Papers by Lei Xiao

Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2026.acl-long)

Challenge:	Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach:	They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome:	The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.

Copied to clipboard

Zhong-Zhi Li, Xiao Liang, Zihao Tang, Lei Ji, Peijie Wang, Haotian Xu, Xing W, Haizhen Huang, Weiwei Deng, Yeyun Gong, Zhijiang Guo, Xiao Liu, Fei Yin, Cheng-Lin Liu

FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)

Challenge:	Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques.
Approach:	They propose a method that uses Extended Chain-of-Thought (EFT) to reduce the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
Outcome:	The proposed method reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.

Copied to clipboard

Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, null Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong

Automatic Table Union Search with Tabular Representation Learning (2023.findings-acl)

Challenge:	Large language models exhibit significant performance discrepancies between high- and low-resource languages.
Approach:	They present an open-source multilingual LLM with 8 billion parameters and a multilingual instruction dataset.
Outcome:	The proposed model achieves consistent multilingual representations across languages.

Copied to clipboard

Xuming Hu, Shen Wang, Xiao Qin, Chuan Lei, Zhengyuan Shen, Christos Faloutsos, Asterios Katsifodimos, George Karypis, Lijie Wen, Philip S. Yu

DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections (2026.findings-acl)

Challenge:	Existing methods to identify uniability based on column representations are insufficient to reveal latent relational features to describe column relation between pair of columns.
Approach:	They propose a self-supervised table union search framework called AutoTUS to learn column relational representations in a multi-stage manner.
Outcome:	The proposed framework improves on the SOTA baseline and on real-world datasets.

Copied to clipboard

Haebin Shin, Lei Ji, Xiao Liu, Zhiwei Yu, Hyunwoo Yoo, Qi Chen, Yeyun Gong

Challenge:	Several studies rely on additional models to optimize mixtures.
Approach:	They propose a method that dynamically optimizes instruction-tuning dataset mixtures by prior-scaled Boltzmann Exploration and a multi-armed bandit setup.
Outcome:	The proposed method improves the TÜLU-2-mixture and TÜLO-3-mixtures across 10 benchmarks while introducing minimal computational overhead over naive sampling.

Stimulate the Critical Thinking of LLMs via Debiasing Discussion (2025.emnlp-main)

Copied to clipboard

Ruiyu Xiao, Lei Wu, Yuanxing Liu, Weinan Zhang, Ting Liu

Robustness in NLP

Challenge:	Existing studies show that large language models (LLMs) are often prone to stance homogeneity and human preference biases when faced with conflicting perspectives.
Approach:	They propose a novel two-stage training framework to address stance homogeneity bias and human preference bias by generating multi-model discussion datasets and optimizing reinforcement learning from human feedback to align with discussion correctness.
Outcome:	The proposed framework reduces stance homogeneity bias and human preference bias and improves generalization capabilities on non-discussion scenarios and out-of-domain datasets.

Learning Geometry-Aware Representations for New Intent Discovery (2024.acl-long)

Copied to clipboard

Kai Tang, Junbo Zhao, Xiao Ding, Runze Wu, Lei Feng, Gang Chen, Haobo Wang

MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis (2026.acl-long)

Challenge:	Existing methods for intent classification fail to distinguish new intents due to intertwined centers . a novel framework that learns geometry-aware representations to maximally separate all intents is proposed .
Approach:	They propose a new intent discovery framework that learns geometry-aware representations to maximally separate all intents.
Outcome:	The proposed framework achieves a new state-of-the-art performance on three benchmarking datasets.

Copied to clipboard

Xiao Sun, null Ymyang, Xinyi Jiang, Yu Tian, Junnan Zhu, Jiang Zhong, Qin Lei, Jingwang Huang, Haoyang Zeng, Xinyu Zhou, Xin Xiao, Kaiwen Wei

Reasoning

Challenge:	Mental health disorders represent a burgeoning global public health challenge . lack of ecological validity and fine-grained diagnostic supervision limits their utility .
Approach:	They propose a medical-specialized LLM trained to internalize clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning.
Outcome:	The proposed model achieves state-of-the-art with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis.

