Papers by Wei He

Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking (2026.findings-acl)

Challenge:	Large language models have created significant safety concerns . factuality ability is crucial in determining whether they can be deployed and applied safely and compliantly within specific regions.
Approach:	They propose a benchmark to evaluate the factuality of large language models in China . they evaluate the models' ability to provide accurate and reliable information .
Outcome:	The proposed benchmark evaluates the factuality abilities of existing LLMs and compares them to LLM abilities.

Copied to clipboard

Shengbo Gong, Xianfeng Tang, Qi He, Carl Yang, Wei Jin

Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery (2022.emnlp-main)

Challenge:	Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs).
Approach:	They propose a framework that leverages an LLM to decompose questions into searchable triplets with placeholders.
Outcome:	Empirical results show that T2RAG outperforms state-of-the-art multi-round and Graph RAG methods while reducing retrieval costs by up to 45%.

Copied to clipboard

Yutao Mou, Keqing He, Pei Wang, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu

Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models (2025.acl-long)

Challenge:	Existing methods for finding out-of-domain intents suffer from in-domain overfitting problem . previous methods fail to transfer prior knowledge to downstream clustering .
Approach:	They propose a unified K-nearest neighbor contrastive learning framework to discover OOD intents . they propose IND pre-training objective to learn discriminative features while maintaining intra-class diversity .
Outcome:	The proposed framework improves on three benchmark datasets.

Copied to clipboard

Xinlin Zhuang, Jiahui Peng, Ren Ma, Yinfan Wang, Tianyi Bai, Xingjian Wei, Qiu Jiantao, Chi Zhang, Ying Qian, Conghui He

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

Challenge:	composition of pre-training datasets for large language models remains undisclosed . current methods for evaluating data quality are limited by single-dimensional evaluation or redundancy-focused strategies.
Approach:	They propose a multi-dimensional data selection method that integrates dimensions with existing quality metrics through learned optimal weightings.
Outcome:	The proposed method doubles convergence speed for 1.3B model models and improves downstream task performance by 3.23%.

Copied to clipboard

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

Robustness in NLP

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.

Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions (2024.emnlp-main)

Copied to clipboard

Quan Liu, Zhenhong Zhou, Longzhu He, Yi Liu, Wei Zhang, Sen Su

HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST (2026.findings-acl)

Challenge:	Existing defenses against jailbreaks focus on perturbing or inspecting inputs, but ignore competing objectives, the underlying cause of alignment failures.
Approach:	They propose a novel defense that employs adaptive decoding to address the root causes of jailbreak issues.
Outcome:	The proposed defense improves safety alignment while maintaining helpfulness.

Copied to clipboard

Shuyu Zhang, Yifan Wei, Xinru Wang, Yanmin Zhu, Yangfan He, Yixuan Weng, Yujie Liu, Bin Li

Low-Resource NLP

Challenge:	Existing approaches to zero-shot Dialog State Tracking (zs-DST) are inadequate to generalize to new domains without extensive training.
Approach:	They propose a framework that enhances zero-shot slot inference through robust prompt alignment.
Outcome:	Experiments on multi-domain datasets show that HiCoLoRA outperforms baselines, achieving SOTA in zs-DST.

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

Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)

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

Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Nijun Li, Tao Gui, Yun Li, Qi Zhang, Xuanjing Huang

ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)

Challenge:	Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target.
Approach:	They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success.
Outcome:	The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design.

Copied to clipboard

Chaoyue He, Xin Zhou, Yi Wu, Xinjia Yu, Yan Zhang, Lei Zhang, Di Wang, Shengfei Lyu, Hong Xu, Wang Xiaoqiao, Wei Liu, Chunyan Miao

Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs (2025.emnlp-main)

Challenge:	ESGenius is a comprehensive benchmark for evaluating Large Language Models on ESG and sustainability knowledge.
Approach:	They introduce ESGenius, a benchmark for evaluating and enhancing ESG proficiency . they use a rigorous two-stage evaluation protocol and a repository of foundational frameworks .
Outcome:	ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in ESG and sustainability-focused question answering.

Copied to clipboard

Zhang Zhang, Guhao Feng, Jian Guan, Di He, Wei Wu

Beyond the Textual: Generating Coherent Visual Options for MCQs (2025.findings-emnlp)

Challenge:	Direct Preference Optimization (DPO) eliminates complex reward modeling in aligning large language models with human preferences, but its online variant faces significant efficiency bottlenecks due to costly real-time preference sampling and the reward model annotation.
Approach:	They propose a framework that transforms static datasets into dynamically adaptive equivalents without the need for an explicit reward model.
Outcome:	The proposed approach matches or exceeds the performance of a fully online DPO.

Copied to clipboard

Wanqiang Wang, Longzhu He, Wei Zheng

MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models (2023.emnlp-demo)

Challenge:	Multiple choice questions (MCQs) are crucial for deep thinking and knowledge integration in education.
Approach:	They propose a cross-modal options synthesis framework for generating MCQs with visual options.
Outcome:	The proposed framework produces a plausible and visually similar answer and distractor . it also includes a discrimination module to identify content suitable for visual options .

Copied to clipboard

Dingyao Yu, Kaitao Song, Peiling Lu, Tianyu He, Xu Tan, Wei Ye, Shikun Zhang, Jiang Bian

Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model (P19-1)

Challenge:	MusicAgent integrates numerous music-related tools and an autonomous workflow to address user requirements.
Approach:	a new system is built to integrate music-related tools and an autonomous workflow . the system is based on large language models (LLMs) that can be used to organize and decompose requests .
Outcome:	the proposed system integrates numerous music-related tools and an autonomous workflow to address user requirements.

Copied to clipboard

Wei Li, Jingjing Xu, Yancheng He, ShengLi Yan, Yunfang Wu, Xu Sun

Structured Data in NLP

Challenge:	Existing models for article comment generation are too long and often result in general and irrelevant comments.
Approach:	They propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph.
Outcome:	The proposed model can generate coherent and informative comments compared with several strong baseline models.

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Canhui Wu, Qiong Cao, Chang Li, Zhenfang Wang, Chao Xue, Yuwei Fan, Wei Xi, Xiaodong He

Rethinking Smoothness for Fast and Adaptable Entity Alignment Decoding (2025.findings-naacl)

Challenge:	Existing reinforcement learning methods for large reasoning models suffer from excessive verbosity, known as "overthinking." Existing models penalize generated tokens to promote conciseness, but these methods encounter two challenges: they may develop hacking behavior in later stages of training by discarding reasoning steps.
Approach:	They propose a framework that steers large reasoning models toward more efficient reasoning . they prioritize correctness while imposing penalties for redundant steps .
Outcome:	The proposed framework reduces token usage by 69.7% on AIME24.

