Papers by Wei Jin

Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs (2021.acl-long)

Challenge:	Previous work shows that large language models generate hallucinations, yet the origins and mechanisms of these signals remain unclear.
Approach:	They propose to validate and disentangle two different pathways for truthfulness cues . they also propose to use the same mechanism to derive self-contained evidence from the generated answer .
Outcome:	The proposed applications improve hallucination detection performance by integrating two different inputs.

Copied to clipboard

Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents (2026.acl-long)

Challenge:	Temporal Knowledge Graphs (TKGs) are used in many different areas of research.
Approach:	They propose to use a beam search policy to induce multiple clues from historical facts . they propose to adopt a graph convolution network based sequence method to deduce answers from clues .
Outcome:	The proposed model can predict future facts in two stages, Clue Searching and Temporal Reasoning.

Copied to clipboard

null Ymyang, Jiang Zhong, Li Jin, Xiao Sun, Jingwang Huang, null Gaojinpeng, Qing Liu, Yang Bai, Jingyuan Zhang, Rui Jiang, Qin Lei, Kaiwen Wei

CodeArena: Evaluating and Aligning CodeLLMs on Human Preference (2025.emnlp-main)

Challenge:	Existing benchmarks focus on simple image-text interactions, overlooking complex visual formats like charts.
Approach:	They propose a semi-automatic framework for generating evaluation samples through multi-modal keypoint extraction, knowledge graph construction, and qa pair synthesis.
Outcome:	The proposed framework generates 4,738 question-answering pairs across 8 domains from real-world documents.

Copied to clipboard

Jian Yang, Jiaxi Yang, Wei Zhang, Jin Ke, Yibo Miao, Lei Zhang, Liqun Yang, Zeyu Cui, Yichang Zhang, Zhoujun Li, Binyuan Hui, Junyang Lin

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (2024.emnlp-main)

Challenge:	Code large language models (codeLLMs) focus on synthesizing the correct code snippet, ignoring the alignment with human preferences.
Approach:	They propose a benchmark code-based on 40 categories and 44 programming languages to emulate real-world coding tasks.
Outcome:	The proposed benchmarks show that open-source code LLMs perform better than open-sourced ones.

Copied to clipboard

Yu Zhang, Xiusi Chen, Bowen Jin, Sheng Wang, Shuiwang Ji, Wei Wang, Jiawei Han

Respond in my Language: Mitigating Language Inconsistency in Response Generation based on Large Language Models (2024.acl-long)

Challenge:	Existing surveys on scientific LLMs focus on one or two fields or a single modality.
Approach:	They survey 260 scientific LLMs and examine their architectures and pre-training techniques . they also discuss commonalities and differences between LLM architectures .
Outcome:	The proposed model architectures and evaluation techniques are used to improve scientific discovery.

Copied to clipboard

Liang Zhang, Qin Jin, Haoyang Huang, Dongdong Zhang, Furu Wei

Text Generation

Challenge:	Large Language Models (LLMs) show strong instruction understanding ability across multiple languages, but are easily biased towards English in instruction tuning.
Approach:	They propose to use a model with Pseudo-Inconsistent Penalization to prevent the model from generating English responses when given non-English language prompts during training and prior Enhanced decoding to improve the language consistency of the model.
Outcome:	The proposed methods significantly improve the language consistency of the model without multilingual data.

A Survey on Efficient Large Language Model Training: From Data-centric Perspectives (2025.acl-long)

Copied to clipboard

Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, Ming Zhang

PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback (2026.findings-acl)

Challenge:	achieving data-efficient post-training of Large Language Models is a key research question.
Approach:	They propose a taxonomy of data-efficient LLM post-training methods from a data-centric perspective.
Outcome:	The proposed methods cover data selection, data quality enhancement, synthetic data generation, data distillation and compression, and self-evolving data ecosystems.

Copied to clipboard

Wei Xia, Jin Wu, Haoran Shi, Xiangyu Wang, Chanjin Zheng

Explainability & Interpretability in NLP

Challenge:	Existing approaches to Automated Essay Scoring (AES) treat scoring and feedback as separate components, resulting in fragmentation.
Approach:	They propose a psychometrically-aware framework that integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation.
Outcome:	The proposed framework integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation.