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

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

DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)

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

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton

Program Transfer for Answering Complex Questions over Knowledge Bases (2022.acl-long)

Challenge:	commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools .
Approach:	They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression .
Outcome:	The proposed approach outperforms human experts in medical examinations on diverse datasets.

Copied to clipboard

Shulin Cao, Jiaxin Shi, Zijun Yao, Xin Lv, Jifan Yu, Lei Hou, Juanzi Li, Zhiyuan Liu, Jinghui Xiao

Knowledge Representation

Challenge:	Program induction for complex questions over knowledge bases relies on a large number of parallel question-program pairs for the given KB, but the gold program annotations are usually lacking, making learning difficult.
Approach:	They propose an approach to leverage program annotations on rich KBs as external supervision signals to aid program induction for low-resourced KB.
Outcome:	The proposed approach outperforms SOTA methods on ComplexWebQuestions and WebQuestionSP.

Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation (2026.acl-long)

Copied to clipboard

Xiangxu Zhang, Lei Li, Yanyun Zhou, Xiao Zhou, Yingying Zhang, Xian Wu

Challenge:	Current evaluations of large language models (LLMs) are limited in capturing key challenges of clinical diagnostic scenarios.
Approach:	They propose a dynamic benchmark for medical diagnostics that provides a stress test of diagnostic robustness.
Outcome:	The proposed model provides a stress test of diagnostic robustness and veracity, helpfulness and consistency.

PodAgent: A Comprehensive Framework for Podcast Generation (2025.findings-acl)

Copied to clipboard

Yujia Xiao, Lei He, Haohan Guo, Feng-Long Xie, Tan Lee

Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026.acl-long)

Challenge:	Existing automatic audio generation methods struggle to generate podcast-like audio programs effectively.
Approach:	They propose a framework for creating podcast-like audio programs that generates informative topic-discussion content by designing a multi-agent collaboration system, builds a voice pool and uses LLM-enhanced speech synthesis to generate expressive conversational speech.
Outcome:	The proposed framework surpasses direct GPT-4 generation in topic-discussion dialogue content, and produces more expressive conversational speech.

Copied to clipboard

Kailai Yang, Xiao Liu, Lei Ji, Hao Li, Xiao Liang, Zhiwei Liu, Yeyun Gong, Peng Cheng, Mao Yang

SCOP: Evaluating the Comprehension Process of Large Language Models from a Cognitive View (2025.acl-long)

Challenge:	Existing methods for reweighting data mixtures rely on manual designation with certain heuristics based on intuition or empirical results.
Approach:	They propose a model-based framework that learns to re-weight domains by reinforcement learning on large quantities of data mixing trajectories with corresponding feedback from an evaluation environment.
Outcome:	The proposed framework outperforms baselines in achieving balanced performance across source and target fields and domain spaces without retraining.

Copied to clipboard

Yongjie Xiao, Hongru Liang, Peixin Qin, Yao Zhang, Wenqiang Lei

E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning (2022.findings-acl)

Challenge:	despite the potential of large language models, it is difficult to fully count on them in real-world scenarios.
Approach:	They propose to examine how LLMs perform during the comprehension process from a cognitive perspective.
Outcome:	The proposed model analyzes how LLMs perform during the comprehension process from a cognitive perspective.

Copied to clipboard

Jiangjie Chen, Rui Xu, Ziquan Fu, Wei Shi, Zhongqiao Li, Xinbo Zhang, Changzhi Sun, Lei Li, Yanghua Xiao, Hao Zhou

Revealing the Barriers of Language Agents in Planning (2025.naacl-long)

Challenge:	Existing benchmarks to test word analogy do not reveal the underneath process of analogical reasoning of neural models.
Approach:	They propose an explanation benchmark for analogical reasoning using a Civil Service exam . they use a free-text explanation scheme to explain whether an analogy should be drawn .
Outcome:	The proposed benchmark is very challenging for state-of-the-art models, it is found.