Copied to clipboard

Yuanyi Wang, Han Li, Haifeng Sun, Lei Zhang, Bo He, Wei Tang, Tianhao Yan, Qi Qi, Jingyu Wang

GL-GAN: Perceiving and Integrating Global and Local Styles for Handwritten Text Generation with Mamba (2025.coling-main)

Challenge:	Existing methods for integrating knowledge graphs rely on entity and relation embeddings . Fig. 1 shows how to decode knowledge graph in under 6 seconds .
Approach:	They propose a framework that only utilizes entity embeddings to decode knowledge graphs.
Outcome:	The proposed framework reconstructs KG representation by maximizing smoothness of entity embeddings.

Copied to clipboard

Yiming Wang, Hongxi Wei, Heng Wang, Shiwen Sun, Chao He

Text Generation

Challenge:	Existing models lack the ability to perceive and integrate handwriting styles, which affects the realism of the synthesized samples.
Approach:	They propose a Hybrid Style Encoder that captures global and local styles and integrates them into a Dynamic Feature Enhancement Module (DFEM).
Outcome:	The proposed model outperforms state-of-the-art models on two widely used handwriting datasets and can provide training data for handwritten text recognition and signature verification.

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

Copied to clipboard

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

Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning (2022.acl-short)

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

Copied to clipboard

Yutao Mou, Keqing He, Yanan Wu, Zhiyuan Zeng, Hong Xu, Huixing Jiang, Wei Wu, Weiran Xu

Generalized Intent Discovery: Learning from Open World Dialogue System (2022.coling-1)

Challenge:	Existing methods to find out out-of-domain (OOD) intents do not take prior knowledge of in-domain data into account.
Approach:	They propose a disentangled knowledge transfer method to bridge the gap between IND pre-training and OOD clustering by using a unified multi-head contrastive learning framework.
Outcome:	The proposed method is able to group new unknown intents into different clusters, enabling future development of the system.

Copied to clipboard

Yutao Mou, Keqing He, Yanan Wu, Pei Wang, Jingang Wang, Wei Wu, Yi Huang, Junlan Feng, Weiran Xu

LEMMA: Learning from Errors for MatheMatical Advancement in LLMs (2025.findings-acl)

Challenge:	Existing intent classification models rely on a pre-defined intent set and supervised labels, which is limited in some practical scenarios.
Approach:	They propose to extend an IND intent classifier to an open-world intent set including IND and OOD intents.
Outcome:	The proposed task can classify IND and OOD intents while discovering new unlabeled OOD types incrementally.

Copied to clipboard

Zhuoshi Pan, Yu Li, Honglin Lin, Qizhi Pei, Zinan Tang, Wei Wu, Chenlin Ming, H. Vicky Zhao, Conghui He, Lijun Wu

Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention (D19-1)

Challenge:	Existing approaches focus on improving the quality of correct training data, neglecting the value contained in error data, thereby hindering the model’s reflective ability.
Approach:	They propose to improve LLM's reasoning ability by learning from error data and a grounded mistake augmentation method to collect representative errors.
Outcome:	The proposed model achieves significant performance improvements over other strong models with less than 90k data.

Copied to clipboard

Lei Cao, Huijun Zhang, Ling Feng, Zihan Wei, Xin Wang, Ningyun Li, Xiaohao He

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing approaches to detect suicidal ideation on social media are limited to a small group of people.
Approach:	They propose to use tree holes to embed words into microblogs to strengthen the sensibility of suicide-related lexicons and to use a two-layered attention mechanism to grasp intermittently changing points from individual's open blog streams.
Outcome:	The proposed approach can achieve over 91% accuracy with the use of suicide-oriented word embeddings and attention on a large-scale well-labelled suicide data set.

Copied to clipboard

Wei Liu, Siya Qi, Xinyu Wang, Chen Qian, Yali Du, Yulan He

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

Challenge:	Recent advances in reinforcement learning, such as DeepSeek R1-Zero, highlight the effectiveness of incentive training, but these methods rely on external verifiers, which limits their applicability to domains like mathematics and coding, where such verifier is readily available.
Approach:	They propose a general reinforcement learning framework that requires only standard supervised fine-tuning data with no need for an external verifier.
Outcome:	The proposed framework outperforms the model of the same size distilled from large reasoning models such as DeepSeek R1 671B by 7.7%.

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.

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving (2025.acl-long)

Copied to clipboard

Teng Wang, Wing Yin Yu, Zhenqi He, Zehua Liu, HaileiGong HaileiGong, Han Wu, Xiongwei Han, Wei Shi, Ruifeng She, Fangzhou Zhu, Tao Zhong

AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)

Challenge:	Existing datasets in operations research domain lack detailed annotations of the modeling process, focusing only on objective values.
Approach:	They propose an annotation-based tree-of-thought tree-based reasoning algorithm that integrates reinforcement learning into a tree- of-though.
Outcome:	The proposed algorithm outperforms state-of-the-art methods on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets.

Copied to clipboard

Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang

Federated LoRA Fine-Tuning with Pipelined Error-Mitigated Aggregation and Matrix-Wise Freezing (2026.findings-acl)

Challenge:	Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks.
Approach:	They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.
Outcome:	The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS.

Copied to clipboard

Haoran Wang, Xiong Wang, Yuqing Li, Jing Chen, Junyi Zhang, Nan Yan, Kun He, Wei Wang

Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation (2023.acl-long)

Challenge:	Existing methods for fine-tuning large language models often suffer from biased model aggregation and are hindered by significant communication and computation burden.
Approach:	They propose a Federated low-rank adaptation system for large language models that leverages pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing to mitigate aggregations.
Outcome:	The proposed system improves time-to-target by 2.17-8.48 on real-world datasets.

Copied to clipboard

Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, Weiran Xu

Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation (2024.findings-emnlp)

Challenge:	Existing controllable dialogue generation models focus on single attribute and lack generalization capability to out-of-distribution multiple attribute combinations.
Approach:	They propose a compositional generalization model that learns from seen attributes and generalizes to unseen combinations.
Outcome:	The proposed model can learn from seen attribute values and generalize to unseen combinations.

Copied to clipboard

Bolei He, Nuo Chen, Xinran He, Lingyong Yan, Zhenkai Wei, Jinchang Luo, Zhen-Hua Ling

A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction (2026.findings-acl)

Challenge:	Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models . however, such approach can generate inconsistent answer with external references .
Approach:	They propose to integrate the verification module into the RAG to improve external retrieval correctness and internal generation consistency.
Outcome:	The proposed model can significantly surpass the state-of-the-art baselines using different LLM backbones.

Copied to clipboard

Chengguang Gan, Sunbowen Lee, Qingyu Yin, Yunhao Liang, Xinyang He, Hanjun Wei, Younghun Lim, Shijian Wang, Hexiang Huang, QingHao Zhang, Shiwen Ni, Tatsunori Mori

Multilinguality

Challenge:	Existing work on the Mutual Reinforcement Effect in information extraction has not been empirically validated . 76 percent of the 21 sub-datasets exhibit the Mutual Reforcement effect across languages .
Approach:	They propose a multilingual MRE mix dataset that integrates 21 sub-datasets covering English, Japanese, and Chinese.
Outcome:	The proposed framework reduces manual annotation effort while preserving structural requirements of MRE tasks.