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

Copied to clipboard

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

Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems (2025.emnlp-main)

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

Copied to clipboard

Song Jin, Juntian Zhang, Yuhan Liu, Xun Zhang, Yufei Zhang, Guojun Yin, Fei Jiang, Wei Lin, Rui Yan

Challenge:	Existing platforms lack a mechanism for user actions to dynamically reshape the environment.
Approach:	They propose a novel agent-based simulation platform for recommender systems with a robust interaction mechanism.
Outcome:	The proposed platform improves the credibility of the simulation and replicates the Matthew Effect and Brand Loyalty.

A Neural Transition-based Model for Nested Mention Recognition (D18-1)

Copied to clipboard

Bailin Wang, Wei Lu, Yu Wang, Hongxia Jin

Challenge:	Existing methods to recognize nested mentions are based on Stack-LSTM . nesting mentions can be used for downstream tasks like question answering and relation extraction.
Approach:	They propose a scalable transition-based method to model the nested structure of mentions.
Outcome:	The proposed method gets the state-of-the-art performance in ACE datasets showing its effectiveness in detecting nested mentions.

Distributed LLM Serving on Consumer-Grade GPUs by Reconciling Computation and Communication (2025.findings-emnlp)

Copied to clipboard

Lewei Jin, Kui Zhang, Yongqi Chen, null Zhuoyifan, Renjie Li, Yi Gao, Bowei Yang, Zhengong Cai, Wei Dong

Green & Sustainable NLP

Challenge:	Large language models are reshaping internet services, and serving them is costly.
Approach:	They propose an efficient distributed LLM serving system that splits prefill and decode requests into smaller chunks .
Outcome:	The proposed system reduces TTFT, TPOT, and latency compared to the state-of-the-art system.

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

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.

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Copied to clipboard

Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen

PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting (2022.findings-naacl)

Challenge:	Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach:	They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome:	The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .

Copied to clipboard

Zhen Zhang, Wei Zhu, Jinfan Zhang, Peng Wang, Rize Jin, Tae-Sun Chung

Self-Harmonized Chain of Thought (2025.naacl-long)

Challenge:	Pre-trained language models (PLMs) are the state-of-the-art (SOTA) models for natural language processing (NLP).
Approach:	They propose a patient and confident early exiting BERT (PCEE-BERT) that can work with different PLMs and popular model compression methods.
Outcome:	The proposed method outperforms existing models on the GLUE benchmarks and achieves different speed-up ratios.

Copied to clipboard

Ziqi Jin, Wei Lu

DocumentNet: Bridging the Data Gap in Document Pre-training (2023.emnlp-industry)

Challenge:	Existing methods for chain-of-thought prompting have limitations . arithmetic, commonsense, and symbolic reasoning tasks are challenging .
Approach:	They propose a method that unifies diverse solution paths into a consistent reasoning pattern.
Outcome:	The proposed method outperforms existing methods by 2.8% on reasoning tasks.

Copied to clipboard

Lijun Yu, Jin Miao, Xiaoyu Sun, Jiayi Chen, Alexander Hauptmann, Hanjun Dai, Wei Wei

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)

Challenge:	Document understanding tasks are a tedious task that requires extensive training and privacy constraints.
Approach:	They propose a method to collect weakly labeled data from the web to benefit VDER training . the collected dataset does not depend on specific document types or entity sets .
Outcome:	The proposed method does not depend on specific document types or entity sets, making it universally applicable to all VDER tasks.

Copied to clipboard

Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

A Comprehensive Evaluation of Quantization Strategies for Large Language Models (2024.findings-acl)

Challenge:	Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps.
Approach:	They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts.
Outcome:	The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models.

Copied to clipboard

Renren Jin, Jiangcun Du, Wuwei Huang, Wei Liu, Jian Luan, Bin Wang, Deyi Xiong

Guide the Many-to-One Assignment: Open Information Extraction via IoU-aware Optimal Transport (2023.acl-long)

Challenge:	Quantization studies have focused on instruction-tuned LLMs, leaving their performance on other benchmarks unclear.
Approach:	They propose a framework to evaluate quantized large language models using four dimensions . they propose to reduce the bits needed for model weights or activations with minimal performance loss .
Outcome:	The proposed framework can retain comparable performance to non-quantized LLMs on most benchmarks.

