Papers by Yan Gao

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models (2024.acl-long)

Challenge:	Large language models have demonstrated impressive performance across a wide range of tasks, but this achievement comes with the trade-off of significant computational demands.
Approach:	They propose a scaling law that decomposes the overall validation loss and assigns different importance weights to tokens to assess a specific meta-capability.
Outcome:	The proposed model can predict the loss trending of models across different levels of computation without a gap between validation loss and model's downstream capabilities.

Copied to clipboard

Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li

PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions (2025.findings-emnlp)

Challenge:	Despite the advances in large language models, they still face difficulties with multi-step reasoning tasks.
Approach:	They propose a method that randomly masks certain tokens within the chain of thought to improve model accuracy by 5% over standard supervised fine-tuning.
Outcome:	The proposed method improves accuracy and accuracy by 5% over standard fine-tuning with a few codes modified.

Copied to clipboard

Song Dai, Yibo Yan, Jiamin Su, Zihao Dongfang, Yubo Gao, Yonghua Hei, Jungang Li, Junyan Zhang, Sicheng Tao, Zhuoran Gao, Xuming Hu

Do Large Language Models excel in Complex Logical Reasoning with Formal Language? (2025.emnlp-main)

Challenge:	Current physics benchmarks focus on text-only inputs or only on problem-solving . current physics reasoning benchmarks neglect critical intermediate steps of variable identification and process formulation.
Approach:	a new benchmark evaluates multimodal large language models in physics reasoning . the benchmark measures variables, process formulations, and solution derivation .
Outcome:	PhysicsArena is the first multimodal physics reasoning benchmark . it evaluates MLLMs across three critical dimensions: variable identification, process formulation, and solution derivation.

Copied to clipboard

Jin Jiang, Jianing Wang, Yuchen Yan, Yang Liu, Jianhua Zhu, Mengdi Zhang, Liangcai Gao

A Generative Pre-Trained Language Model for Channel Prediction in Wireless Communications Systems (2025.emnlp-main)

Challenge:	Existing studies on LLMs have focused on formal language, but evaluations of their performance are limited.
Approach:	They propose to use a formal language to evaluate LLMs across logical reasoning problems using formal languages.
Outcome:	The proposed model outperforms Instruct models in three dimensions, taxonomy of tasks, and format of trajectories, and achieves the best generalization performance across other languages.

Copied to clipboard

Bo Lin, Huanming Zhang, Yuhua Jiang, Yucong Wang, Tengyu Zhang, Shaoqiang Yan, Hongyao Li, Yihong Liu, Feifei Gao

Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation (2022.acl-long)

Challenge:	Existing model-based channel prediction methods suffer from limited accuracy due to imperfect temporal modeling, while existing AI-based methods suffers from limited generalization due to inadequate training strategies.
Approach:	They propose a generative pre-trained language model for channel prediction based on channel correlation and train it based upon transformer decoder architecture.
Outcome:	The proposed model can learn various channel characteristics and perform impressive tasks across multiple dimensions.

Copied to clipboard

Xinyu Pi, Bing Wang, Yan Gao, Jiaqi Guo, Zhoujun Li, Jian-Guang Lou

LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Challenge:	Existing Text-to-SQL parsers are vulnerable to perturbations in NL questions . we propose the Adversarial Table Perturbation (ATP) as a new attacking paradigm .
Approach:	They propose to use the Adversarial Table Perturbation to measure robustness of Text-to-SQL parsers against adversarial perturbations.
Outcome:	The proposed approach outperforms baseline methods in robustness evaluations on ADVETA and can be used in future projects.

Copied to clipboard

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models (2021.emnlp-main)

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

Copied to clipboard

Bill Yuchen Lin, Wenyang Gao, Jun Yan, Ryan Moreno, Xiang Ren

Robustness in NLP

Challenge:	Recent named entity recognition models have great performance on many conventional benchmarks, but it is not reliable in realistic applications.
Approach:	They propose a method to create natural adversarial examples using Wikidata and pre-trained language models.
Outcome:	The proposed method produces natural adversarial examples with a shifted distribution from training data.

DRBO: Mitigating Short Board Effect via Dynamic Reward Balancing in Multi-reward LLM Optimization (2025.findings-emnlp)

Copied to clipboard

Nuo Chen, Yufei Gao, Yongnan Jin, Yan Hu, Anningzhe Gao, Lingyong Yan, Benyou Wang

Challenge:	a new framework to optimize large language models (LLMs) for evaluation metrics is needed to balance weaker metrics.
Approach:	They propose a Dynamic Reward Balancing Optimization framework to mitigate the "short-board effect" they apply it to single-task and multi-type task scenarios .
Outcome:	The proposed framework improves performance and balances performance across multiple metrics.

Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation (2021.acl-long)

Copied to clipboard

Xiuying Chen, Hind Alamro, Mingzhe Li, Shen Gao, Xiangliang Zhang, Dongyan Zhao, Rui Yan

Structured Data in NLP

Challenge:	Existing related work generation models are inflexible and extract sentences from multiple papers to form a related work discussion.
Approach:	They propose a Relation-aware Related work generator which generates an abstractive related work from the given multiple scientific papers in the same research area.
Outcome:	The proposed model improves over existing models and can be used to familiarize researchers with the state of the art in the field.

SocialBench: Sociality Evaluation of Role-Playing Conversational Agents (2024.findings-acl)

Copied to clipboard

Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Gao Xing, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang

Towards the Law of Capacity Gap in Distilling Language Models (2025.acl-long)

Challenge:	Existing studies on role-playing agents have focused on enhancing their conversational capability, role-specific knowledge and style, but there has been a gap in assessing their social intelligence.
Approach:	They propose a benchmark to evaluate the sociality of role-playing agents using LLMs.
Outcome:	The proposed benchmark is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances.

Copied to clipboard

Chen Zhang, Qiuchi Li, Dawei Song, Zheyu Ye, Yan Gao, Yao Hu

Pre-training Entity Relation Encoder with Intra-span and Inter-span Information (2020.emnlp-main)

Challenge:	Language model (LM) distillation aims at distilling knowledge in a large teacher LM to a small student one.
Approach:	They propose to use the law of capacity gap to distill knowledge from a large teacher to a small student model.
Outcome:	The proposed model outperforms other language models on a larger scale by using the law of capacity gap inducted from a preliminary study on small-scale (3B) LMs.

Copied to clipboard

Yijun Wang, Changzhi Sun, Yuanbin Wu, Junchi Yan, Peng Gao, Guotong Xie

SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models (2026.acl-long)

Challenge:	Existing pre-trained models do not handle text spans and relation among text span pairs.
Approach:	They propose to integrate span-related information into pre-trained encoder for entity relation extraction task.
Outcome:	The proposed pre-training method outperforms distantly supervised pre-trained models on two entity relation extraction benchmark datasets.

Copied to clipboard

Peihua Mai, Xuanrong Gao, Youlong Ding, Xianglong Du, Wei Liu, Yan Pang

E5: Zero-shot Hierarchical Table Analysis using Augmented LLMs via Explain, Extract, Execute, Exhibit and Extrapolate (2024.naacl-long)

Challenge:	Existing privacy-preserving inference methods sacrifice utility or efficiency, authors say . current approaches suffer a trilemma between privacy, utility, and efficiency, they say .
Approach:	They propose a model-agnostic framework for privacy-preserving LLM inference that reformulates privacy protection at the batch level rather than the individual-prompt level.
Outcome:	The proposed model-agnostic framework achieves 20% higher utility than previous models . it reduces query cost by up to 5 compared to non-batched inference .

Copied to clipboard

Zhehao Zhang, Yan Gao, Jian-Guang Lou

Iterative Document Representation Learning Towards Summarization with Polishing (D18-1)

Challenge:	Hierarchical tables with multi-level headers are confusing for models due to their complex structure, implicit semantics, and calculation relationships.
Approach:	They propose a code-augmented framework for zero-shot hierarchical table question answering that combines self-explaining the table's hierarchic structures with external code execution to prevent hallucinations.
Outcome:	The proposed framework outperforms state-of-the-art fine-tuning methods with a 44.38 Exact Match improvement.

Copied to clipboard

Xiuying Chen, Shen Gao, Chongyang Tao, Yan Song, Dongyan Zhao, Rui Yan

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)

Challenge:	Existing summarization methods read through document only once to generate a document representation, resulting in a sub-optimal representation.
Approach:	They propose an iterative model for supervised extractive text summarization which polishes the document representation on many passes through the document.
Outcome:	The proposed model outperforms state-of-the-art extractive systems on CNN/DailyMail and DUC2002 datasets.

Copied to clipboard

Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen

Challenge:	Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios.
Approach:	They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance.
Outcome:	The proposed framework improves model capabilities across all domains and scales.

DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations (2023.acl-long)

Copied to clipboard

Ang Lv, Jinpeng Li, Yuhan Chen, Gao Xing, Ji Zhang, Rui Yan

R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)

Challenge:	a context leads to various responses, and a response answers multiple contexts.
Approach:	They propose a method that augments open-domain dialogue generation from a many-to-many perspective.
Outcome:	The proposed method can augment open-domain dialogue generation tasks with automatic and human evaluation.

Copied to clipboard

Xiaowei Yuan, Lei Jin, Haoxin Zhang, Ziyang Huang, Yan Gao, null Yiwu, Yao Hu, Jun Zhao, Kang Liu

LEGO-ABSA: A Prompt-based Task Assemblable Unified Generative Framework for Multi-task Aspect-based Sentiment Analysis (2022.coling-1)

Challenge:	Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms .
Approach:	They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding.
Outcome:	The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing.