Trustworthiness and Self-awareness in Large Language Models: An Exploration through the Think-Solve-Verify Framework (2024.lrec-main)

Copied to clipboard

Zhendong Liu, Changhong Xia, Wei He, Chongjun Wang

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling (2025.naacl-long)

Challenge:	Large Language Models (LLMs) are becoming increasingly influential in reasoning tasks, but they lack trustworthiness and introspective self-awareness when subjected to complex reasoning tasks.
Approach:	They propose a framework to explore LLMs’ trustworthiness, introspective self-awareness, and collaborative reasoning by using the Think-Solve-Verify framework.
Outcome:	The proposed approach improves from 67.3% to 72.8% on the AQuA dataset and demonstrates the model’s ability to explain the given answers.

Copied to clipboard

Yiwen Ding, Zhiheng Xi, Wei He, Lizhuoyuan Lizhuoyuan, Yitao Zhai, Shi Xiaowei, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang

UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning (2022.emnlp-main)

Challenge:	Large language models (LLMs) generate solutions themselves and iteratively train on filtered, high-quality rationales, but performance reaches a ceiling after a few iterations.
Approach:	They propose a strategy to improve the efficiency of sampling heavy-tailed data by using Socratic-style guidance signals to help LLMs reasoning with complex queries.
Outcome:	The proposed approach is effective on difficult queries and on held-out tasks, while requiring human supervision.

Copied to clipboard

Yutao Mou, Pei Wang, Keqing He, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu

Leveraging Web-Crawled Data for High-Quality Fine-Tuning (2024.findings-emnlp)

Challenge:	Existing methods to detect out-of-domain (OOD) intents ignore alignment between representation learning and scoring function, limiting performance.
Approach:	They propose a unified neighborhood learning framework to detect OOD intents . they propose to align representation learning with scoring function .
Outcome:	The proposed method is able to detect out-of-domain (OOD) intents from user queries.

Copied to clipboard

Jing Zhou, Chenglin Jiang, Wei Shen, Xiao Zhou, Xiaonan He

AdaFuse: Adaptive Ensemble Decoding for Large Language Models (2026.acl-long)

Challenge:	Currently, large language models are fine-tuned using expensive human-annotated data or GPT-4 generated data.
Approach:	They propose to use web-crawled data to train a language model on a smaller set of data . their results show that the model can convert web data with irregular formats into high-quality ones .
Outcome:	The proposed model outperforms open-source models larger than 32B and outperformed open-sourced models such as GPT-3.5.

Copied to clipboard

Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He

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

Challenge:	Existing ensemble approaches to large language models lack flexibility for mid-generation adaptation.
Approach:	They propose an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation.
Outcome:	The proposed framework outperforms existing ensemble frameworks on open-domain QA, arithmetic reasoning, and machine translation tasks.

Copied to clipboard

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

CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models (2024.findings-naacl)

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

Wenhong Zhu, Hongkun Hao, Zhiwei He, Yun-Ze Song, Jiao Yueyang, Yumeng Zhang, Hanxu Hu, Yiran Wei, Rui Wang, Hongyuan Lu

TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models (2024.lrec-main)

Challenge:	Existing methods to evaluate large language models are prone to data contamination.
Approach:	They propose a method which parses contaminated data and back-translates it into a candidate set.
Outcome:	The proposed method reduces data contamination and evaluates the LLMs more cleanly.

Copied to clipboard

Junbing Yan, Chengyu Wang, Taolin Zhang, Xiaofeng He, Jun Huang, Wei Zhang, Longtao Huang, Hui Xue

Enhancing Dialogue Symptom Diagnosis with Global Attention and Symptom Graph (D19-1)

Challenge:	Existing methods for incorporating external knowledge into language models do not prioritize learning embeddings for entity-related tokens.
Approach:	They propose a framework for incorporating external knowledge into pre-training models that utilize entity-related tokens.
Outcome:	The proposed framework reduces pre-training time by 50% and outperforms other KEPLMs in knowledge probing tasks and multiple knowledge-aware language understanding tasks.

Copied to clipboard

Xinzhu Lin, Xiahui He, Qin Chen, Huaixiao Tou, Zhongyu Wei, Ting Chen

Natural Language Interfaces

Challenge:	Existing studies on symptom diagnosis based on EHRs focus on the standard electronic medical records, but the dialogues between doctors and patients that contain more rich information are not well studied.
Approach:	They propose to build a global attention mechanism to capture more symptom related information and build symptom graphs to model the associations between symptoms rather than treating each symptom independently.
Outcome:	The proposed model achieves the state-of-the-art on the constructed dataset.

DialMed: A Dataset for Dialogue-based Medication Recommendation (2022.coling-1)

Copied to clipboard

Zhenfeng He, Yuqiang Han, Zhenqiu Ouyang, Wei Gao, Hongxu Chen, Guandong Xu, Jian Wu

Natural Language Interfaces

Challenge:	Existing studies on medication recommendation mainly rely on EHRs, but some details of interactions between doctors and patients may be ignored or omitted in EHR.
Approach:	They propose to use medical dialogues to recommend medications with medical dialogue data . they propose to model dialogue structure and disease knowledge aware network .
Outcome:	The proposed method is a promising solution to recommend medications with medical dialogues.

Align Voting Behavior with Public Statements for Legislator Representation Learning (2021.acl-long)

Copied to clipboard

Xinyi Mou, Zhongyu Wei, Lei Chen, Shangyi Ning, Yancheng He, Changjian Jiang, Xuanjing Huang

Representation Learning

Challenge:	Existing studies rely on roll call data to estimate political preference of legislators.
Approach:	They propose to integrate voting behavior and public statements on Twitter to jointly model legislators.
Outcome:	The proposed model improves on the task of roll call vote prediction . it also shows that the model captures nuances in statements .

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities (2025.acl-long)

Copied to clipboard

Hui Wei, Zihao Zhang, Shenghua He, Tian Xia, Shijia Pan, Fei Liu

Challenge:	Existing studies have focused on developing LLMs to automate complex planning tasks.
Approach:	They propose to provide a comprehensive overview of current LLM planners to fill this gap . they examine performance criteria including completeness, executability, optimality, representation, generalization, and efficiency .
Outcome:	The proposed survey examines performance criteria for LLM planners and highlights their strengths and weaknesses.

More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage (2026.acl-long)

Copied to clipboard

Wei He

Harnessing Consistency for Robust Test-Time LLM Ensemble (2026.findings-eacl)

Challenge:	Vision-Language Models excel at photorealistic generation, but struggle to represent abstract meanings.
Approach:	They propose a benchmark that replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings.
Outcome:	The proposed benchmark replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings.

Copied to clipboard

Zhichen Zeng, Qi Yu, Xiao Lin, Ruizhong Qiu, Xuying Ning, Tianxin Wei, Yuchen Yan, Jingrui He, Hanghang Tong

Robustness in NLP

Challenge:	Existing efforts to improve LLM ensemble quality have focused on model consistency, but failures are often due to heterogeneous tokenization schemes and varying model expertise.
Approach:	They propose a plug-and-play technique that harnesses model consistency for robust LLM ensemble.
Outcome:	The proposed technique improves ensemble performance and robustness against erroneous signals.