Copied to clipboard

Kaiwen Wei, Yiran Yang, Li Jin, Xian Sun, Zequn Zhang, Jingyuan Zhang, Xiao Li, Linhao Zhang, Jintao Liu, Guo Zhi

ADEPT-SQL: A High-performance Text-to-SQL Application for Real-World Enterprise-Level Databases (2025.acl-demo)

Challenge:	Open Information Extraction (OIE) aims to extract structured information from text without the limitations of close ontology.
Approach:	They propose a method to assign ground truth labels to parallelly generated tuple proposals . they leverage intersection-over-union (IoU) as assignment quality measurement .
Outcome:	The proposed method outperforms the state-of-the-art models on three benchmarks.

Copied to clipboard

Yongnan Chen, Zhuo Chang, Shijia Gu, Yuanhang Zong, Zhang Mei, Shiyu Wang, Hezixiang Hezixiang, Hongzhi Chen, Jin Wei, Bin Cui

Programming Languages in NLP

Challenge:	et al., 2017) address domain-specific knowledge barriers, schemas complexity, and computational costs of large LLMs.
Approach:	They propose a domain-adapted Text2SQL system that addresses critical deployment challenges in professional fields.
Outcome:	The proposed system achieves 97% execution accuracy on real-world databases . it is faster than existing systems and has a higher performance than existing ones.

Video Dialog via Progressive Inference and Cross-Transformer (D19-1)

Copied to clipboard

Weike Jin, Zhou Zhao, Mao Gu, Jun Xiao, Furu Wei, Yueting Zhuang

Natural Language Interfaces

Challenge:	Existing visual dialog methods use RNN to encode the dialog history as a vector representation . a new method for video dialog is proposed, which progressively updates query information based on dialog history and video content until the agent think the information is sufficient and unambiguous.
Approach:	They propose a method which progressively updates query information based on dialog history and video content until the agent thinks it is sufficient and unambiguous.
Outcome:	The proposed method can be used to infer video dialog answers on large-scale datasets.

On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning (2026.acl-long)

Copied to clipboard

Di Wu, Jiaxin Fan, Chloe Gu, Guanbo Wang, Wei Yin, Wenhao Li, Bo Jin

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety (2026.acl-long)

Challenge:	Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and verbal goals.
Approach:	They propose an On-policy Reinforcement fine-tuning framework with offline rewards for Embodied Task Planning that preserves generalization benefits of RFT while addressing costly interaction and sparse rewards.
Outcome:	The proposed framework outperforms closed-source and online-RL methods on EmbodiedBench, a recent benchmark for interactive embodied tasks.

Copied to clipboard

Can Jin, Rui Wu, Tong Che, Qixin Zhang, Hongwu Peng, Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han, Zhao Zhang, Yuan Cao, Ruixiang Tang, Dimitris N. Metaxas

Robustness in NLP

Challenge:	OpenAI introduces deliberative alignment (DA) to enhance safety of its o-series models, but effectiveness of this approach in open-source LLMs is understudied.
Approach:	They propose a case-augmented deliberative alignment method for large language models . they propose to use reinforcement learning on self-generated safety reasoning chains .
Outcome:	The proposed method avoids narrowly enumerated rules and allows broader adaptability.

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

Copied to clipboard

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

Incorporating Emoji Descriptions Improves Tweet Classification (N19-1)

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

Copied to clipboard

Abhishek Singh, Eduardo Blanco, Wei Jin

Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs (2025.naacl-long)

Challenge:	Tweets are short messages that often include specialized language such as hashtags and emojis.
Approach:	They propose a simple strategy to replace emojis with their natural language description and use pretrained word embeddings to process tweets.
Outcome:	The proposed method is more effective than pretrained emoji embeddings for tweet classification.

Copied to clipboard

Jiancheng Dong, Lei Jiang, Wei Jin, Lu Cheng

BinaryBERT: Pushing the Limit of BERT Quantization (2021.acl-long)

Challenge:	Randomly concatenating data points can lead to cross-contamination due to the significant difference in their subject matter.
Approach:	They propose a method that randomly concatenates data of varying lengths until reaching the designed maximum length to optimize context length and reduce padding.
Outcome:	The proposed method significantly improves performance on GSM8K and HumanEval, and also improves fairness and accuracy by 15%.