Copied to clipboard

Tianhao Gao, Jun Fang, Hanyu Liu, Zhiyuan Liu, Chao Liu, Pengzhang Liu, Yongjun Bao, Weipeng Yan

Sentiment Analysis

Challenge:	Existing generative methods focus on a single task at a time.
Approach:	They propose a unified generative multi-task framework that can solve multiple ABSA tasks . they propose to control the type of task prompts consisting of multiple element prompts .
Outcome:	The proposed framework achieves state-of-the-art results in almost all ABSA tasks and competitive results in task transfer scenarios.

Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT - A Text-to-SQL Parsing Comparison (2023.findings-emnlp)

Copied to clipboard

Shuo Sun, Yuchen Zhang, Jiahuan Yan, Yuze Gao, Donovan Ong, Bin Chen, Jian Su

CRT-QA: A Dataset of Complex Reasoning Question Answering over Tabular Data (2023.emnlp-main)

Challenge:	a number of open-source large language models claim to be performing better than commercial ones . however, these models fall short of the performance achieved by closed-source models like GPT-3.5 .
Approach:	They evaluate six popular large language models against each other to evaluate their performance . authors say open-source models are not as effective as those built by commercial models .
Outcome:	a new set of models claim to match or surpass the language understanding abilities of commercial models . the results show that the models performed far below the performance of closed-source models compared to open-source ones .

Copied to clipboard

Zhehao Zhang, Xitao Li, Yan Gao, Jian-Guang Lou

Selection and Generation: Learning towards Multi-Product Advertisement Post Generation (2020.emnlp-main)

Challenge:	Large language models (LLMs) show powerful reasoning abilities on text-based tasks, but their reasoning capability on structured data such as tables has not been systematically explored.
Approach:	They first establish a comprehensive taxonomy of reasoning and operation types for tabular data analysis and then construct a complex reasoning QA dataset over tabular dataset.
Outcome:	The proposed method is able to solve table reasoning tasks without handcrafted demonstrations.

Copied to clipboard

Zhangming Chan, Yuchi Zhang, Xiuying Chen, Shen Gao, Zhiqiang Zhang, Dongyan Zhao, Rui Yan

Text Generation

Challenge:	E-commerce websites have billions of products, so it is impossible to write all copywriting manually.
Approach:	They propose a model to generate an AD post using a select network and a MGenNet network to generate a post including selected products.
Outcome:	The proposed model achieves impressive performance on a large-scale real-world AD post dataset.

2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition (2023.findings-emnlp)

Copied to clipboard

Jiasheng Zhang, Xikai Liu, Xinyi Lai, Yan Gao, Shusen Wang, Yao Hu, Yiqing Lin

Low-Resource NLP

Challenge:	Named Entity Recognition (NER) tasks are a fundamental task of natural language processing (NLP).
Approach:	They propose a text-to-text framework for Few-Shot Named Entity Recognition (NER) that employs instruction finetuning and auxiliary tasks to enhance the model's understanding of entity types in the overall semantic context of a sentence.
Outcome:	The proposed framework outperforms existing Few-Shot NER methods and remains competitive with state-of-the-art NER algorithms.

Scientific Paper Extractive Summarization Enhanced by Citation Graphs (2022.emnlp-main)

Copied to clipboard

Xiuying Chen, Mingzhe Li, Shen Gao, Rui Yan, Xin Gao, Xiangliang Zhang

Learning to Use Tools via Cooperative and Interactive Agents (2024.findings-emnlp)

Challenge:	citation graphs can be used to extract scientific papers under different conditions.
Approach:	They propose a multi-granularity unsupervised summarization model that fine tunes a pre-trained encoder model on the citation graph by link prediction tasks.
Outcome:	The proposed model outperforms baseline models on a public benchmark dataset.

Copied to clipboard

Zhengliang Shi, Shen Gao, Xiuyi Chen, Yue Feng, Lingyong Yan, Haibo Shi, Dawei Yin, Pengjie Ren, Suzan Verberne, Zhaochun Ren

“What Do You Mean by That?” A Parser-Independent Interactive Approach for Enhancing Text-to-SQL (2020.emnlp-main)

Challenge:	Existing methods for large language models (LLMs) use one agent to iterate and execute tools, but they suffer from performance degradation when addressing practical tasks.
Approach:	They propose a tool learning framework that coordinates three specialized agents for tool selection, tool execution, and action calibration separately.
Outcome:	The proposed framework outperforms baseline models on three datasets with 14% higher success rate.

