Papers by Zheng Lu

From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for LLM-Based Paper Evaluation (2026.findings-acl)

Challenge:	Existing code sandboxes fail to provide accurate verification and efficiency under high-concurrency workloads.
Approach:	They propose a high-fidelity code verification system that provides sandbox feedback for RL training and evaluation.
Outcome:	The proposed system outperforms heuristic-matching baselines on LiveCodeBench and training stability on high-concurrency workloads.

Copied to clipboard

Pujun Zheng, Jiacheng Yao, Jinquan Zheng, Chenyang Gu, Guoxiu He, Jiawei Liu, Yong Huang, Tianrui Guo, Wei Lu

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)

Challenge:	Large language models (LLMs) are currently used to evaluate scientific papers by assigning an absolute score to each paper independently.
Approach:	They propose a comparison-native framework for paper evaluation that integrates comparison into both data construction and model learning.
Outcome:	The proposed framework achieves an average relative improvement of 21.8% over the strong baseline DeepReview-14B, while exhibiting robust generalization to five previously unseen datasets.

Copied to clipboard

Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun

Multilinguality

Challenge:	Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language.
Approach:	They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking.
Outcome:	The proposed approach mitigates language bias and consistently improves mRAG performance across languages.

Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis (2023.findings-emnlp)

Copied to clipboard

Jianqiao Lu, Wenyong Huang, Nianzu Zheng, Xingshan Zeng, Yu Yeung, Xiao Chen

Experience-driven Multi-turn Reinforcement Learning for GUI Agents (2026.acl-long)

Challenge:	Latent Synthesis is an efficient textual data utilization framework for end-to-end speech processing models . labeled speech data are scarcer and more expensive for collection compared to textual ones .
Approach:	They propose a textual data utilization framework for E2E speech processing models . they train a latent synthesizer to convert textual information into an intermediate latent representation .
Outcome:	The proposed framework improves on low-resource speech recognition and spoken language understanding tasks.

Copied to clipboard

Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang

Challenge:	GUI agents have demonstrated remarkable progress in automating complex user interface interactions . training such agents for long-horizon tasks remains challenging due to limited rewards and prohibitive costs.
Approach:	They propose a method that leverages expert trajectories as environment experiences for on-policy multi-turn training.
Outcome:	The proposed method achieves significant gains over the base model with 1K public trajectories as RL experiences . it achieves competitive performance against strong baselines such as UI-TARS-7B and GPT-4o .

KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model’s Reasoning Path Aggregation (2025.findings-acl)

Copied to clipboard

Siyuan Fang, Kaijing Ma, Tianyu Zheng, Xeron Du, Ningxuan Lu, Ge Zhang, Qingkun Tang

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment (2026.acl-long)

Challenge:	Existing methods for large language models (LLMs) are limited by step-by-step decision-making on KGs, or require fine-tuning or pre-training on specific KG.
Approach:	They propose a framework that harnesses the global planning abilities of large language models (LLMs) for efficient and accurate KG reasoning.
Outcome:	Extensive experiments show that the proposed framework achieves state-of-the-art performance in KGQA tasks, delivering both high efficiency and accuracy.

Copied to clipboard

Jiwei Tang, Zhicheng Zhang, Shunlong Wu, Jingheng Ye, Lichen Bai, Zitai Wang, Tingwei Lu, Lin Hai, Yiming Zhao, Hai-Tao Zheng, Hong-Gee Kim

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

Challenge:	Large Language Models (LLMs) have achieved remarkable performance across NLP tasks . however, in long-context scenarios, they face high computational cost and information redundancy.
Approach:	They propose an encoder-decoder context compression framework that generates a compact sequence of soft tokens for downstream tasks.
Outcome:	Experiments show that GMSA outperforms baselines on multiple long-context question answering and summarization benchmarks while maintaining low end-to-end latency.

Copied to clipboard

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

Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios (2025.findings-naacl)

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

Copied to clipboard

Jiwei Tang, Jin Xu, Tingwei Lu, Zhicheng Zhang, YimingZhao YimingZhao, LinHai LinHai, Hai-Tao Zheng

Executing Natural Language-Described Algorithms with Large Language Models: An Investigation (2024.lrec-main)

Challenge:	Long prompts contain redundant information and are sensitive to the position of key information in long context scenarios.
Approach:	They propose a training-free prompt compression framework that retains key information at token level while removing distracting tokens.
Outcome:	The proposed framework outperforms existing methods on long context benchmarks.

Copied to clipboard

Xin Zheng, Qiming Zhu, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning (2025.emnlp-main)

Challenge:	Recent advances in large language models (LLMs) have revolutionized the field of natural language processing and artificial intelligence, creating new SOTAs and reaching human-level language understanding performance on a series of tasks and benchmarks.
Approach:	They propose to use an algorithm test set sourced from Introduction to Algorithm to assess LLMs' code execution abilities.
Outcome:	The proposed model can execute programs described in natural language as long as no heavy numeric computation is involved.