Copied to clipboard

Haoli Bai, Wei Zhang, Lu Hou, Lifeng Shang, Jin Jin, Xin Jiang, Qun Liu, Michael Lyu, Irwin King

TabPrompt: Graph-based Pre-training and Prompting for Few-shot Table Understanding (2023.findings-emnlp)

Challenge:	Recent pre-trained language models have achieved remarkable performance improvement in various tasks, but the improvement generally comes at the cost of increasing model size and computation.
Approach:	They propose a binary quantization technique which initializes binaryBERT by splitting from a ternary network.
Outcome:	The proposed model achieves state-of-the-art performance on the GLUE and SQUAD benchmarks while being 24x smaller.

Copied to clipboard

Rihui Jin, Jianan Wang, Wei Tan, Yongrui Chen, Guilin Qi, Wang Hao

Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval (2021.acl-long)

Challenge:	Existing methods of Table Understanding (TU) focus on the textual content within the tabular data, disregarding the topological information of the table.
Approach:	They propose a framework that uses tabs to understand tabular data without ignoring the topological information of the table.
Outcome:	The proposed framework outperforms baselines in few-shot table understanding tasks.

Copied to clipboard

Hongyin Tang, Xingwu Sun, Beihong Jin, Jingang Wang, Fuzheng Zhang, Wei Wu

Representation Learning

Challenge:	Existing retrieval models based on dense representations show better performance than sparse representations.
Approach:	They propose a method to mimic the queries to each of the documents by an iterative clustering process and represent the documents using multiple pseudo queries.
Outcome:	The proposed model achieves state-of-the-art results on a large dataset while remaining high efficiency.

Find-the-Common: A Benchmark for Explaining Visual Patterns from Images (2024.lrec-main)

Copied to clipboard

Yuting Shi, Naoya Inoue, Houjing Wei, Yufeng Zhao, Tao Jin

P²Net: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts (2025.findings-acl)

Challenge:	Recent advances in Instruction-fine-tuned Vision and Language Models (IVLMs) have prompted some studies to analyze the reasoning capabilities of IVLMs.
Approach:	They introduce a vision and language task for Inductive Visual Reasoning that uses common attributes across visual scenes to find common answers.
Outcome:	The proposed model can archive with 48% accuracy on the FTC, compared with state-of-the-art models.

Copied to clipboard

Kaiwen Wei, Jie Yao, Jiang Zhong, Yangyang Kang, Jingyuan Zhang, Changlong Sun, Xin Zhang, Fengmao Lv, Li Jin

Sailor: Open Language Models for South-East Asia (2024.emnlp-demo)

Challenge:	Existing methods for key information extraction are based on a limited set of entity categories and fixed layouts.
Approach:	They propose a large-scale, human-annotated dataset for key information extraction . it is based on a human-annotated layout and 1,162 entity categories . they propose 'parallel pointer-based network' that leverages implicit relationships .
Outcome:	Experiments on widely-used datasets show that the proposed model outperforms state-of-the-art methods while maintaining fast inference speeds.

Copied to clipboard

Longxu Dou, Qian Liu, Guangtao Zeng, Jia Guo, Jiahui Zhou, Xin Mao, Ziqi Jin, Wei Lu, Min Lin

Assist Non-native Viewers: Multimodal Cross-Lingual Summarization for How2 Videos (2022.emnlp-main)

Challenge:	Large language models (LLMs) rely on English data for training, but are often not comparable across other languages.
Approach:	They propose to develop a family of open language models for SEA languages . they use BPE dropout, aggressive data cleaning and deduplication to improve model robustness .
Outcome:	The proposed models perform well across four benchmarks, including commonsense reasoning, question answering, reading comprehension and examination.

Copied to clipboard

Nayu Liu, Kaiwen Wei, Xian Sun, Hongfeng Yu, Fanglong Yao, Li Jin, Guo Zhi, Guangluan Xu

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

Challenge:	Existing multimodal summarization methods are limited to monolingual videos . a proposed task aims to generate cross-lingual summaries from multimodal inputs .
Approach:	They propose a task to generate cross-lingual summaries from multimodal inputs of videos . they propose fusion network that integrates multimodal and cross-linguistic information .
Outcome:	The proposed task outperforms existing methods on a reorganized How2 dataset on the reorganized How2 data set.