Copied to clipboard

Jian Xie, Kexun Zhang, Jiangjie Chen, Siyu Yuan, Kai Zhang, Yikai Zhang, Lei Li, Yanghua Xiao

Reasoning

Challenge:	Existing studies show language agents lack human-level planning abilities . limitations and mechanisms to address them remain insufficiently understood .
Approach:	They apply a feature attribution study to identify key factors hindering agent planning . they identify the limited role of constraints and diminishing influence of questions .
Outcome:	The proposed model achieves 15.6% on a real-world planning benchmark.

AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels (2025.findings-emnlp)

Copied to clipboard

Lei Li, Xiangxu Zhang, Xiao Zhou, Zheng Liu

Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry: Fine-grained Method and Comprehensive Evaluation (2026.findings-acl)

Challenge:	Effective zero-shot dense retrieval in the medical domain remains difficult due to the scarcity of relevance-labeled data.
Approach:	They propose a framework that leverages large language models to generate hypothetical documents . they also propose 'CMIRB' to provide a rigorous evaluation suite .
Outcome:	The proposed framework outperforms HyDE in retrieval accuracy and generalization . it leverages large language models to generate hypothetical documents conditioned on a query .

Copied to clipboard

Shuo Wang, Qing Zhu, Yang Xiao, Minglong Lei

AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Challenge:	Existing studies on classical Chinese poetry are limited by modality constraints, dataset size, or the level of refinement.
Approach:	They propose to construct a large-scale and fine-grained multimodal knowledge graph of classical Chinese poetry using an informative ontology graph and a text-image alignment method.
Outcome:	The proposed method collects knowledge about classical Chinese poetry from ontology graphs and performs four tasks that demonstrate its comprehensiveness and high quality.

Copied to clipboard

Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang

Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Challenge:	Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach:	They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome:	The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin

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

Challenge:	Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach:	They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome:	The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.

Copied to clipboard

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

Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria (2025.acl-long)

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

Copied to clipboard

Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, Deyi Xiong

Challenge:	Existing evaluation methods are inadequate to evaluate large language models (LLMs).
Approach:	They propose a fine-grained generative LLM evaluator with instance-level customazable evaluation criteria that can be used to evaluate large language models.
Outcome:	The proposed model outperforms existing LLM evaluators and instruction-tuned LLMs on multiple benchmarks and sets new SOTA results.

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)

Copied to clipboard

Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)

Challenge:	Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages.
Approach:	They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English.
Outcome:	The proposed model outperforms open-source and Tibetan-focused models on diverse tasks.

Copied to clipboard

Yuchun Fan, Yongyu Mu, YiLin Wang, Lei Huang, Junhao Ruan, Bei Li, Tong Xiao, Shujian Huang, Xiaocheng Feng, Jingbo Zhu

MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs (2020.acl-main)

Challenge:	Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios.
Approach:	They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage.
Outcome:	The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method.

Copied to clipboard

Jifan Yu, Gan Luo, Tong Xiao, Qingyang Zhong, Yuquan Wang, Wenzheng Feng, Junyi Luo, Chenyu Wang, Lei Hou, Juanzi Li, Zhiyuan Liu, Jie Tang

PolyJoin: Semantic Multi-key Joinable Table Search in Data Lakes (2025.findings-naacl)

Challenge:	Massive open online courses (MOOCs) are a popular educational platform for advanced research.
Approach:	They propose to use MOOCCube to build a large-scale data repository of over 700 MOOC courses, 100k concepts, 8 million student behaviors with an external resource.
Outcome:	The proposed datasets show that they can facilitate research in MOOCs.