A Flexible Multi-Task Model for BERT Serving (2022.acl-short)

Copied to clipboard

Tianwen Wei, Jianwei Qi, Shenghuan He

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Challenge:	a proposed BERT-based multi-task framework is suitable for iterative and incremental development of the tasks.
Approach:	They propose an efficient BERT-based multi-task framework that is suitable for iterative and incremental development of the tasks.
Outcome:	The proposed framework achieves 99.6% of performance of the full fine-tuning method while reducing up to two thirds of its overhead.

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss (2024.findings-acl)

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

Wei He, Marco Idiart, Carolina Scarton, Aline Villavicencio

Representation Learning

Challenge:	Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in natural language processing (NLP).
Approach:	They propose an approach to model idiomaticity effectively using a triplet loss that incorporates the asymmetric contribution of components words to an idiomatic meaning by using adaptive contrastive learning and resampling miners.
Outcome:	The proposed model outperforms previous models significantly on a SemEval challenge and outperformed previous alternatives in many metrics.

Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning (2025.emnlp-main)

Copied to clipboard

Jingyang Lin, Andy Wong, Tian Xia, Shenghua He, Hui Wei, Mei Han, Jiebo Luo

Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adapt (2024.emnlp-industry)

Challenge:	Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond.
Approach:	They propose a synthetic dataset in the financial domain that integrates Chain-of-Thought reasoning into LLMs in a supervised manner to facilitate effective long-context understanding.
Outcome:	The proposed model outperforms standard GPT-4o-mini on the Loong benchmark and fine tunes LLaMA-3.1-8B-Instruct on the model, achieving a 28.0% gain on the financial subset.

Copied to clipboard

Peter Anderson, Mano Vikash Janardhanan, Jason He, Wei Cheng, Charlie Flanagan

Representation Learning

Challenge:	Financial documents are filled with specialized terminology, arcane jargon, and curious acronyms that pose challenges for general-purpose text embeddings.
Approach:	They propose to fine tune financial text embeddings finetuned on a carefully constructed dataset of 14.3M query-passage pairs including both public and proprietary financial documents.
Outcome:	The proposed embeddings achieve Recall@1 of 62.8% on a held-out test set, vs. only 39.2% for the best general-purpose text embeddING from OpenAI.

LongHeads: Multi-Head Attention is Secretly a Long Context Processor (2024.findings-emnlp)

Copied to clipboard

Yi Lu, Xin Zhou, Wei He, Jun Zhao, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Green & Sustainable NLP

Challenge:	Large language models struggle to process lengthy inputs due to limited length generalization and attention’s quadratic computational demands.
Approach:	They propose a training-free framework that allows each head to attend to important context chunks instead of allowing each head a full sentence .
Outcome:	The proposed framework unlocks multi-head attention's untapped potential by allowing each head to attend to important context chunks instead of the full sentence.

LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration (2024.emnlp-main)

Copied to clipboard

Jun Zhao, Can Zu, Xu Hao, Yi Lu, Wei He, Yiwen Ding, Tao Gui, Qi Zhang, Xuanjing Huang

Question Answering

Challenge:	Large language models (LLMs) have been successful in understanding language and processing text, but their cost prohibits their practical applications.
Approach:	They propose a multi-agent collaboration method that breaks down lengthy documents into smaller, more manageable chunks and organizes the member agents to read their assigned chunks.
Outcome:	The proposed method achieves 16.42% and 1.63% accuracy gains over existing models on single-hop and multi-hop QA settings.

Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (2026.acl-long)

Copied to clipboard

Yuanchen Bei, Tianxin Wei, Xuying Ning, Yanjun Zhao, Zhining Liu, Xiao Lin, Yada Zhu, Hendrik Hamann, Jingrui He, Hanghang Tong

Natural Language Interfaces

Challenge:	Existing benchmarks evaluate multi-session memory in text-only conversations or assess multimodal understanding within localized contexts.
Approach:	They propose a benchmark for evaluating multimodal long-term conversational memory in MLLM agents.
Outcome:	The proposed framework assesses key memory capabilities along three functional dimensions: memory extraction and test-time adaptation, memory reasoning, and memory knowledge management.

ART: rule bAsed futuRe-inference deducTion (2023.emnlp-main)

Copied to clipboard

Mengze Li, Tianqi Zhao, Bai Jionghao, Baoyi He, Jiaxu Miao, Wei Ji, Zheqi Lv, Zhou Zhao, Shengyu Zhang, Wenqiao Zhang, Fei Wu

Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement (2025.emnlp-industry)

Challenge:	Existing studies focus on language-based premises and deduce valid conclusions from visual observations.
Approach:	They propose a rule-based deductive reasoning task that uses video to deduce the correct future event . they use commonsense knowledge to annotate video and a strong baseline to conduct reasoning .
Outcome:	Empirical studies validate the rationality of ARTNet in deductive reasoning upon visual observations . ART is a method that rigorously follows a set of explicit constraints to deduce valid conclusions from empirical facts .

Copied to clipboard

Haotan Guo, Jianfei He, Jiayuan Ma, Hongbin Na, Zimu Wang, Haiyang Zhang, Qi Chen, Wei Wang, Zijing Shi, Tao Shen, Ling Chen

PEER: Pre-training ELECTRA Extended by Ranking (2023.findings-acl)

Challenge:	Phonetic Cloaking Replacement (PCR) is a problem in content moderation in China.
Approach:	They organize PCR into a four-way surface-form taxonomy and compile PCR-ToxiCN, a dataset of 500 phonetically cloaked offensive posts gathered from the RedNote platform.
Outcome:	The proposed model achieves only an F1-score and zero-shot chain-of-thought prompting pushes performance even lower.

Copied to clipboard

Ru He, Wei Wang, Songfang Huang, Fei Huang

PAPERMIND: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs (2026.findings-acl)

Challenge:	Existing models for pre-training require expensive pre-trainer computation cost . ELECTRA model can perform replaced token detection (RTD) task with reduced pre- training cost compared to current models .
Approach:	They propose to extend a discriminator-based replaced token detection task into a ranker-based task . they propose to use a binary classifier to perform a more precise task with negligible additional computation cost.
Outcome:	The proposed model outperforms state-of-the-art models with ELECTRA in GLUE tasks given the same cost.

Copied to clipboard

Yanjun Zhao, Tianxin Wei, Jiaru Zou, Xuying Ning, Yuanchen Bei, Lingjie Chen, Simmi Rana, Wendy H. Yang, Hanghang Tong, Jingrui He

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics (2026.findings-acl)

Challenge:	Existing benchmarks assess integrated and agent-oriented scientific reasoning in isolation . Existing systems assess integrated reasoning in isolated tasks .
Approach:	They propose a benchmark to evaluate integrated and agent-oriented scientific reasoning over research papers.
Outcome:	The proposed benchmark evaluates integrated and agent-oriented scientific reasoning over scientific papers.