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

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models (2026.findings-acl)

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

Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, Deyi Xiong

Few-shot Link Prediction on Hyper-relational Facts (2024.lrec-main)

Challenge:	Reinforcement learning with verifiable rewards (RLVR) has emerged as a paradigm for enhancing the reasoning capabilities of large language models.
Approach:	They propose a positive-advantage reweighting approach that regulates model entropy by adjusting the loss weights assigned to tokens with positive advantages during RLVR training.
Outcome:	The proposed approach regulates model entropy by adjusting loss weights assigned to tokens with positive advantages during RLVR training while maintaining competitive performance.

Copied to clipboard

Jiyao Wei, Saiping Guan, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Chain-of-Specificity: Enhancing Task-Specific Constraint Adherence in Large Language Models (2025.coling-main)

Challenge:	Existing methods to predict missing elements in hyper-relational facts require high-quality data.
Approach:	They propose a task to predict a missing entity in a hyper-relational fact with limited support instances.
Outcome:	The proposed model outperforms existing models on three datasets.

Copied to clipboard

Kaiwen Wei, Jiang Zhong, Hongzhi Zhang, Fuzheng Zhang, Di Zhang, Li Jin, Yue Yu, Jingyuan Zhang

NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing approaches to enhancing large language models fail to emphasize specific constraints and unlock the underlying knowledge.
Approach:	They propose a method that emphasizes specific constraints and unlocks knowledge within LLMs by iteratively emphasising on specific constraints.
Outcome:	The proposed method outperforms existing methods in enhancing generated content, especially in terms of specificity.

Copied to clipboard

Yue Fang, Shaohan Huang, Xin Yu, Haizhen Huang, Zihan Zhang, Weiwei Deng, Furu Wei, Feng Sun, Qi Zhang, Zhi Jin

Machine Translation

Challenge:	Existing formal proof assistants rely on instruction tuning and lack fine-grained structural and semantic alignment.
Approach:	They propose a reinforcement learning framework that enables LLMs to translate natural language into formal language such as Lean 4 . they use a model with basic translation ability to refine the model's reinforcement learning .
Outcome:	The proposed method outperforms baseline models on NL-to-Lean 4 tasks.

Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction (2021.acl-long)

Copied to clipboard

Kaiwen Wei, Xian Sun, Zequn Zhang, Jingyuan Zhang, Guo Zhi, Li Jin

STRUX: An LLM for Decision-Making with Structured Explanations (2025.naacl-short)

Challenge:	Existing methods to extract event arguments focus on learning pair-wise information between arguments and the given trigger.
Approach:	They propose a framework to extract event-related arguments from a given event frame-level scope.
Outcome:	The proposed method achieves state-of-the-art on the RAMS dataset.

Copied to clipboard

Yiming Lu, Yebowen Hu, Hassan Foroosh, Wei Jin, Fei Liu

GOME: Grounding-based Metaphor Binding With Conceptual Elaboration For Figurative Language Illustration (2024.emnlp-main)

Challenge:	a new LLM decision-making framework is designed to help users understand how and why decisions are made.
Approach:	They introduce a new LLM decision-making framework called STRUX that provides structured explanations for LLM decisions.
Outcome:	The proposed framework improves decision-making by providing structured explanations . it has been evaluated on the task of forecasting stock investment decisions based on earnings call transcripts - superior performance against strong baselines compared with previous frameworks based upon earnings call transcriptions demonstrating superior performance .

Copied to clipboard

Linhao Zhang, Jintao Liu, Li Jin, Hao Wang, Kaiwen Wei, Guangluan Xu

Visual Data in NLP

Challenge:	Existing Large Language Models (LLMs) and multimodal models are unable to illustrate figurative language based on literal objects, ignoring the underlying groundings and associations across disparate metaphorical domains.
Approach:	They propose a grounding-based method for metaphor illustration that integrates metaphorical knowledge into systematic instructions for existing large language models.
Outcome:	The proposed method is superior to existing LLMs, diffusion models, or their direct collaboration.