Copied to clipboard

Xuming Hu, Chuan Lei, Xiao Qin, Asterios Katsifodimos, Christos Faloutsos, Huzefa Rangwala

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

Challenge:	Existing joinable table search methods focus on single key (unary) joins, where a single column is the join key, but are ineffective when dealing with join keys composed of multiple columns (n-ary joins) Existing methods are inefficient when dealing . with joins composed of n-aries, which are prevalent on web table corpora.
Approach:	They propose a joinable table search method that finds multi-key joinable tables on the web, given a query table.
Outcome:	The proposed method outperforms the state-of-the-art methods on two real-world web table benchmarks.

Copied to clipboard

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

Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information (2020.emnlp-main)

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

Copied to clipboard

Zehui Lin, Xiao Pan, Mingxuan Wang, Xipeng Qiu, Jiangtao Feng, Hao Zhou, Lei Li

Multilinguality

Challenge:	Existing pre-training methods are not effective for machine translation tasks.
Approach:	They propose a method to pre-train a universal multilingual neural machine translation model . they use random aligned substitution technique to bring words and phrases with similar meanings closer in the representation space.
Outcome:	The proposed approach improves translation quality on low, medium, rich resource languages.

PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents (2026.eacl-industry)

Copied to clipboard

Minjia Wang, Yunfeng Wang, Xiao Ma, Dexin Lv, Qifan Guo, Lynn Zheng, Benliang Wang, Lei Wang, Jiannan Li, Yongwei Xing, Junzhe Xu, Zheng Sun

Challenge:	Publicly available corpora cover only slivers of human activity, such as email threads, chat logs, purchase histories, sensor traces, and provide large-scale supervision for data-hungry machine-learning pipelines.
Approach:	They propose a method for synthesizing realistic digital footprints using large language model agents from a structured user profile.
Outcome:	The proposed method generates diverse sequences of user events, producing corresponding digital artifacts such as emails, messages, calendar entries, reminders, etc.

Prove Your Point!: Bringing Proof-Enhancement Principles to Argumentative Essay Generation (2024.emnlp-main)

Copied to clipboard

Ruiyu Xiao, Lei Wu, Yuhang Gou, Weinan Zhang, Ting Liu

Challenge:	Existing arguments generation methods often overlook connections between opinions . Existing methods struggle with providing compelling proof .
Approach:	They propose a two-stage framework for argumentative essay generation with a focus on logical enhancement.
Outcome:	The proposed framework generates argumentative essays with better logical validity and persuasiveness than baseline models.

PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents (2026.acl-long)

Copied to clipboard

Lei Wei, Xiao Peng, null Tt, Guannan Zhang, Chenhao Jiang, Hongyu Li, Lanbo Lin, Yuanwu Xu, Jiayao Liu, Kesu Wang, Bin Wang

Representation-Guided Parameter-Efficient LLM Unlearning (2026.findings-acl)

Challenge:	Large Language Model (LLM) agents struggle with ultra-long-horizon tasks requiring hundreds or thousands of interaction steps.
Approach:	They propose a framework that reconceptualizes context management as a Next Step Prediction problem.
Outcome:	The proposed framework improves task success rates and robust cross-lingual performance.

Copied to clipboard

Zeguan Xiao, Lang Mo, Yun Chen, Lei Yang, Jiehui Zhao, Lili Yang, Guanhua Chen

Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models (2025.findings-emnlp)

Challenge:	Existing methods to unlearning large language models often memorize sensitive or harmful information, but they struggle with the forget-retain trade-off due to the polysemantic nature of LLMs parameters.
Approach:	They propose a representation-guided low-rank unlearning approach that leverages the geometric properties of representation spaces to achieve robust and precise unlearning.
Outcome:	The proposed approach outperforms state-of-the-art models on TOFU and WMDP benchmarks while maintaining higher model utility.

Copied to clipboard

Yuchun Fan, Yilin Wang, Yongyu Mu, Lei Huang, Bei Li, Xiaocheng Feng, Tong Xiao, JingBo Zhu

Dynamically Fused Graph Network for Multi-hop Reasoning (P19-1)

Challenge:	Large vision-language models exhibit an imbalance in multilingual capabilities .
Approach:	They propose a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise Language Specific layers fine-tuning.
Outcome:	The proposed training recipe achieves efficient multilingual enhancement for LVLMs by fine-tuning language specific layers.