Copied to clipboard

Jiazheng Liu, Sipeng Zheng, Börje F. Karlsson, Zongqing Lu

Natural Language Interfaces

Challenge:	Existing multimodal large language models are trained on single-turn vision question-answering tasks, which do not accurately reflect real-world human conversations.
Approach:	They propose a large-scale multi-turn multimodal dialogue dataset that uses rules and GPT assistance to generate a multi-turned multimodal dialog dataset.
Outcome:	The proposed dataset is a strong benchmark for multi-turn multimodal dialogue learning . it features complex dialogues with contextual dependencies that force models to track, ground, and recall information across multiple turns and disparate visual regions.

When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models (2025.emnlp-main)

Copied to clipboard

Yingming Zheng, Hanqi Li, Kai Yu, Lu Chen

CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset (2023.findings-acl)

Challenge:	Large language models (LLMs) have achieved impressive performance across NLP tasks.
Approach:	They propose to use long-context SFT to improve short-contemporary performance . they also decouple and analyze two key components, Multi-Head Attention and Feed-Forward Network .
Outcome:	The proposed model improves short-context performance, contrary to pretraining.

Copied to clipboard

Hanchong Zhang, Jieyu Li, Lu Chen, Ruisheng Cao, Yunyan Zhang, Yu Huang, Yefeng Zheng, Kai Yu

Programming Languages in NLP

Challenge:	a cross-domain text-to-SQL task aims to parse user questions into SQL on complete unseen databases . a single-domain task evaluates the performance on identical databases based on the same domain .
Approach:	They propose a cross-domain text-to-SQL task that parses user questions into SQL on unseen databases.
Outcome:	The proposed system can parse user questions into SQL on complete unseen databases.

Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning (2024.emnlp-main)

Copied to clipboard

Lu Chen, Rui Zheng, Binghai Wang, Senjie Jin, Caishuang Huang, Junjie Ye, Zhihao Zhang, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

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

Challenge:	Current methods rely on ranking losses to teach reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions.
Approach:	They propose a method that incorporates contrastive learning into the reward modeling process to enhance generalization and stabilize the reinforcement learning training process.
Outcome:	The proposed method enhances generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences.

Copied to clipboard

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

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)

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

Copied to clipboard

Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Challenge:	Existing presentation agents rely on predefined workflows and fixed templates to generate presentations.
Approach:	They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation.
Outcome:	The proposed framework can be used to generate presentations with environmental observations.

A Prism Module for Semantic Disentanglement in Name Entity Recognition (P19-1)

Copied to clipboard

Kun Liu, Shen Li, Daqi Zheng, Zhengdong Lu, Sheng Gao, Si Li

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse (2026.acl-demo)

Challenge:	Xu et al., 2015) proposed a noise reduction mechanism to disentangle semantics of words . hard and soft attention mechanisms are used to reduce noise in NLP tasks .
Approach:	They propose a prism module to disentangle semantic aspects of words and reduce noise . they propose combining prism modules with downstream models to improve model performance .
Outcome:	The proposed method significantly improves the performance of baselines on named entity recognition (NER) tasks.

Copied to clipboard

Zhang Zhang, Shuqi Lu, Hongjin Qian, Di He, Zheng Liu

Attention-Enhancing Backdoor Attacks Against BERT-based Models (2023.findings-emnlp)

Challenge:	Existing frameworks for building LLM-based agents treat agent behavior as static-knowledge gained during execution is not preserved for future use.
Approach:	They propose a new paradigm that preserves successful task solutions as executable subagent code rather than textual experience.
Outcome:	The proposed agent-based agent-driven paradigm preserves successful tasks as executable subagent code rather than textual experience.

Copied to clipboard

Weimin Lyu, Songzhu Zheng, Lu Pang, Haibin Ling, Chao Chen

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Existing textual backdoor attacks focus on generating stealthy triggers or modifying model weights.
Approach:	They propose a Trojan Attention Loss (TAL) which enhances the Trojan behavior by directly manipulating attention patterns.
Outcome:	The proposed method improves the effectiveness of the backdoor attacks on different backbone models and tasks.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Self-Para-Consistency: Improving Reasoning Tasks at Low Cost for Large Language Models (2024.findings-acl)

Copied to clipboard

Wenqing Chen, Weicheng Wang, Zhixuan Chu, Kui Ren, Zibin Zheng, Zhichao Lu

Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment (2022.acl-long)

Challenge:	Recent studies have shown that self-consistency decoding can improve performance for complex reasoning tasks with large language models.
Approach:	They propose a self-consistency decoding strategy that generates multiple paraphrases for each test question and then generates reasoning paths for the original and all the paraphrased questions based on greedy decoding.
Outcome:	The proposed strategy reduces the sampling number and improves performance on complex reasoning tasks.

Copied to clipboard

Zijie Huang, Zheng Li, Haoming Jiang, Tianyu Cao, Hanqing Lu, Bing Yin, Karthik Subbian, Yizhou Sun, Wei Wang

Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration (2026.eacl-long)

Challenge:	Existing methods to predict missing facts in knowledge graphs are limited in language alignment . SS-AGA uses seed alignment as an edge type to fuses all KGs as a whole graph .
Approach:	They propose a self-supervised adaptive graph alignment method that fuses all KGs as a whole graph by regarding alignment as 'a new edge type' they propose SS-AGA method that uses relation-aware attention weights to capture potential alignment pairs in a new paradigm.
Outcome:	The proposed method can predict missing facts in a knowledge graph (KG) but language alignment is scarce and new alignment identification is noisy.