TrustAgent: Towards Safe and Trustworthy LLM-based Agents (2024.findings-emnlp)

Copied to clipboard

Wenyue Hua, Xianjun Yang, Mingyu Jin, Zelong Li, Wei Cheng, Ruixiang Tang, Yongfeng Zhang

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

Challenge:	Existing LLMs are primarily used for simple text-related tasks, but LLM-based agents can undertake more complex tasks that require planning and interaction with the physical world and humans.
Approach:	They propose an Agent-Constitution-based agent framework with a particular focus on improving the LLM-based agents' safety.
Outcome:	The proposed framework can enhance an LLM agent’s safety across multiple domains by identifying and mitigating potential dangers during the planning process.

Copied to clipboard

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

CDA: A Contrastive Data Augmentation Method for Alzheimer’s Disease Detection (2023.findings-acl)

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

Junwen Duan, Fangyuan Wei, Jin Liu, Hongdong Li, Tianming Liu, Jianxin Wang

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)

Challenge:	Existing methods for detecting AD are challenging and time-consuming due to lack of data and generalizability of the models.
Approach:	They propose a contrastive data augmentation method which simulates the cognitive impairment of a patient by randomly deleting a proportion of text from the transcript to create negative samples.
Outcome:	The proposed method achieves the best performance among language-based models on the benchmark ADReSS Challenge dataset.

Copied to clipboard

Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Dialogue Systems & Conversational Agents

Challenge:	Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns.
Approach:	They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory.
Outcome:	Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy.

Plug and Play Knowledge Distillation for kNN-LM with External Logits (2022.aacl-short)

Copied to clipboard

Xuyang Jin, Tao Ge, Furu Wei

Tab-CoT: Zero-shot Tabular Chain of Thought (2023.findings-acl)

Challenge:	Despite the promising evaluation results by knowledge distillation (KD) in natural language understanding (NLU) and sequence-to-sequence (seq2sequ) tasks, KD for causal language modeling (LM) remains a challenge.
Approach:	They propose to use external logits to improve a student's kNN-LM by leveraging teacher's knowledge at test time.
Outcome:	The proposed method improves a student's kNN-LM in multiple language modeling datasets and improves perplexity.

Copied to clipboard

Jin Ziqi, Wei Lu

Narrative Order Aware Story Generation via Bidirectional Pretraining Model with Optimal Transport Reward (2023.findings-emnlp)

Challenge:	Recent efforts to encourage more structured reasoning procedures to be captured have shown that chain-of-though (CoT) prompting methods can be effective in NLP tasks.
Approach:	They propose a tabular-format CoT prompting method that allows the complex reasoning process to be explicitly modeled in a highly structured manner.
Outcome:	The proposed method shows impressive performance improvements on a range of reasoning tasks.

Copied to clipboard

Zhicong Lu, Li Jin, Guangluan Xu, Linmei Hu, Nayu Liu, Xiaoyu Li, Xian Sun, Zequn Zhang, Kaiwen Wei

Can GRPO Boost Complex Multimodal Table Understanding? (2025.emnlp-main)

Challenge:	Existing storytelling systems suffer from insufficient understanding of event correlations and inadequate awareness of event temporal order.
Approach:	They propose a narrative order aware framework to generate coherent stories with flashbacks . they propose 'bidirectional pretraining model with Optimal Transport Reward' to improve quality .
Outcome:	The proposed framework generates coherent stories with flashbacks with a novel optimal transport reward.

Copied to clipboard

Xiaoqiang Kang, Shengen Wu, Zimu Wang, Yilin Liu, Xiaobo Jin, Kaizhu Huang, Wei Wang, Yutao Yue, Xiaowei Huang, Qiufeng Wang

Contextual Modeling for Document-level ASR Error Correction (2024.lrec-main)

Challenge:	Existing table understanding methods struggle with low initialization accuracy and coarse rewards in tabular contexts.
Approach:	They propose a three-stage RL framework that enhances multimodal table understanding through: (1) Warm-up that prompts initial perception and reasoning capabilities; (2) Perception Alignment GRPO (PA-GRPO); (3) Hint-Completion GR PO (HC-GRP);
Outcome:	The proposed framework outperforms existing models on held-in and held-out datasets, outperforming SFT and GRPO largely.