Copied to clipboard

Jinxiang Xie, Zihao Li, Wei He, Rui Ding, Shi Han, Dongmei Zhang

Low-Resource NLP

Challenge:	Text analysis of tabular data relies on two core operations: summarization for corpus-level theme extraction and tagging for row-level labeling.
Approach:	They propose a framework that enhances output stability by constraining the model’s latent reasoning trajectory.
Outcome:	The proposed framework improves stability by constraining the model's latent reasoning trajectory.

Towards Visual Question Answering on Pathology Images (2021.acl-short)

Copied to clipboard

Xuehai He, Zhuo Cai, Wenlan Wei, Yichen Zhang, Luntian Mou, Eric Xing, Pengtao Xie

MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Challenge:	Pathology imaging is used for identifying the causes and effects of diseases or injuries.
Approach:	They propose a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images.
Outcome:	The proposed framework performs self-supervised pretraining and finetuning end-to-end to learn powerful visual and textual representations jointly and automatically identifies and excludes noisy self-controlled examples from pretraining.

Copied to clipboard

Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li

Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework (2026.acl-industry)

Challenge:	Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach:	They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome:	The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.

Copied to clipboard

Ziqiang Zhang, Jing Ma, Zilong Wang, Jiayuan Chen, Yi Qiao, Yu He, Wei Zhang, Dai Cheng, Xiaoyu Shen

SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution (2026.findings-acl)

Challenge:	a production-grade pricing system for tourism is challenging due to unstructured nature of travel orders and ever-evolving pricing policies.
Approach:	They propose a production-grade pricing system with a strict decision boundary . they propose to combine structured extraction and bounded policy/path selection with interpretable condition trees .
Outcome:	The proposed system processed 3,960 orders in six months and reduced the order management team from 15-20 to 3 . the system reduced the per-order handling time from 10 minutes to 2 minutes.

Copied to clipboard

Zhenyu He, Qingping Yang, Wei Shen, Xiaojian Zhong, Kechi Zhang, Chenxin An, Wenlei Shi, Tianle Cai, Di He, Jiaze Chen, Jingjing Xu

Answer-focused and Position-aware Neural Question Generation (D18-1)

Challenge:	SWE-Swiss-32B demonstrates strong generalization to other common LLM benchmarks.
Approach:	They propose a two-phase training recipe that decomposes issue resolution into three core skills: Localization, Repair, and Unit Test Generation.
Outcome:	The proposed model achieves a 60.2% score on the SWE-bench Verified benchmark and is in the top-tier performance bracket of much larger models.

Copied to clipboard

Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang

Text Generation

Challenge:	Recent neural network-based approaches generate interrogative words that do not match the answer type.
Approach:	They propose an answer-focused and position-aware neural question generation model to address these issues.
Outcome:	The proposed model outperforms the baseline and outperformed the state-of-the-art system.

CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels (2025.findings-acl)

Copied to clipboard

Lingxiao Wei, He Yan, Lu Xiangju, Junmin Zhu, Jun Wang, Wei Zhang

Information Extraction & Text Mining

Challenge:	Currently, long-context summarization mainly relies on memory ability.
Approach:	They propose a multi-scale long-context summarization benchmark based on Chinese novels . they use human-driven annotations to analyze long-constituency models .
Outcome:	The proposed benchmark features human-driven annotations across four subsets with lengths ranging from 16k to 128k.

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation (2022.findings-acl)

Copied to clipboard

Tianxiang Sun, Xiangyang Liu, Wei Zhu, Zhichao Geng, Lingling Wu, Yilong He, Yuan Ni, Guotong Xie, Xuanjing Huang, Xipeng Qiu

Challenge:	Existing methods to measure instance difficulty use generalization and threshold-tuning . a new approach to learn to exit is based on hash functions to assign tokens to a fixed exiting layer.
Approach:	They propose a Hash-based Early Exiting approach that replaces learn-to-exit modules with hash functions to assign each token to a fixed exiting layer.
Outcome:	The proposed approach improves on learning to exit and predicting instance difficulty.

QueryLink: Leveraging Query-Memory Alignment for Long-Term Reasoning in LLM Agents (2026.findings-acl)

Copied to clipboard

Xuxian Hu, Zhu Teng, Wei Zhang, Ming He, Jianping Fan

Information Retrieval

Challenge:	Existing approaches to integrating external memory prioritize memory organization while overlooking a critical semantic gap between implicit, intent-driven queries and explicit, narrative-based memories.
Approach:	They propose a framework that leverages Query-Memory Alignment to project both queries and memories into a shared semantic space.
Outcome:	The proposed framework significantly outperforms SOTA methods on the LoCoMo and LongMemEval benchmarks and can be integrated as a plug-and-play component to boost existing vector-based systems like A-MEM.

From Complex to Simple: Unraveling the Cognitive Tree for Reasoning with Small Language Models (2023.findings-emnlp)

Copied to clipboard

Yan Junbing, Chengyu Wang, Taolin Zhang, Xiaofeng He, Jun Huang, Wei Zhang

Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy (2020.acl-main)

Challenge:	Existing methods to solve complex logical reasoning problems are cumbersome for language models.
Approach:	They propose to use iterative methodology to construct a cognitive tree using language models . they propose to generate multiple responses by utilizing in-context examples .
Outcome:	The proposed model achieves a performance level comparable to that of GPT-3.5 . the proposed model contains fewer parameters than 5% of the model with 175B parameters .

Copied to clipboard

Xiexiong Lin, Weiyu Jian, Jianshan He, Taifeng Wang, Wei Chu

AIR: Complex Instruction Generation via Automatic Iterative Refinement (2025.emnlp-main)

Challenge:	Knowledge-driven conversation approaches have attracted considerable research attention in recent years.
Approach:	They propose a method that integrates recurrent knowledge interaction among response decoding steps to incorporate appropriate knowledge.
Outcome:	The proposed method improves on two datasets Wizard-of-Wikipedia and DuConv with different knowledge formats and different languages.

Copied to clipboard

Wei Liu, Yancheng He, Yu Li, Hui Huang, Chengwei Hu, Jiaheng Liu, Shilong Li, Wenbo Su, Bo Zheng

Text Generation

Challenge:	Existing methods for generating complex instructions are resource-intensive and lack diversity.
Approach:	They propose a framework to generate complex instructions with constraints using a document-generated initial instruction and an iterative refinement framework to incorporate LLM-as-judge guidance.
Outcome:	The proposed framework significantly outperforms existing methods for generating complex instructions, and outperformed existing methods.

CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection (2025.findings-acl)

Copied to clipboard

Fanxiao Li, Jiaying Wu, Canyuan He, Wei Zhou

Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems (2020.coling-main)

Challenge:	Multimodal large language models have demonstrated impressive capabilities in visual reasoning and text generation.
Approach:	They propose a multimodal large language model that captures deeper relationships between images and text . they propose CMIE, which uses a Coexistence Relationship Generation strategy and an AS mechanism to detect misinformation.
Outcome:	The proposed framework outperforms existing methods in detecting out-of-context misinformation.