Copied to clipboard

Guozhao Mo, Yanjiang Liu, Yafei Shi, Jiawei Chen, Yang Li, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Bo Zheng, Xianpei Han

Linguistics & Cognitive NLP

Challenge:	Existing methods for dynamic web navigation rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models.
Approach:	They propose a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration.
Outcome:	The proposed framework surpasses the proprietary model Claude-3.5 Sonnet on the WebArena benchmark.

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

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

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

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

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

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

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

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

Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic (2025.findings-acl)

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

Xin Zheng, Jie Lou, Boxi Cao, Xueru Wen, Yuqiu Ji, Hongyu Lin, Yaojie Lu, Xianpei Han, Debing Zhang, Le Sun

FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression (2026.findings-eacl)

Challenge:	Existing approaches to improve the reasoning performance of large language models rely on intuitive instance-level feedback, which limits the reasoning capabilities.
Approach:	They propose a framework that pushes LLMs toward System-2-like critic capability by using a step-wise CoT reasoning paradigm and automatic construction of weak-supervision data without human annotation.
Outcome:	The proposed model significantly improves task-solving performance by filtering out invalid solutions or iterative refinement.

Copied to clipboard

Jiayi Tian, Ryan Solgi, Jinming Lu, Yifan Yang, Hai Li, Zheng Zhang

ProcessBench: Identifying Process Errors in Mathematical Reasoning (2025.acl-long)

Challenge:	Low-rank decomposition methods suffer from accuracy degradation and expensive calibration procedures.
Approach:	They propose a fast and accurate, training-free structural compression method based on fine-grained low-rank transformations in the activation space.
Outcome:	The proposed method outperforms pruning baselines in generalization and downstream performance while delivering inference speedups.

Copied to clipboard

Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin

Logic: Long-form Outline Generation via Imitative and Critical Self-refinement (2025.findings-emnlp)

Challenge:	Existing models fail to generalize to more challenging math problems, authors say . existing benchmarks related to assessing language models' reasoning process are limited .
Approach:	They propose a tool to measure language models' ability to identify erroneous steps in reasoning . they use two types of models: process reward models and critic models .
Outcome:	The proposed model outperforms existing models in evaluating language models' reasoning process . the best open-source model has demonstrated the critique capability competitive with the proprietary model .

Copied to clipboard

Hengwei Liu, Yongliang Shen, Zhe Zheng, Haoyuan Ma, Xingyu Wu, Yin Zhang, Weiming Lu

Information Retrieval

Challenge:	Existing methods for long-form outline generation have low knowledge density and lack detail . retrieval-augmented approaches struggle to maintain logical coherence across retrieved information .
Approach:	They propose a system that mimics human writers' refinement process by mimicking outlines through imitation and critical self-refinement.
Outcome:	The proposed system improves on the FreshWiki and WikiOutline datasets and establishes a coherent planning framework and structured knowledge base.

Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (2025.findings-acl)

Copied to clipboard

Wenhao Liu, Siyu An, Junru Lu, Muling Wu, Tianlong Li, Xiaohua Wang, Changze Lv, Xiaoqing Zheng, Di Yin, Xing Sun, Xuanjing Huang

Representation Learning

Challenge:	Role-playing Agents (RPAs) struggle to recognize and respond to hard queries that conflict with their role-play knowledge.
Approach:	They propose a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model’s refusal accuracy.
Outcome:	The proposed model improves RPAs’ refusal ability of conflicting requests while maintaining their general role-playing capabilities.

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)

Copied to clipboard

Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu, Wenqi Zhang, Yuchen Yan, Qiuying Peng, Jun Wang, Weiming Lu

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming (2026.acl-long)

Challenge:	Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification.
Approach:	They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth.
Outcome:	The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation.

Copied to clipboard

Jiwei Tang, Shilei Liu, Zhicheng Zhang, Qingsong Lv, Runsong Zhao, Tingwei Lu, Langming Liu, Haibin Chen, Yujin Yuan, Hai-Tao Zheng, Wenbo Su, Bo Zheng

Challenge:	Existing task-aware methods require loading the entire input sequence at once for compression, which suffer from computational inefficiency.
Approach:	They propose a framework that adopts an adaptive hybrid reading strategy to reduce computational inefficiency and redundant information in long-context scenarios.
Outcome:	Experiments show that RAM outperforms baselines on multiple question answering and summarization benchmarks while delivering up to a 12x speedup on long inputs.

FNSCC: Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering for Short Text (2025.findings-emnlp)

Copied to clipboard

Zijian Zheng, Yonghe Lu, Jian Yin

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning (2025.findings-emnlp)

Challenge:	Short texts pose significant challenges for clustering due to semantic sparsity, limited context and fuzzy category boundaries.
Approach:	proposed framework incorporates neighborhood information at instance and cluster levels . a cluster-level framework introduces fuzzy neighborhood-aware weighting .
Outcome:	The proposed framework outperforms state-of-the-art models on short texts . it excludes neighbors from negative sample set to enhance inter-cluster separability .