Copied to clipboard

Lin Qiu, Yunxuan Xiao, Yanru Qu, Hao Zhou, Lei Li, Weinan Zhang, Yong Yu

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering (2025.findings-emnlp)

Challenge:	Text-based question answering (TBQA) has been studied extensively in recent years.
Approach:	They propose a Dynamically Fused Graph Network to answer questions requiring multiple scattered evidence and reasoning over them.
Outcome:	The proposed method achieves competitive results on a public TBQA dataset and produces interpretable reasoning chains.

Copied to clipboard

Yushi Sun, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen

Structured Data in NLP

Challenge:	Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing to retrieve knowledge strictly necessary for answer generation.
Approach:	They propose a retrieval-filtering-summarization pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information.
Outcome:	The proposed pipeline surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%.

UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)

Copied to clipboard

Yuzhe Yang, Yifei Zhang, Yan Hu, Yilin Guo, Ruoli Gan, Yueru He, Mingcong Lei, Xiao Zhang, Haining Wang, Qianqian Xie, Jimin Huang, Honghai Yu, Benyou Wang

LEVEN: A Large-Scale Chinese Legal Event Detection Dataset (2022.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have expanded their potential applications in finance.
Approach:	They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions.
Outcome:	The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios.

Copied to clipboard

Feng Yao, Chaojun Xiao, Xiaozhi Wang, Zhiyuan Liu, Lei Hou, Cunchao Tu, Juanzi Li, Yun Liu, Weixing Shen, Maosong Sun

UCTG: A Unified Controllable Text Generation Framework for Query Auto-Completion (2025.coling-industry)

Challenge:	Existing legal event detection datasets only cover incomprehensive event types and have limited annotated data.
Approach:	They present a large-scale Chinese legal event detection dataset . they use legal events as side information to promote downstream applications .
Outcome:	The proposed method improves 2.2 points precision in low-resource judgment prediction and 1.5 points precision for unsupervised case retrieval.

Copied to clipboard

Zhipeng Li, Shuang Zheng, Jiaping Xiao, Xianneng Li, Lei Wang

Low-Resource NLP

Challenge:	Existing approaches to control text generation (CTG) are essentially challenging to adapt to various control objectives and constraints, which results in mixed success.
Approach:	They propose a unified controllable text generation framework which integrates a control module, a prompt module, and a generation module.
Outcome:	The proposed framework significantly improves query accuracy and coherence in tasks with different objectives and constraints.

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

Copied to clipboard

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

Multilinguality

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

GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks (2026.acl-long)

Copied to clipboard

Jianwen Luo, Yiming Huang, Jinxiang Meng, Fangyu Lei, Shizhu He, Xiao Liu, Shanshan Jiang, Bin Dong, Jun Zhao, Kang Liu

LayerNorm Induces Recency Bias in Transformer Decoders (2026.findings-acl)

Challenge:	Existing toolsets that use large language models are limited to single-task settings.
Approach:	They propose a framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios.
Outcome:	The proposed framework achieves up to 4.3 faster milestone completion in Minecraft compared to the previous state-of-the-art method and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks.

Copied to clipboard

Junu Kim, Xiao Liu, Zhenghao Lin, Lei Ji, Yeyun Gong, Edward Choi

Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning (2026.findings-acl)

Challenge:	Existing studies show that stacking causal self-attention layers alone induces a positional bias in attention scores toward earlier tokens, but this differs from the bias toward later tokens observed in Transformer decoders, known as recency bias.
Approach:	They propose to stack causal self-attention layers and layer norm to induce recency bias in Transformer decoders by analyzing the interaction between causal self and other architectural components.
Outcome:	The proposed method provides new theoretical insights into how positional information interacts with architectural components and suggests improvements in positional encoding strategies.