Copied to clipboard

Jin Jiang, Xunjian Yin, Xiaojun Wan, Wei Peng, Rongjun Li, Jingyuan Yang, Yanquan Zhou

Protein Large Language Models: A Comprehensive Survey (2025.findings-emnlp)

Challenge:	Existing work on document-level ASR error correction ignores contextual information . however, there are limited studies on incorporating contextual information into AEC .
Approach:	They propose a context-aware method that retrieves contextual information from a datastore . they use two English and two Chinese datasets to model document-level AEC .
Outcome:	The proposed model can utilize contextual information to improve document-level AEC . the data store containing contextual information provides even better results .

Copied to clipboard

Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang

Inductive Link Prediction in N-ary Knowledge Graphs (2025.coling-main)

Challenge:	Existing studies focus on specific aspects or applications, but this study provides a comprehensive overview of Protein-specific large language models.
Approach:	This paper proposes a structured taxonomy of state-of-the-art ProteinLLMs . they analyze how they leverage large-scale protein sequence data for improved accuracy .
Outcome:	The proposed model covers their architectures, training datasets, evaluation metrics, and diverse applications.

Copied to clipboard

Jiyao Wei, Saiping Guan, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Multi-granularity Textual Adversarial Attack with Behavior Cloning (2021.emnlp-main)

Challenge:	Existing methods to predict missing elements in NKGs are fixed and therefore cannot be used in real-world situations.
Approach:	They propose a task to predict missing elements in unseen facts involving unseent entities and roles in emerging NKGs by embedding unseense entities and role-encoding neural networks.
Outcome:	The proposed task outperforms representative models across all datasets.

Copied to clipboard

Yangyi Chen, Jin Su, Wei Wei

Robustness in NLP

Challenge:	Existing adversarial attack models are vulnerable to adversarials crafted by human-imperceptible perturbations.
Approach:	They propose a multi-granularity adversarial attack model that generates high-quality adversarials with fewer queries to victim models.
Outcome:	The proposed model generates high-quality adversarial samples with fewer queries to victim models compared to baseline models . the proposed model also reduces query times for black-box models that only output labels without confidence scores .

Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models (2024.findings-acl)

Copied to clipboard

Ran Xu, Hejie Cui, Yue Yu, Xuan Kan, Wenqi Shi, Yuchen Zhuang, May Dongmei Wang, Wei Jin, Joyce Ho, Carl Yang

Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation (2022.acl-long)

Challenge:	Clinical natural language processing (NLP) is a subfield that requires the extraction, analysis, and interpretation of unstructured clinical text.
Approach:	They propose a model which infuses knowledge into clinical text generation with LLMs for clinical NLP tasks.
Outcome:	The proposed model improves performance across 8 clinical NLP tasks and 18 datasets by 7.7%-8.7% on average.

Copied to clipboard

Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Weihua Luo, Rong Jin

Machine Translation

Challenge:	Neural machine translation (NMT) tasks require large amounts of parallel data to augment training.
Approach:	They propose a data augmentation paradigm that augments each training instance with an adjacency semantic region that could cover adequate variants of literal expression under the same meaning.
Outcome:	The proposed paradigm improves on the state-of-the-art in supervised neural machine translation tasks.

Event Causality Extraction via Implicit Cause-Effect Interactions (2023.emnlp-main)

Copied to clipboard

Jintao Liu, Zequn Zhang, Kaiwen Wei, Zhi Guo, Xian Sun, Li Jin, Xiaoyu Li

From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation (2026.acl-long)

Challenge:	Existing studies have not exploited the interactions between the cause and effect event that could provide crucial clues for causality reasoning.
Approach:	They propose an Implicit Cause-Effect interaction framework which captures the implicit intra- and inter-event interactions by incorporating the privileged information for reasoning.
Outcome:	The proposed framework captures the implicit intra- and inter-event interactions by incorporating the privileged information (ground truth event types and arguments) for reasoning.

Copied to clipboard

Kaiwen Wei, Kejun he, Xiaomian Kang, Jie Zhang, null Ymyang, Li Jin, Zhenyang Li, Jiang Zhong, Richard He Bai, Junnan Zhu

Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)

Challenge:	Generative recommendation models inherently bias towards local contexts, failing to capture deeper historical dependencies necessary for understanding complex user intents.
Approach:	They propose a training framework that shifts the objective from simple next-step prediction to deep comprehension of history by entropy-guided masking policy and a curriculum learning scheduler to enhance the framework.
Outcome:	The proposed framework outperforms state-of-the-art generative models on three public datasets and shows that it is more accurate than current models.