Copied to clipboard

Yangning Li, Tingwei Lu, Yinghui Li, Yankai Chen, Wei-Chieh Huang, Wenhao Jiang, Hui Wang, Hai-Tao Zheng, Philip S. Yu

UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)

Challenge:	Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) current methods suffer from the curriculum rigidity, resulting in a fixed and potentially sub-optimal learning trajectory.
Approach:	a framework for efficient instruction tuning is proposed to address the issue of curriculum rigidity . current methods rely on static heuristic difficulty metrics and fail to adapt to evolving capabilities .
Outcome:	Efficient instruction tuning aims to enhance the ultimate performance of large language models . current methods suffer from the curriculum rigidity, resulting in a fixed learning trajectory .

Copied to clipboard

Jing Xiong, Jianghan Shen, Fanghua Ye, Chaofan Tao, Zhongwei Wan, Jianqiao Lu, Xun Wu, Chuanyang Zheng, Zhijiang Guo, Min Yang, Lingpeng Kong, Ngai Wong

Cross-Lingual Dependency Parsing by POS-Guided Word Reordering (2020.findings-emnlp)

Challenge:	Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands.
Approach:	They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content.
Outcome:	The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup.

Copied to clipboard

Lu Liu, Yi Zhou, Jianhan Xu, Xiaoqing Zheng, Kai-Wei Chang, Xuanjing Huang

Syntactic Text Processing

Challenge:	Existing approaches to cross-lingual dependency parsing rely on large corpus size and cost.
Approach:	They propose a cross-lingual dependency parsing approach based on word reordering . they propose to train a model that transfers knowledge learned in one or multiple languages to target languages .
Outcome:	The proposed approach outperforms the baseline approach in Hindi and Latin by 15.3% and 6.7%.

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

Copied to clipboard

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

VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs (2025.emnlp-main)

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

Copied to clipboard

Keer Lu, Keshi Zhao, Zhuoran Zhang, Zheng Liang, Bin Cui, Tengjiao Wang, Wentao Zhang

Towards Quantifiable Dialogue Coherence Evaluation (2021.acl-long)

Challenge:	Existing work focuses on domain-specific enhancements during fine-tuning, the challenge of which lies in catastrophic forgetting of knowledge across other domains.
Approach:	They propose a data composition framework that allows LLMs to enhance their multi-domain capabilities during supervised fine-tuning.
Outcome:	The proposed framework improves multi-domain fostering performance by 29.77% compared to uniform weights.

Copied to clipboard

Zheng Ye, Liucun Lu, Lishan Huang, Liang Lin, Xiaodan Liang

Dialogue Systems & Conversational Agents

Challenge:	Existing automatic dialogue coherence evaluation metrics are expensive and high-latency, which cannot meet the requirements of a dialogue system.
Approach:	They propose a framework to train a quantifiable dialogue coherence metric that can reflect actual human rating standards.
Outcome:	Experimental results show that the model trained by QuantiDCE presents stronger correlations with human judgements than the other state-of-the-art metrics.

Object-oriented Neural Programming (OONP) for Document Understanding (P18-1)

Copied to clipboard

Zhengdong Lu, Xianggen Liu, Haotian Cui, Yukun Yan, Daqi Zheng

FloorPlan-LLaMa: Aligning Architects’ Feedback and Domain Knowledge in Architectural Floor Plan Generation (2025.acl-long)

Challenge:	Object-oriented Neural Programming (OONP) is a framework for semantically parsing documents in domains.
Approach:	They propose a framework for semantically parsing documents in specific domains using OONP . OOPN parsers use a rich family of operations to represent the semantics of the document .
Outcome:	The proposed framework can learn to handle fairly complicated ontology with training data of modest sizes.

Copied to clipboard

Jun Yin, Pengyu Zeng, Haoyuan Sun, Yuqin Dai, Han Zheng, Miao Zhang, Yachao Zhang, Shuai Lu

Challenge:	Existing evaluation methods for floor plan generation rely on statistical metrics like FID, GED, and PSNR, which fail to evaluate using domain knowledge.
Approach:	They propose to use a first floor plan dataset to train a floor plan generation model based on a multi-dimensional preference score and a textual analysis to integrate architects’ professional expertise and preferences.
Outcome:	The proposed model outperforms baseline models in text-conditional and class-condition tasks and is more rational and aligns better with human preferences.

Is the Attention Matrix Really the Key to Self-Attention in Multivariate Long-Term Time Series Forecasting? (2026.acl-long)

Copied to clipboard

Xinyu Li, Kexi Chen, Jiajie Shen, Ying Zheng, Hong Lu, Jin Zhao, Xin Wang

Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback (2024.findings-acl)

Challenge:	In multivariate long-term time series forecasting, it is widely believed that the effectiveness of self-attention arises from its attention matrix.
Approach:	They propose a multi-branch MLP that isolates the ‘multi-brain mapping with element-wise operation’ structure from the Transformer and shows that it achieves competitive performance.
Outcome:	The proposed model outperforms three classic and three latest Transformer models and shows that it achieves competitive performance.

Copied to clipboard

Zhangqian Bi, Yao Wan, Zheng Wang, Hongyu Zhang, Batu Guan, Fangxin Lu, Zili Zhang, Yulei Sui, Hai Jin, Xuanhua Shi

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) generate code for given contexts, such as incomplete code, class, data structure, or project-specific information.
Approach:	They propose a compiler feedback-based code generation approach that leverages static analysis to identify mismatches between the generated code and the project's context.
Outcome:	The proposed model outperforms retrieval-based code generation baselines and significantly outperfies the existing large language models.

DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments (2025.emnlp-main)

Copied to clipboard

Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, Pengfei Liu

Scaling LLMs’ Social Reasoning: Sprinkle Cognitive “Aha Moment” into Fundamental Long-thought Logical Capabilities (2025.findings-acl)

Challenge:	Large Language Models (LLMs) with web search capabilities show significant potential for deep research.
Approach:	They introduce a framework for end-to-end training of LLM-based deep research agents . they implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures.
Outcome:	The proposed framework improves on open-domain research tasks by 28.9 points over prompt engineering and 7.2 points over RAG-based RL agents.

Copied to clipboard

Guiyang Hou, Wenqi Zhang, Zhe Zheng, Yongliang Shen, Weiming Lu

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

Challenge:	Existing studies have examined how large language models’ social reasoning capabilities evolve during model size scaling or reasoning tokens scaling.
Approach:	They propose to optimize evaluation of Large Language Models from both data and model perspectives and to analyze their reasoning trajectories to identify notable cognitive "Aha Moments"
Outcome:	The proposed model outperforms the o1-preview model by 19.0 points in the evaluation of large language models.

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

MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning (2026.acl-long)

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.

Copied to clipboard

Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Binbin Zheng, Chaowen Hu, Zekai Shao, Cong Qin, Lu Pan, Ke Zeng, Xunliang Cai

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)

Challenge:	Existing RLVR algorithms rely on rigid, uniform, and symmetric trust region mechanisms . current algorithms lack robustness, asymmetric signal reliability and inefficient gradient utilization .
Approach:	They propose a framework to harmonize three dimensions of RLVR algorithms, a paper argues . a binary cutoff is used to discard valuable reinforcement signals, they argue .
Outcome:	The proposed framework outperforms baselines in evaluating a robust RLVR solution.

Copied to clipboard

Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen, Baichuan Zhou, Shenzhe Zhu, Yi Lu, Haozhe Wang, Chi Ruan, Benjamin Schneider, Weixu Zhang, Xiang Li, Andy Zheng, Yuyu Zhang, Ping Nie, Wenhu Chen

From log 𝜋 to 𝜋: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight (2026.acl-long)

Challenge:	Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge.
Approach:	They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance.
Outcome:	Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points.

Copied to clipboard

Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Chaowen Hu, Cong Qin, Zekai Shao, Binbin Zheng, Lu Pan, Ke Zeng

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

Challenge:	Standard algorithms for Large Language Models (LLMs) enforce stability via "hard clipping" but relying on log-probability gradient yields divergent weights as probabilities vanish, destabilizing LLM training.
Approach:	They propose a decoupled gradient policy optimization that uses a decay mechanism to decouple the probability of a boundary token.
Outcome:	The proposed algorithm outperforms baselines on various mathematical benchmarks.

Copied to clipboard

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

Plan Dynamically, Express Rhetorically: A Debate-Driven Rhetorical Framework for Argumentative Writing (2025.emnlp-main)

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

Xueguan Zhao, Wenpeng Lu, Chaoqun Zheng, Weiyu Zhang, Jiasheng Si, Deyu Zhou

Linguistic Theories

Challenge:	Argumentative essay generation (AEG) is a complex task that requires advanced semantic understanding, logical reasoning, and organized integration of perspectives.
Approach:	They propose a debate-driven rhetorical framework for argumentative writing that integrates Bitzer’s rhetorical situation theory to improve logical depth, argumentative diversity, and rhetorical persuasiveness.
Outcome:	The proposed framework improves logical depth, argumentative diversity, and rhetorical persuasiveness over existing state-of-the-art models.

Harnessing LLMs for Temporal Data - A Study on Explainable Financial Time Series Forecasting (2023.emnlp-industry)

Copied to clipboard

Xinli Yu, Zheng Chen, Yanbin Lu

Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)

Challenge:	Recent advances in machine learning and artificial intelligence have opened up numerous opportunities and challenges in financial time series forecasting.
Approach:	They propose to use Large Language Models for explainable financial time series forecasting to leverage cross-sequence information and extract insights from text and price time series.
Outcome:	The proposed model outperforms ARMA-GARCH and gradient-boosting tree models while underperforming on other models.

Copied to clipboard

Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values.
Approach:	They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values .
Outcome:	The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets.

Speculative Contrastive Decoding (2024.acl-short)

Copied to clipboard

Hongyi Yuan, Keming Lu, Fei Huang, Zheng Yuan, Chang Zhou

LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment (2026.findings-acl)

Challenge:	Large language models (LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias.
Approach:	They propose a decoding approach that leverages predictions from smaller language models to achieve both decoding acceleration and quality improvement.
Outcome:	The proposed method achieves both decoding acceleration and quality improvement on four diverse language tasks.

Copied to clipboard

Chenji Lu, Zhuo Chen, Hui Zhao, Zhiyuan Zeng, Gang Zhao, Junjie Ren, null Lihaoran, Songyan Liu, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng

MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension (2024.findings-emnlp)

Challenge:	E-commerce search relevance is a critical component of retrieval systems.
Approach:	They propose a large-generative model for search relevance that trains reasoning knowledge, multi-modal understanding and rule awareness into three core competencies.
Outcome:	The proposed model outperforms GPT-5 in Macro-F1 and achieves 27% online gain.