Copied to clipboard

Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, Min Yang

Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversity (2025.findings-emnlp)

Challenge:	Existing task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation.
Approach:	They propose a dual dynamic memory network for multi-turn dialog generation . the model dynamically expands the dialog memory turn by turn and keeps track of dialog history .
Outcome:	The proposed model outperforms baseline models on three benchmark datasets on human evaluation and automatic evaluation.

Copied to clipboard

Zihao Li, Feihao Fang, Xitong Zhang, Jiaru Zou, Zhining Liu, Wei Xiong, Ziwei Wu, Baoyu Jing, Jingrui He

O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning (2026.findings-acl)

Challenge:	Using real-world datasets, we conduct the most comprehensive study to date, auditing various state-of-the-art reward models across nine sensitive attributes, including age, gender, ethnicity, etc.
Approach:	They propose a method to mitigate group disparities in reward modeling by using real-world data.
Outcome:	The proposed method is based on a population-based dataset with nine demographic attributes, including gender, ethnicity, age, gender, and ethnicity.

Copied to clipboard

Haotian Luo, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Xiaochun Cao, Dacheng Tao, Naiqiang Tan, Li Shen

Metaphor Reasoning is Meta-reasoning (2026.acl-long)

Challenge:	Recent long-thought reasoning models adopt extended reasoning processes similar to how humans ponder over complex problems.
Approach:	They propose a model that uses RL-style fine-tuning to reduce inference overhead while maintaining accuracy.
Outcome:	The proposed model reduces inference overhead while maintaining accuracy.

Copied to clipboard

Qianyu He, Junting Lu, Yikai Zhang, Siyu Yuan, Xiaojun Meng, Jiansheng Wei, Jiaqing Liang, Yanghua Xiao

Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations (2024.acl-long)

Challenge:	Existing work on metaphor reasoning's impact on reasoning abilities is limited.
Approach:	They propose a system for synthesizing metaphorical riddles that satisfy five quality dimensions: diverse, balanced, reasoning-oriented, challenging, and verifiable.
Outcome:	The proposed system improves reasoning abilities across six domains using only thousands of metaphorical riddles.

Copied to clipboard

Jiaxing Sun, Weiquan Huang, Jiang Wu, Chenya Gu, Wei Li, Songyang Zhang, Hang Yan, Conghui He

LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation (2025.findings-acl)

Challenge:	Currently, many benchmarks evaluate the commonsense reasoning of large language models (LLMs), but most are English-based, limiting non-English evaluations.
Approach:	They propose to use Chinese commonsense reasoning to evaluate LLMs' commonsensing ability.
Outcome:	The proposed benchmark covers both globally known and Chinese-specific commonsense reasoning abilities and can be used as a reference for future research.

Copied to clipboard

Xinrui He, Yikun Ban, Jiaru Zou, Tianxin Wei, Curtiss Cook, Jingrui He

STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning (2026.acl-long)

Challenge:	Existing frameworks for missing data imputation are lacking in a finetuning-free process and mitigating biases and uncertainty in LLM outputs.
Approach:	They propose a framework for imputation of large language models with a forest of few-shot learning LLM "trees" they use bipartite information graphs to identify relevant neighboring entries with feature and value granularity.
Outcome:	The proposed framework is based on a concept of bipartite information graphs to identify high-quality relevant neighboring entries with both feature and value granularity.

Copied to clipboard

Juntong Ni, Shiyu Wang, Qi He, Ming Jin, Wei Jin

Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System (2026.acl-long)

Challenge:	Existing models focus on predictive accuracy over reasoning, a gap exists . time series data are ubiquitous in real-world systems and exhibit complex spatio-temporal structures.
Approach:	They propose a time series reasoning model that integrates time series, graph structure, and text for explicit reasoning.
Outcome:	The proposed model achieves average accuracy gains between 17% and 135% at 0.004x the cost of proprietary models and generalizes robustly to real-world data.

Copied to clipboard

Yifei Wei, Linqing Zhong, Yi Liu, Yuxiang Lu, Xindong He, Maoqing Yao, Guanghui Ren

Challenge:	Vision-Language-Action models ground high-level semantic instructions into executable physical actions.
Approach:	They propose a Coarse-to-Fine Dual-System VLA architecture that decouples learning complexity into a coarse-to fine hierarchy while leveraging structural modularity to implement an asynchronous execution strategy.
Outcome:	The proposed architecture decouples learning complexity into a coarse-to-fine hierarchy while leveraging structural modularity to implement an asynchronous execution strategy.

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage (2025.findings-acl)

Copied to clipboard

Xiaoning Dong, Wenbo Hu, Wei Xu, Tianxing He

Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization (2022.naacl-main)

Challenge:	Existing methods to design sophisticated instructions for the LLM to follow, or rely on multiple iterations, could hinder the performance and efficiency of jailbreaks.
Approach:	They propose a simple assistive task linkage paradigm which masks harmful keywords within malicious queries and uses a masked language model task to encode the semantics of the mangled keywords.
Outcome:	The proposed paradigm can effectively circumvent LLM safeguards and elicit harmful responses.

Copied to clipboard

Lulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He, Weiran Xu, Huixing Jiang, Wei Wu, Yanan Wu

Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)

Challenge:	Existing methods for domain adaptation of abstractive dialogue summarization lack generalization ability on new domains.
Approach:	They propose a domain-oriented prefix-tuning model that uses a prefix module to alleviate domain entanglement and discrete prompts to guide the model to focus on key contents of dialogues.
Outcome:	The proposed model can be generalized to two multi-domain dialogue summarization datasets.

Copied to clipboard

Yu Zou, Yan Chen, Lida He, Qi Zhou, Xiaorui Zhou, Aixi Zhong, Yi Wang, Wei Li, Qingyu Wang, Jiatao Li, Wei Gong, Jialei Zeng, Jingmei Zhao, Ke Jiang, Qing Li

Information Retrieval

Challenge:	Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge.
Approach:	They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage.
Outcome:	The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold.

Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification (P18-1)

Copied to clipboard

Yizhong Wang, Kai Liu, Jing Liu, Wei He, Yajuan Lyu, Hua Wu, Sujian Li, Haifeng Wang

LLM Factoscope: Uncovering LLMs’ Factual Discernment through Measuring Inner States (2024.findings-acl)

Challenge:	Recent years have seen rapid growth in the MRC community . MRC is believed to be a crucial step in building a general intelligent agent .
Approach:	They propose an end-to-end neural model that enables multiple passages to verify each other based on their content representations.
Outcome:	The proposed model outperforms the baseline on the English MS-MARCO dataset and the Chinese DuReader dataset, and achieves state-of-the-art performance on both datasets.

