome:	The proposed framework improves existing methods in misinformation prevention by 63% . it demonstrates that existing methods exhibit false negative rates against misinformation .

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides (2025.emnlp-main)

Copied to clipboard

Hao Zheng, Xinyan Guan, Hao Kong, Wenkai Zhang, Jia Zheng, Weixiang Zhou, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

Evidence Retrieval is almost All You Need for Fact Verification (2024.findings-acl)

Challenge:	Existing methods for generating presentations from documents focus on improving and evaluating content quality in isolation, overlooking visual appeal and structural coherence.
Approach:	They propose an edit-based presentation generation system that analyzes and iterates on slides to create new slides.
Outcome:	The proposed presentation generation tool outperforms existing methods in three dimensions . it analyzes slides, iterates and generates edit actions based on selected slides .

Copied to clipboard

Liwen Zheng, Chaozhuo Li, Xi Zhang, Yu-Ming Shang, Feiran Huang, Haoran Jia

Responsible & Trustworthy NLP

Challenge:	Existing evidence retrieval methods adopt a trivial retrieval strategy, resulting in task-irrelevant evidence and undesirable performance.
Approach:	They propose a framework for evidence retrieval and joint fact verification that integrates two modules.
Outcome:	The proposed framework improves evidence retrieval and claims verification on a FEVER dataset.

Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations (2024.findings-emnlp)

Copied to clipboard

Nuo Chen, Zinan Zheng, Ning Wu, Ming Gong, Dongmei Zhang, Jia Li

MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning (2026.findings-acl)

Challenge:	Existing research focuses on developing powerful large language models for mathematical reasoning within monolingual languages.
Approach:	They propose to use translation to build powerful multilingual math reasoning models . they propose different training strategies to build xMR LLMs that outperform open-source LLM .
Outcome:	The proposed model outperforms open-source LLMs and surpasses ChatGPT in few-shot scenarios.

Copied to clipboard

Yimin Deng, Zhenxi Lin, Yejing Wang, Guoshuai Zhao, Pengyue Jia, Zichuan Fu, Derong Xu, Yefeng Zheng, Xiangyu Zhao, Li Zhu, Xian Wu, Xueming Qian

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning (2025.findings-acl)

Challenge:	Existing approaches focus on diagnostic reasoning based on internal model knowledge or static knowledge bases.
Approach:	They propose a two-stage diagnostic reasoning framework that integrates multi-perspective evidence to generate a diagnostic prediction.
Outcome:	The proposed method generates suspected diagnoses and reasoning traces from web search, SOAP-formatted case, and clinical case database.

Copied to clipboard

Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, Xuming Hu

Weights-Rotated Preference Optimization for Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for MU forget quality and model utility are not fully explored for safety in MLLMs.
Approach:	They propose a safety unlearning benchmark for MLLMs to measure over-forgetting . they propose MU methods to forget quality and model utility .
Outcome:	The proposed method reduces over-forgetting by 79.5% while maintaining forget quality and model utility.

Copied to clipboard

Chenxu Yang, Ruipeng Jia, Mingyu Zheng, Naibin Gu, Zheng Lin, Siyuan Chen, Weichong Yin, Hua Wu, Weiping Wang

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Challenge:	Existing methods to align large language models with high reward hacking are limited by the complexity of the parameter space and the complexity.
Approach:	They propose a weights-rotated preference optimization algorithm that constrains the output layer logits with the KL divergence inherited from DPO and fine-tunes the intermediate hidden states.
Outcome:	The proposed algorithm achieves a 3.27-point improvement on AlpacaEval 2 and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters.

Copied to clipboard

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Programming Languages in NLP

Challenge:	Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach:	They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome:	The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.

TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network (2021.emnlp-main)

Copied to clipboard

Zheng Fang, Yanan Cao, Tai Li, Ruipeng Jia, Fang Fang, Yanmin Shang, Yuhai Lu

Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training (2025.acl-long)

Challenge:	Existing methods to label data and identify entities require large amounts of manually annotated texts for training supervised models.
Approach:	They propose a dictionary extension method which extracts new entities through the type expanded model.
Outcome:	The proposed method outperforms state-of-the-art supervised systems on different types of datasets and surpasses supervised models.

Copied to clipboard

Ziyong Lin, Haoyi Wu, Shu Wang, Kewei Tu, Zilong Zheng, Zixia Jia

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis (2025.findings-emnlp)

Challenge:	Existing methods for converting large language models into powerful text encoders require extensive training on large datasets.
Approach:	They propose a training-free approach that enables bidirectional attention and suppresses the attention sink phenomenon, resulting in superior performance.
Outcome:	The proposed approach enables bidirectional attention and suppresses the attention sink phenomenon, resulting in superior performance.

Copied to clipboard

Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen

SimulBench: Evaluating Language Models with Creative Simulation Tasks (2025.findings-naacl)

Challenge:	Existing approaches to deep search training lack high-quality training trajectories, prohibitive computational costs and lack of high-fidelity training data.
Approach:	They propose a framework that synthesizes high-quality training data by simulating real user interactions in live web search environments.
Outcome:	The proposed framework synthesizes high-quality training data by simulating user interactions in live web search environments.

Copied to clipboard

Qi Jia, Xiang Yue, Tuney Zheng, Jie Huang, Bill Yuchen Lin

Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks (2025.emnlp-main)

Challenge:	Existing benchmarks for large language models do not fully evaluate their potential for broad implementation.
Approach:	They propose to use a fixed LLM as a user agent to engage with an LLM to collect dialogues first under different tasks.
Outcome:	The proposed framework outperforms LLaMA-3-70b-Chat on 18.55% more cases.

Copied to clipboard

Xubo Qin, Jun Bai, Jiaqi Li, Zixia Jia, Zilong Zheng

LIME: Less Is More for MLLM Evaluation (2025.findings-acl)

Challenge:	Existing methods for retrieval of information excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks.
Approach:	They propose a family of small-scale language models for query reasoning and rewriting in reasoning-intensive retrieval.
Outcome:	The proposed model outperforms existing models on a BRIGHT benchmark with BM25 retrievers.

Copied to clipboard

King Zhu, Qianbo Zang, Shian Jia, Siwei Wu, Feiteng Fang, Yizhi Li, Shuyue Guo, Tianyu Zheng, Jiawei Guo, Bo Li, Haoning Wu, Xingwei Qu, Jian Yang, Ruibo Liu, Xiang Yue, Jiaheng Liu, Chenghua Lin, Hamid Alinejad-Rokny, Min Yang, Shiwen Ni, Wenhao Huang, Ge Zhang

Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios (2026.findings-acl)

Challenge:	Existing MLLM benchmarks and unified evaluation frameworks cannot accurately and efficiently reflect the ability of MLMLs.
Approach:	They propose a semi-automated benchmark curated using a pipeline that filters out uninformative samples and eliminates answer leakage by focusing on tasks that require image-based understanding.
Outcome:	The proposed benchmark reduces the number of samples by 76% and evaluation time by 77% while it can more effectively distinguish different models’ abilities.

Copied to clipboard

Xiaomin Li, Tala Wang, Zichen Zhong, Ying Zhang, Zirui Zheng, Takashi Isobe, Dezhuang Li, Huchuan Lu, You He, Xu Jia