Copied to clipboard

Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan Yao, Hai-Tao Zheng, Yu Li

Question Answering

Challenge:	Existing models generate erroneous information and evaluations fail to assess factual correctness of models.
Approach:	They propose to use MoleculeQA to evaluate molecular factual correctness in large language models by organizing molecules into a taxonomy and building QA pairs through human and LLM efforts.
Outcome:	The proposed model improves the factual correctness of generated information and enables the development of new models.

MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning (2024.acl-long)

Copied to clipboard

Chengpeng Li, Zheng Yuan, Hongyi Yuan, Guanting Dong, Keming Lu, Jiancan Wu, Chuanqi Tan, Xiang Wang, Chang Zhou

DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction (P19-1)

Challenge:	In math reasoning with large language models, fine-tuning data augmentation by query evolution and diverse reasoning paths is empirically verified effective.
Approach:	They propose to fine-tune data augmentation by query evolution and diverse reasoning paths.
Outcome:	The proposed model achieves new state-of-the-art on GSM8K and MATH.

Copied to clipboard

Shun Zheng, Xu Han, Yankai Lin, Peilin Yu, Lu Chen, Ling Huang, Zhiyuan Liu, Wei Xu

RecMind: Large Language Model Powered Agent For Recommendation (2024.findings-naacl)

Challenge:	Existing methods for labeling relational facts require significant expert labor to write relation-specific patterns, which makes them too sophisticated to generalize quickly.
Approach:	They propose a neural pattern diagnosis framework that can summarize and refine relation-specific patterns with human experts in the loop.
Outcome:	The proposed framework can summarize and refine high-quality relational patterns from noise data with human experts in the loop.

Copied to clipboard

Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Yanbin Lu, Xiaojiang Huang, Yingzhen Yang

Task-Agnostic Detector for Insertion-Based Backdoor Attacks (2024.findings-naacl)

Challenge:	Existing recommendations systems are limited in generalizing to new tasks due to model scale and data size constraints.
Approach:	They propose an LLM-powered autonomous recommender agent, RecMind, which is capable of leveraging external knowledge to provide zero-shot personalized recommendations.
Outcome:	The proposed model outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks and achieves comparable performance to a fully trained recommendation model P5.

Copied to clipboard

Weimin Lyu, Xiao Lin, Songzhu Zheng, Lu Pang, Haibin Ling, Susmit Jha, Chao Chen

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)

Challenge:	Existing methods for textual backdoor detection are task-specific and less effective beyond sentence classification.
Approach:	They propose a task-agnostic method for backdoor detection that leverages final layer logits and an efficient pooling technique.
Outcome:	TABDet can jointly learn from diverse task-specific models, demonstrating superior detection efficacy over traditional methods.

Copied to clipboard

Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization (2024.findings-emnlp)

Challenge:	supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models.
Approach:	They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Outcome:	The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns.

Copied to clipboard

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu, Zheng Liu, Tun Lu, Xing Xie, Ning Gu

Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach (2025.acl-long)

Challenge:	Existing methods to steer LLMs towards human preference suffer from noisy positive-negative training pairs.
Approach:	They propose a distributional preference optimization method which maximizes discrepancy between dispreferred responses and generated non-negative ones.
Outcome:	The proposed method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence.

Copied to clipboard

Shenglai Zeng, Pengfei He, Kai Guo, Tianqi Zheng, Hanqing Lu, Yue Xing, Hui Liu

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs (2026.eacl-long)

Challenge:	Large Language Models (LLMs) enhanced with external contexts face challenges in handling imperfect evidence.
Approach:	They propose a framework that can balance internal knowledge with external contexts . they propose gating mechanisms and low-rank representation adapters to adjust hidden representations based on a lightweight intervention function .
Outcome:	The proposed model can effectively balance internal knowledge with external context, similar to human cognitive processes.

Copied to clipboard

Yujia Zheng, Tianhao Li, Haotian Huang, Tianyu Zeng, Jingyu Lu, Chuangxin Chu, Yuekai Huang, Ziyou Jiang, Qian Xiong, Yuyao Ge, Mingyang Li

Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Challenge:	Existing studies treat prompts as flat text, overlooking their internal structure, and different components within a prompt contribute unequally to robustness.
Approach:	They propose a framework that decomposes prompts into functional components and a method that selectively modifies components to expose component-wise vulnerabilities.
Outcome:	The proposed framework exposes component-wise vulnerabilities while ensuring linguistic plausibility through perplexity-based filtering.

Copied to clipboard

Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong

MAST: A Multi-View Alignment Strategy for Optimal Transport-Based Contrastive Clustering of Short Text (2026.findings-acl)

Challenge:	Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach:	They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome:	The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.

Copied to clipboard

Zijian Zheng, Yonghe Lu

Text Clustering

Challenge:	Short text clustering has gained significant prominence due to its ubiquity in real-world applications.
Approach:	They propose a multi-view alignment strategy with transport-based clustering that integrates structural views to capture multi-granularity semantic features.
Outcome:	Experiments show that MAST outperforms state-of-the-art methods on benchmark datasets.