Copied to clipboard

Jinwen He, Yujia Gong, Zijin Lin, Cheng’an Wei, Yue Zhao, Kai Chen

Challenge:	Large Language Models (LLMs) produce outputs that deviate from factual reality, especially in sensitive applications such as medical consultation and legal advice.
Approach:	They propose a Siamese network-based model that leverages LLMs’ inner states for factual detection.
Outcome:	The proposed model achieves over 96% accuracy on a custom-collected factual detection dataset.

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)

Copied to clipboard

Nan He, Weichen Xiong, Hanwen Liu, Yi Liao, Lei Ding, Kai Zhang, Guohua Tang, Xiao Han, Yang Wei

Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold (2022.naacl-main)

Challenge:	Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication.
Approach:	They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness.
Outcome:	The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%.

Copied to clipboard

Yanan Wu, Keqing He, Yuanmeng Yan, QiXiang Gao, Zhiyuan Zeng, Fujia Zheng, Lulu Zhao, Huixing Jiang, Wei Wu, Weiran Xu

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)

Challenge:	Existing methods for OOD detection are based on labeled in-domain data . detecting out-of-domain (OOD) or unknown intents is challenging .
Approach:	They propose a novel reassigned contrastive learning method to discriminate IND intents for over-confident OOD and an adaptive class-dependent local threshold mechanism to separate similar IND and OOD intents.
Outcome:	The proposed method is effective for both aspects of overconfidence issues.

Copied to clipboard

Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo

PAFT: Prompt-Agnostic Fine-Tuning (2025.emnlp-main)

Challenge:	Existing research on reinforcement learning for LLMs under data scarcity has not been unified.
Approach:	They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric.
Outcome:	The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area.

Copied to clipboard

Chenxing Wei, Yao Shu, Mingwen Ou, Ying He, Fei Yu

S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering (2023.acl-short)

Challenge:	Prompt-agnostic fine-tuning (PAFT) improves performance by reducing overfitting to specific prompts.
Approach:	They propose a method that enhances robustness through dynamic prompt variation during training.
Outcome:	The proposed method achieves higher generalization accuracy on unseen prompts than standard methods with similar training efficiency.

Copied to clipboard

Fangyu Lei, Xiang Li, Yifan Wei, Shizhu He, Yiming Huang, Jun Zhao, Kang Liu

PairRE: Knowledge Graph Embeddings via Paired Relation Vectors (2021.acl-long)

Challenge:	Existing question answering systems use a retriever-reader framework to answer multi-hop questions . existing models lack retrieval, selector, and reasoner capabilities .
Approach:	They propose a three-stage text tableQA framework which comprises of retriever, selector, and reasoner.
Outcome:	The proposed framework outperforms baseline methods in the few-shot setting and ranks first on the HybridQA leaderboard.

Copied to clipboard

Linlin Chao, Jianshan He, Taifeng Wang, Wei Chu

pFedRAG: A Personalized Federated Retrieval-Augmented Generation System with Depth-Adaptive Tiered Embedding Tuning (2025.findings-emnlp)

Challenge:	Existing knowledge graph embedding methods fail to solve two major problems at the same time, leading to unsatisfactory results.
Approach:	They propose a model with paired vectors for each relation representation that can be adaptively adjusted to fit for different complex relations.
Outcome:	Experiments on two knowledge graph datasets show the proposed model can handle complex relations and encode relation patterns.

Copied to clipboard

Hangyu He, Xin Yuan, Kai Wu, Ren Ping Liu, Wei Ni

BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis (2022.findings-acl)

Challenge:	Personalized Federated RAG framework enables efficient collaborative fine-tuning of embedding models . depth-adaptive tieered Embedding (DATE) architecture is tailored for local data and training results of each client.
Approach:	a new Personalized Federated RAG framework is proposed for large language models . the framework enables efficient collaborative fine-tuning of embedding models based on common knowledge .
Outcome:	a novel Personalized Federated RAG framework is proposed for large language models . the framework enables efficient collaborative fine-tuning of embedding models based on common knowledge .

Copied to clipboard

Shuo Liang, Wei Wei, Xian-Ling Mao, Fei Wang, Zhiyong He

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis is challenging because a sentence may contain multiple aspects or complicated relationships.
Approach:	They propose a bi-syntax aware Graph Attention Network to model the context of every aspect and sentiment relations across aspects for learning.
Outcome:	The proposed model outperforms the state-of-the-art methods on four benchmark datasets.

DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models (2025.naacl-long)

Copied to clipboard

Wei He, Kai Han, Yehui Tang, Chengcheng Wang, Yujie Yang, Tianyu Guo, Yunhe Wang

A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis (2021.emnlp-main)

Challenge:	Large language models (LLMs) face excessive computational and memory requirements due to the commonly used Transformer architecture.
Approach:	They propose a method to enhance the flow of hidden information between layers in large language models by selectively integrating shallow-layer hidden states into deeper layers.
Outcome:	The proposed method maintains parallelizability and inference efficiency of SSMs while significantly boosting performance on public benchmarks.

Copied to clipboard

Jiawei Liu, Kaisong Song, Yangyang Kang, Guoxiu He, Zhuoren Jiang, Changlong Sun, Wei Lu, Xiaozhong Liu

A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis (2022.coling-1)

Challenge:	Recent efforts to predict chatbot failure hatches vital apprehensions due to complexity of human conversation.
Approach:	They propose a model that integrates dialogue satisfaction estimation and handoff prediction in one multi-task learning framework.
Outcome:	The proposed model integrates dialogue satisfaction estimation and handoff prediction in one multi-task learning framework.

Copied to clipboard

Wei Chen, Jinglong Du, Zhao Zhang, Fuzhen Zhuang, Zhongshi He

Information Extraction & Text Mining

Challenge:	Existing methods for aspect-sentiment analysis ignore internal correlations between aspect extraction and sentiment classification.
Approach:	They propose a hierarchical interactive network to model two-way interactions between two tasks appropriately using shallow-level and deep-level inputs.
Outcome:	Extensive experiments on three real-world datasets demonstrate that the proposed model outperforms existing methods.

Learning to Instruct: Fine-Tuning a Task-Aware Instruction Optimizer for Black-Box LLMs (2025.findings-emnlp)

Copied to clipboard

Yunzhe Qi, Jinjin Tian, Tianci Liu, Ruirui Li, Tianxin Wei, Hui Liu, Xianfeng Tang, Monica Xiao Cheng, Jingrui He

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models (2024.findings-naacl)

Challenge:	Learning to Instruct is a new paradigm for black-box LLMs with inaccessible internal states.
Approach:	They propose a new paradigm that formulates instruction optimization as an LLM fine-tuning objective for a white-box “instruction engineer” LLM.
Outcome:	The proposed framework outperforms strong baselines in performance and efficiency.

Copied to clipboard

Wei He, Shichun Liu, Jun Zhao, Yiwen Ding, Yi Lu, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? (2026.findings-acl)

Challenge:	Existing methods that rely on limited demos and out-of-demonstration (OOD) queries fail when faced with out- of-demotion queries.
Approach:	They propose a query-aware prompting method that elicits the inherent generalizability of large language models by query-based demo generation.
Outcome:	The proposed method outperforms state-of-the-art methods in the OOD setting and two public math benchmarks.