Copied to clipboard

Zhiyin Yu, Bo Zhang, Qibin Hou, Zhonghai Wu, Xiao Luo, Lei Bai

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)

Challenge:	Experimental results show that EasyRL consistently outperforms state-of-the-art baselines due to the substantial annotation cost and issues such as model collapse or reward hacking.
Approach:	They propose a supervised RL approach with a divide-and-conquer strategy that simulates the human cognitive acquisition curve using easy labeled data.
Outcome:	The proposed approach outperforms state-of-the-art models on mathematical and scientific benchmarks using only 10% of easy labeled data.

Copied to clipboard

Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie

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

Challenge:	Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach:	They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome:	The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.

Copied to clipboard

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

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

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

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

FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph (2023.acl-industry)

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

Xiaodan Wang, Chengyu Wang, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, Ming Gao

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (2024.acl-long)

Challenge:	Recent advances in visual-language pre-trained (VLP) models have greatly improved cross-modal retrieval performance . however, the fine-grained interactions between objects from different modalities are far from well-established . e-commerce domain lacks sufficient training data and fine-granular cross-modulal knowledge .
Approach:	They propose a visual-language pre-trained (VLP) image-text retrieval model that integrates cross-modal knowledge into the model to improve performance.
Outcome:	The proposed model improves performance on e-commerce image-text retrieval task by a large margin.

Copied to clipboard

Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li

Multilinguality

Challenge:	Large language models (LLMs) can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases.
Approach:	They propose a bilingual, multi-task benchmark for long context understanding that extends context windows and more sophisticated memory mechanisms to improve models' long context capabilities.
Outcome:	The proposed model outperforms open-source models but struggles on longer contexts.

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)

Copied to clipboard

Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

SEMIROUTER: Sparse-Data Enhanced Routing for Adaptive Multi-LLM System (2026.eacl-long)

Challenge:	Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references.
Approach:	They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings.
Outcome:	The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading.

Copied to clipboard

Zijie Wang, Xinyu Yan, Che Wang, Zeng Zihao, Lei Xiao, Wei Yang Bryan Lim

Green & Sustainable NLP

Challenge:	Existing routing methods suffer from poor scalability and dependence on datasets for training . energy footprint is also considered in the decision to implement our new LLM routing framework .
Approach:	They propose a new LLM routing framework that dynamically allocates queries to the most appropriate LLM.
Outcome:	The proposed method improves data efficiency, adaptability, and routing accuracy compared to existing methods.

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

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 .

Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography (2026.acl-industry)

Copied to clipboard

Sudharshan Balaji, Zhiyu Liu, Zhengyuan Jiang, Shuo Lei, Yimin Chen, Yang Xiao, Shone O. Almeida, Mathew Joseph Karivelil, Christopher Malanga, Ning Wang

Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization (2026.acl-long)

Challenge:	CCTA reports provide an assessment of coronary disease severity to guide patient management.
Approach:	They propose a pipeline that decouples structuring from classification by an LLM-based parser . CCTA-RADS is the largest publicly available dataset of CCDA reports .
Outcome:	The proposed approach improves the F1-score by 6%-13% compared with direct methods.

Copied to clipboard

Yu Fu, Chen Luo, Josef Valvoda, Xin Zhang, Xuejing Lei, Xiao Pan, Hui Liu, Yue Dong

Towards More Accurate Uncertainty Estimation In Text Classification (2020.emnlp-main)

Challenge:	Recent studies show that KV cache compression can increase hallucination scores in LLMs . modern LLM models support extremely long sequences, but their impact on model hallucinosity remains underexplored.
Approach:	They propose a decoding-phase strategy that selectively removes generated KV pairs from retrieval heads responsible for retrieving critical information from source context.
Outcome:	The proposed method reduces hallucination across multiple models and datasets while preserving computational efficiency.