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

Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models (2024.naacl-long)

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

Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, Jingren Zhou

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs? (2025.findings-acl)

Challenge:	Existing ensemble methods for Large Language Models focus on reward model ranking of outputs, leading to significant computation overhead.
Approach:	They propose a reward-guided routing method distilling rewards on training queries to train a routing function.
Outcome:	The proposed method outperforms the best single model and ranks first on 44% of tasks.

Copied to clipboard

Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Xiao Yueyi, Yizhou Chen, Yuqun Zhang, Haotian Zhang, Lu Zhang, Chenbin Chenbin, Yingfei Xiong

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

Challenge:	Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance.
Approach:	They develop a series of billion-scale grammar-based code representations that incorporate grammar rules into the code generation process.
Outcome:	Experiments on HumanEval and MBPP show that grammar-based representations reduce syntax errors and improve performance even in billion-scale models.

Copied to clipboard

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

Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows (2026.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

Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Adina Yakefu, Shuxin Zheng

Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark (2025.coling-main)

Challenge:	FinWorkBench evaluates real-world enterprise-grade finance and accounting workflows . a human evaluation of GPT 5.1 Pro passes only 38.4% of workflows, a study finds .
Approach:	They propose a workflow construction process that combines LLM-assisted mining and expert annotation to build 172 composite workflows.
Outcome:	The proposed process combines expert annotation with LLM-assisted mining of workflows from authentic enterprise environments.

Copied to clipboard

Zhikun Xu, Yinghui Li, Ruixue Ding, Xinyu Wang, Boli Chen, Yong Jiang, Haitao Zheng, Wenlian Lu, Pengjun Xie, Fei Huang

Natural Language Interfaces

Challenge:	Recent work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer dynamic questions well.
Approach:	They propose a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest dynamic questions on the Chinese Internet.
Outcome:	The proposed benchmark will be one of the key data resources for improving LLMs’ Chinese question-answering ability in the future.

Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data (2025.emnlp-main)

Copied to clipboard

Shenglai Zeng, Jiankun Zhang, Pengfei He, Jie Ren, Tianqi Zheng, Hanqing Lu, Han Xu, Hui Liu, Yue Xing, Jiliang Tang

Generating Responses with a Specific Emotion in Dialog (P19-1)

Challenge:	Existing literature suggests that RAG systems may face privacy issues when the retrieval process involves private data.
Approach:	They propose a two-stage synthetic data generation paradigm that uses attributes to preserve contextual information from the original data.
Outcome:	The proposed approach preserves key contextual information from the original data while reducing privacy risks.

Copied to clipboard

Zhenqiao Song, Xiaoqing Zheng, Lu Liu, Mu Xu, Xuanjing Huang

Dialogue Systems & Conversational Agents

Challenge:	EmoDS can express emotions in both ways, but it is difficult to scale to large datasets.
Approach:	They propose an emotional dialog system that can express emotions in both ways . they use strong emotional words and neutral words to increase the intensity of emotions .
Outcome:	The proposed system performs better than baselines in BLEU, diversity and quality of emotional expression.

LLaMA-Rider: Spurring Large Language Models to Explore the Open World (2024.findings-naacl)

Copied to clipboard

Yicheng Feng, Yuxuan Wang, Jiazheng Liu, Sipeng Zheng, Zongqing Lu

Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding (2023.emnlp-industry)

Challenge:	Recent studies have used Large Language Models to help decision-making and planning in environments, but their capacity to acquire environmental knowledge and adapt in an open world remains uncertain.
Approach:	They propose an approach to spur LLMs to explore the open world, gather experiences, and learn to improve their task-solving capabilities by using a feedback-revision mechanism.
Outcome:	The proposed model enhances the efficiency of the LLM in exploring the open world and improves its ability to accomplish more tasks through fine-tuning with merely 1.3k instances of collected data, showing minimal training costs compared to baseline using reinforcement learning.

Copied to clipboard

Zheng Chen, Ziyan Jiang, Fan Yang, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Aram Galstyan

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

Challenge:	Defective queries impact the robustness of conversational AI systems such as Alexa, Siri or Google Assistant.
Approach:	They propose a Personalized Query Rewriting system that takes into account individual preferences or unique error patterns identified from a user's historical interactions with the conversational AI.
Outcome:	The proposed approach has been proven on a large-scale real-world dataset and online A/B experiments.

Copied to clipboard

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

Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization (2026.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

Jiaqi Li, Guangming Wang, Shuntian Zheng, Minzhe Ni, Xiaoman Lu, Guanghui Ye, Yu Guan

ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization (2022.emnlp-main)

Challenge:	Existing vision-language models overemphasize linguistic priors, leading to modality bias.
Approach:	They propose a vision-language aggregation framework that mitigates modality bias in TAL by preserving vision as the dominant signal while adaptively exploiting language only when beneficial.
Outcome:	Experiments on THUMOS14 show that the proposed model outperforms state-of-the-art models by up to 3.2% mAP.