Copied to clipboard

Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng

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

Challenge:	Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge.
Approach:	They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy.
Outcome:	The proposed model protects private data while enhancing the model's knowledge.

Copied to clipboard

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

Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora (2022.naacl-main)

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

Xisen Jin, Dejiao Zhang, Henghui Zhu, Wei Xiao, Shang-Wen Li, Xiaokai Wei, Andrew Arnold, Xiang Ren

TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data (2025.findings-emnlp)

Challenge:	Pretrained language models are typically learned over a large, static corpus and fine-tuned for various downstream tasks.
Approach:	They propose to continuously update a pretrained language model to adapt to emerging data and to keep track of the model's performance.
Outcome:	The proposed model can adapt to new corpora while retaining knowledge in earlier domains.

Copied to clipboard

Changjiang Jiang, Fengchang Yu, Haihua Chen, Wei Lu, Jin Zeng

The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification (2021.findings-acl)

Challenge:	Large language models often underperform due to complex queries, noisy data, and limited numerical capabilities.
Approach:	They propose a framework that integrates seamlessly with mainstream LLMs to improve tabular reasoning.
Outcome:	The proposed framework outperforms existing methods in state-of-the-art analysis.

Copied to clipboard

Haochen Liu, Wei Jin, Hamid Karimi, Zitao Liu, Jiliang Tang

Text Classification

Challenge:	Existing studies on text classification have focused on the bias towards the individuals mentioned in the text content.
Approach:	They propose a framework to mitigate implicit bias in text classification models based on demographic attributes of authors . they propose to use this framework to train deep text classifiers to make predictions on the right features .
Outcome:	The proposed framework outperforms existing models significantly in fairness and performance.

A Survey of Link Prediction in N-ary Knowledge Graphs (2025.emnlp-main)

Copied to clipboard

Jiyao Wei, Saiping Guan, Da Li, Zhongni Hou, Miao Su, Yucan Guo, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Knowledge Representation

Challenge:	N-ary Knowledge Graphs (NKGs) capture n-ary facts containing more than two entities.
Approach:	They present the first comprehensive survey of link prediction in NKGs . they provide an overview of the field and analyze their performance and application scenarios .
Outcome:	The proposed methods provide an overview of the field and analyze performance and application scenarios.

AgentMark: Utility-Preserving Behavioral Watermarking for Agents (2026.acl-long)

Copied to clipboard

Kaibo Huang, Jin Tan, Yukun Wei, Wanling Li, Zipei Zhang, Hui Tian, Zhongliang Yang, Linna Zhou

Challenge:	Recent advances in large language models (LLMs) have improved text generation and reasoning.
Approach:	They propose a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility.
Outcome:	The proposed framework embeds multi-bit provenance into planning decisions while preserving utility.

PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning (2025.acl-long)

Copied to clipboard

Zhicong Lu, Changyuan Tian, PeiguangLi PeiguangLi, Li Jin, Sirui Wang, Wei Jia, Ying Shen, Guangluan Xu

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain (2026.acl-long)

Challenge:	Existing studies on Large Language Models (LLMs) have failed to evaluate their performance in event reasoning with a single event relational type or reasoning format.
Approach:	They propose a benchmark to evaluate LLMs' event reasoning capability using a single event relational type or reasoning format.
Outcome:	The proposed model improves on 10K diverse instruction-tuning demonstrations to alleviate event reasoning-oriented data scarcity.

Copied to clipboard

Song Jin, Juntian Zhang, Xun Zhang, Zeying Tian, Fei Jiang, Guojun Yin, Wei Lin, Yong Liu, Rui Yan

Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables (2022.emnlp-main)

Challenge:	Existing vision-language models lack fine-grained classification, single-view imagery, and inaccurate metadata.
Approach:	They propose a hierarchical, multi-view benchmark to evaluate VLMs across three levels of cognitive complexity.
Outcome:	The proposed benchmark evaluates vision-language models across three levels of complexity . it systematically identifies five primary failure modes . the proposed benchmarks are available on https://github.com/meituan/DiningBench.

Copied to clipboard

Erxin Yu, Lan Du, Yuan Jin, Zhepei Wei, Yi Chang