Copied to clipboard

Jianfeng He, Xuchao Zhang, Shuo Lei, Zhiqian Chen, Fanglan Chen, Abdulaziz Alhamadani, Bei Xiao, ChangTien Lu

Topic-DPR: Topic-based Prompts for Dense Passage Retrieval (2023.findings-emnlp)

Challenge:	Existing models of uncertainty score depend on winning score, which is the maximum probability in a semantic vector.
Approach:	They propose to generate accurate uncertainty score by improving the confidence of winning scores by reducing the effect of overconfidence of winning score and considering the impact of different categories simultaneously.
Outcome:	The proposed model reduces the effect of overconfidence of winning score and considers impact of different categories of uncertainty simultaneously.

Copied to clipboard

Qingfa Xiao, Shuangyin Li, Lei Chen

Low-Resource NLP

Challenge:	Prior research focused on optimizing a single prompt as a continuous prompt, but this approach leads to a semantic space collapse, preventing differentiation between relevant and irrelevant passages.
Approach:	They propose a dense passage retrieval model that uses topic-based prompts and propose 'positive and negative sampling strategies' to boost dense retrieval efficiency.
Outcome:	The proposed model surpasses state-of-the-art retrieval techniques and improves space uniformity.

Competition-Level Problems are Effective LLM Evaluators (2024.findings-acl)

Copied to clipboard

Yiming Huang, Zhenghao Lin, Xiao Liu, Yeyun Gong, Shuai Lu, Fangyu Lei, Yaobo Liang, Yelong Shen, Chen Lin, Nan Duan, Weizhu Chen

Online Iterative Self-Alignment for Radiology Report Generation (2025.acl-long)

Challenge:	Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet there is ongoing debate about their capabilities and the potential data contamination problem.
Approach:	They propose to evaluate the reasoning capabilities of large language models in solving recent competition-level programming problems in Codeforces.
Outcome:	The proposed model has experienced a cliff-like decline in problems after September 2021, which shows the potential data contamination and the challenges for any existing LLM to solve unseen complex reasoning problems.

Copied to clipboard

Ting Xiao, Lei Shi, Yang Zhang, HaoFeng Yang, Zhe Wang, Chenjia Bai

Text Generation

Challenge:	Existing methods for RRG rely on supervised fine-tuning based on data pairs of radiological images and corresponding radiologist-annotated reports.
Approach:	They propose a method that performs supervised fine-tuning on data pairs of radiological images and corresponding radiologist-annotated reports.
Outcome:	The proposed method surpasses existing methods and achieves state-of-the-art performance across multiple evaluation metrics.

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation (2021.acl-long)

Copied to clipboard

Xiao Pan, Mingxuan Wang, Liwei Wu, Lei Li

DiscoverGPT: Multi-task Fine-tuning Large Language Model for Related Table Discovery (2025.findings-naacl)

Challenge:	Existing multilingual machine translation approaches focus on English-centric directions, while non-English directions lag behind.
Approach:	They propose a multilingual machine translation system with an emphasis on non-English directions.
Outcome:	The proposed model outperforms existing models on English-centric and non-English directions on multilingual translation benchmarks.

Copied to clipboard

Xuming Hu, Xiao Qin, Chuan Lei, Asterios Katsifodimos, Zhengyuan Shen, Balasubramaniam Srinivasan, Huzefa Rangwala

Combating Security and Privacy Issues in the Era of Large Language Models (2024.naacl-tutorials)

Challenge:	Existing methods to learn and evaluate the table semantic relatedness of tabular data are based on pretrain-and-finetune paradigms.
Approach:	They propose a multi-task fine-tuning framework that holistically discovers and leverages the intricate relationships among the supervisions to optimize the performance on the data discovery task.
Outcome:	The proposed framework outperforms the best performing baseline by up to 7% in F1 score.

Copied to clipboard

Muhao Chen, Chaowei Xiao, Huan Sun, Lei Li, Leon Derczynski, Anima Anandkumar, Fei Wang