Copied to clipboard

Jiaan Wang, Fandong Meng, Ziyao Lu, Duo Zheng, Zhixu Li, Jianfeng Qu, Jie Zhou

Natural Language Interfaces

Challenge:	Existing approaches to building cross-lingual summarization systems on dialogue documents are limited.
Approach:	They propose a benchmark dataset for building cross-lingual summarization systems on dialogue documents.
Outcome:	The proposed model outperforms pipeline models on ClidSum and mDialBART.

MADAWSD: Multi-Agent Debate Framework for Adversarial Word Sense Disambiguation (2025.emnlp-main)

Copied to clipboard

Kaiyuan Zhang, Qian Liu, Luyang Zhang, Chaoqun Zheng, Shuaimin Li, Bing Xu, Muyun Yang, Xinxiao Qiao, Wenpeng Lu

Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks (2026.acl-long)

Challenge:	Word sense disambiguation (WSD) is a fundamental yet challenging task in natural language processing.
Approach:	a novel multi-agent Debate framework for adversarial word Sense disambiguation is proposed . the framework simulates a real-world debate environment where multiple agents engage in discussions about ambiguous words in the context of adversarials.
Outcome:	The proposed framework integrates with existing LLMs and improves models in Chinese language . it shows that it can be used to improve models in the Chinese language and improve performance .

Copied to clipboard

Xiang Cheng, Yulan Hu, Xiangwen Zhang, Lu Xu, Lide Tan, Zheng Pan, Xin Li, Yong Liu

Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective (2023.eacl-main)

Challenge:	Existing studies on LLM performance on travel planning have shown that existing settings are limited due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries.
Approach:	They propose a benchmark to evaluate LLMs' planning and tool-use abilities in real-world settings by collecting user queries, user preferences, and tools from real scenarios.
Outcome:	The proposed benchmark evaluates agents' capabilities in real-world settings and shows that even advanced models exhibit imbalanced performance across different capabilities.

Copied to clipboard

Zijian Zhang, Chang Shu, Ya Xiao, Yuan Shen, Di Zhu, Youxin Chen, Jing Xiao, Jey Han Lau, Qian Zhang, Zheng Lu

Visual Data in NLP

Challenge:	Recent VSE models combine simple pooling methods with hard triplet loss to improve performance.
Approach:	They propose an adaptive pooling strategy that allows the model to learn how to aggregate features through a combination of simple pooling methods.
Outcome:	The proposed strategy outperforms current state-of-the-art systems on image-to-text and text-toimage retrieval.

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)

Copied to clipboard

Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)

Challenge:	Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations.
Approach:	They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference.
Outcome:	The proposed method significantly mitigates object hallucinations across various model architectures.

Copied to clipboard

Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li, Yueting Zhuang

OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)

Challenge:	Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored.
Approach:	They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes.
Outcome:	The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks.

Copied to clipboard

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection (2026.findings-acl)

Challenge:	Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs.
Approach:	They propose a framework that integrates dialogue, reasoning, and personalized recommendation.
Outcome:	Experiments across public benchmarks show state-of-the-art performance.

Copied to clipboard

Runze Sun, Yu Zheng, Zexuan Xiong, Zhongjin Qu, Lei Chen, Jie Zhou, Jiwen Lu

RAISE: Reinforced Adaptive Instruction Selection For Large Language Models (2025.findings-emnlp)

Challenge:	Existing systems struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities.
Approach:	They propose a framework to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on H-VLI and on established benchmarks.

Copied to clipboard

Qingsong Lv, Yangning Li, Zihua Lan, Zishan Xu, Jiwei Tang, Tingwei Lu, Yinghui Li, Wenhao Jiang, Hong-Gee Kim, Hai-Tao Zheng, Philip S. Yu

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

Challenge:	Existing selection methods rely on static, heuristic quality scores and are executed only once before training.
Approach:	They propose a dynamic selection framework that integrates selection into every training step.
Outcome:	The proposed framework integrates selection into every training step.

Copied to clipboard

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

Synergizing Semantic Anchors and Ordinal Smoothed Cross-Entropy for Speech Fluency Classification (2026.findings-acl)

Challenge:	Existing benchmarks focus on evaluating MLLMs’ pre-existing knowledge or perceptual understanding, often neglecting the critical capability of reasoning.
Approach:	They propose a benchmark designed for visual clue-driven reasoning in daily scenarios that combines rigorous grounding in authentic daily activities and challenging query design that necessitates more than surface-level perception.
Outcome:	The proposed benchmark identifies visual clues and their ability to provide robust reasoning in daily scenarios.

Copied to clipboard

Mulati Kahaer, Sirajahmat Ruzmamat, XuDong Pang, Subinuer Maimaitituerxun, Zaokere Kadeer, Abudurexiti Reheman, Wenwen Lu, Panpan Zheng, Aishan Wumaier

Text Classification

Challenge:	Existing methods fail to bridge the semantic gap between static expert priors and dynamic temporal representations while overlooking the inherent ordinal nature of fluency scores.
Approach:	They propose a set of expert features targeting fluency disruptions and rhythmic regularity to provide explicit linguistic priors.
Outcome:	The proposed model outperforms baseline models in both macroscopic and microscopic speech flow trends and local anomalies.

Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness (2021.emnlp-main)

Copied to clipboard

Hengtong Zhang, Tianhang Zheng, Yaliang Li, Jing Gao, Lu Su, Bo Li