Copied to clipboard

Zewen Liu, Juntong Ni, Xianfeng Tang, Max SY Lau, Qi He, Wenpeng Yin, Wei Jin

A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) and Multimodal LLMs (MLLMs) show strong performance in complex reasoning tasks, but their ability to extract symbolic laws from time series data remains underexplored.
Approach:	They propose a benchmark to assess symbolic reasoning over real-world time series across three tasks: multivariate symbolic regression, Boolean network inference, and causal discovery.
Outcome:	The proposed framework integrates LLMs with genetic programming to form a closed-loop symbolic reasoning system.

Copied to clipboard

Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)

Challenge:	Inductive reasoning is an important task for large language models (LLMs).
Approach:	They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome:	The proposed method improves inductive reasoning in large language models.

Copied to clipboard

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling (2025.acl-long)

Challenge:	Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment.
Approach:	They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives.
Outcome:	The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering.

Copied to clipboard

Jiayi Zeng, Yizhe Feng, Mengliang He, Wenhui Lei, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou

DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models (2024.emnlp-main)

Challenge:	Current error-handling works are performed in a passive manner, with explicit error- handling instructions.
Approach:	They propose a new benchmark to analyze LLMs' performance on a mis-prompt benchmark and a dataset to promote further research.
Outcome:	The proposed benchmark shows that current LLMs show poor performance on proactive error handling, and that SFT improves on error handling instances.

Copied to clipboard

Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, Kang Liu

Programming Languages in NLP

Challenge:	DA-Code is a code generation benchmark designed to assess LLMs on agent-based data science tasks.
Approach:	They propose a code generation benchmark specifically designed for LLMs on agent-based data science tasks.
Outcome:	The benchmark performs better than existing frameworks, but lacks accuracy . it is based on real-world data, and includes examples that cover a wide range of tasks .

Matching Article Pairs with Graphical Decomposition and Convolutions (P19-1)

Copied to clipboard

Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu

Structured Data in NLP

Challenge:	Existing methods for matching sentence pairs do not perform well in longer documents . Existing approaches for matching sentences do not work in longer document understanding tasks .
Approach:	They propose to model article pairs by comparing sentences that enclose same concept vertex . they propose to use a concept interaction graph to match articles by encoding sentences .
Outcome:	The proposed methods show significant improvements over existing methods . the proposed datasets consist of 30K pairs of breaking news articles .

DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)

Copied to clipboard

Shaokai He, Kaiwen Wei, Xinyi Zeng, Xiang Chen, Xue Yang, Zhenyang Li, Jiang Zhong, Yu Tian

IDEA: An Interpretable and Editable Decision-Making Framework for LLMs via Verbal-to-Numeric Calibration (2026.findings-acl)

Challenge:	Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs .
Approach:	They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations .
Outcome:	The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation .

Copied to clipboard

Yanji He, Yuxin Jiang, Yiwen Wu, Bo Huang, Jiaheng Wei, Wei Wang

Explainability & Interpretability in NLP

Challenge:	Existing approaches fail to integrate domain expert insights beyond simple prompting.
Approach:	They propose a framework that extracts LLM decision knowledge into an interpretable parametric model over semantically meaningful factors.
Outcome:	Experiments show that IDEA outperforms DeepSeek R1 and GPT-5.2 in accuracy and accuracy.

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios (2025.acl-long)

Copied to clipboard

Xiaodong Wu, Minhao Wang, Yichen Liu, Xiaoming Shi, He Yan, Lu Xiangju, Junmin Zhu, Wei Zhang

Flexora: Flexible Low-Rank Adaptation for Large Language Models (2025.acl-long)

Challenge:	Existing benchmarks rarely focus on instruction-following in long-context scenarios or stability on different inputs.
Approach:	They propose a scalable dataset to evaluate LLMs’ instruction-following capabilities and stability across long contexts.
Outcome:	The proposed method evaluates LLMs’ instruction-following capabilities and stability across long contexts.

Copied to clipboard

Chenxing Wei, Yao Shu, Ying Tiffany He, Fei Yu

ECC: An Emotion-Cause Conversation Dataset for Empathy Response (2025.emnlp-main)

Challenge:	Large language models (LLMs) have revolutionized artificial intelligence, but performance on specific tasks is limited by knowledge boundaries.
Approach:	They propose a method that automatically selects the most critical layers for fine-tuning to optimize performance across diverse downstream tasks.
Outcome:	The proposed method outperforms baseline models and natural language tasks.

Copied to clipboard

Yuanyuan He, Yongsen Pan, Wei Li, Jiali You, Jiawen Deng, Fuji Ren

Masked Conditional Random Fields for Sequence Labeling (2021.naacl-main)

Challenge:	Existing empathy dialogue datasets focus on emotion labels while cause annotations are added post hoc.
Approach:	They propose an emotion-cause conversation dataset with 2.4K dialogues that can be scalable . they use a framework that utilizes knowledge and large language models to automatically generate dialogues .
Outcome:	The proposed dataset can achieve comparable or even superior performance to existing empathy dialogue datasets.

Copied to clipboard

Tianwen Wei, Jianwei Qi, Shenghuan He, Songtao Sun

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability (2025.findings-acl)

Challenge:	Conditional Random Fields (CRF) based neural models are among the most performant for sequence labeling problems, but they can sometimes generate illegal sequences of tags.
Approach:	They propose a conditional random field-based model that imposes restrictions on candidate paths during both training and decoding phases.
Outcome:	The proposed method improves on existing CRF models with near zero additional cost.

Copied to clipboard

Mengliang He, Jiayi Zeng, Yankai Jiang, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou

Programming Languages in NLP

Challenge:	Existing code generation benchmarks neglect flowchart-based code generation . existing benchmarks lack flowcharting-based evaluation, limiting the potential of large language models and minimizing human error.
Approach:	They propose to use flowcharts to evaluate existing LLMs' code generation capabilities.
Outcome:	The proposed benchmarks show that the supervised fine-tuning technique contributes greatly to the models’ performance.

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models (2025.naacl-long)

Copied to clipboard

Ying Nie, Binwei Yan, Tianyu Guo, Hao Liu, Haoyu Wang, Wei He, Binfan Zheng, Weihao Wang, Qiang Li, Weijian Sun, Yunhe Wang, Dacheng Tao

Distill Visual Chart Reasoning Ability from LLMs to MLLMs (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored.
Approach:	They propose a benchmark to assess the financial knowledge of large language models (LLMs) in China.
Outcome:	The proposed benchmark is the most comprehensive evaluation benchmark to date for LLMs in finance.

Copied to clipboard

Wei He, Zhiheng Xi, Wanxu Zhao, Xiaoran Fan, Yiwen Ding, Zifei Shan, Tao Gui, Qi Zhang, Xuanjing Huang