Copied to clipboard

Yuntao Li, Bei Chen, Qian Liu, Yan Gao, Jian-Guang Lou, Yan Zhang, Dongmei Zhang

LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages (2025.findings-naacl)

Challenge:	In Natural Language Interfaces to Databases systems, text-to-SQL parsers allow users to query databases by using natural language questions.
Approach:	They propose a parser-independent interactive approach that interacts with users using multi-choice questions and can easily work with arbitrary parsers.
Outcome:	The proposed approach improves performance with limited interaction turns by using simulation and human evaluation on two cross-domain datasets with five state-of-the-art parsers.

Copied to clipboard

Xuhan Huang, Qingning Shen, Yan Hu, Anningzhe Gao, Benyou Wang

Reasoning Like Program Executors (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated strong performance across various natural language processing tasks, but their proficiency in mathematical reasoning remains a key challenge.
Approach:	They propose a process-oriented framework to evaluate LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth.
Outcome:	The proposed framework evaluates LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth.

Copied to clipboard

Xinyu Pi, Qian Liu, Bei Chen, Morteza Ziyadi, Zeqi Lin, Qiang Fu, Yan Gao, Jian-Guang Lou, Weizhu Chen

BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations (2023.emnlp-main)

Challenge:	Existing language models are inadequate in reasoning, according to studies . a new reasoning pre-training paradigm is based on pretraining language models with programs .
Approach:	They propose a reasoning pre-training paradigm that empowers language models to harvest reasoning knowledge possessed by program executors.
Outcome:	The proposed reasoning pre-training paradigm can boost models' reasoning skills . it can be instantiated by different kinds of program executors and run on a single database .

Copied to clipboard

Qizhi Pei, Wei Zhang, Jinhua Zhu, Kehan Wu, Kaiyuan Gao, Lijun Wu, Yingce Xia, Rui Yan

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference (2024.findings-acl)

Challenge:	et al., 2022) argue that the current models for drug discovery lack the ability to integrate molecules, proteins, and natural language.
Approach:	They propose a framework that integrates biological knowledge with chemical knowledge and natural language associations.
Outcome:	The proposed framework shows superior performance across a wide range of tasks.

Copied to clipboard

Dongjie Yang, Xiaodong Han, Yan Gao, Yao Hu, Shilin Zhang, Hai Zhao

Challenge:	Existing methods to reduce memory usage for large language models neglect inter-layer dependency between layers and huge memory consumption in pre-computation.
Approach:	They propose a method that compresses the KV cache by layer-wise retaining crucial context.
Outcome:	The proposed method reduces memory usage by layer-wise retaining crucial context . it can improve 2.2x throughput compared to Accelerate with over 54% memory reduction .

CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback (2025.findings-emnlp)

Copied to clipboard

Yifan Wang, Shen Gao, Jiabao Fang, Rui Yan, Billy Chiu, Shuo Shang

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

Challenge:	Existing Sequential Recommendation Systems (SRS) rely on collaborative filtering signals and fail to capture real-time user preferences.
Approach:	They propose a framework that integrates the long-term preference modeling of SRS with the real-time preference elicitation of CRS.
Outcome:	The proposed framework integrates the long-term preference modeling of SRS with the real-time preference elicitation of CRS.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen

Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks (D19-60)

Challenge:	Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach:	They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome:	The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.

Copied to clipboard

Xiepeng Li, Zhexi Zhang, Wei Zhu, Zheng Li, Yuan Ni, Peng Gao, Junchi Yan, Guotong Xie

BioGen: Generating Biography Summary under Table Guidance on Wikipedia (2021.findings-acl)

Challenge:	Existing approaches to represent knowledge in the low-dimensional space are to leverage large-scale unsupervised text corpus to train fixed or contextual representations.
Approach:	They propose to leverage large-scale unsupervised text corpus to train fixed or contextual language representations and to express knowledge into a knowledge graph (KG) they incorporate distributional representations of a KG onto the representations from pre-trained language models, via simply concatenation or multi-head attention.
Outcome:	The proposed models outperform the other models on the COIN: COmmonsense INference in Natural Language Processing (COIN) Workshop datasets.

Copied to clipboard

Shen Gao, Xiuying Chen, Chang Liu, Dongyan Zhao, Rui Yan

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)

Challenge:	Existing methods for summarizing text have not captured the salient information from an article.
Approach:	They propose a table-guided abstractive biography summarization that utilizes factual tables to capture important information and generate a summary of a biography.
Outcome:	The proposed method is the first large-scale biography summarization dataset with tables.

Copied to clipboard

Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai

CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding (2023.acl-long)

Challenge:	RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach:	They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome:	The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.

Copied to clipboard

Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, W.k. Chan, Chong-Wah Ngo, Mike Zheng Shou, Nan Duan

Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout Grounding (2025.findings-emnlp)

Challenge:	Existing work on video temporal grounding for long videos is limited by existing datasets.
Approach:	They propose a query-guided window selection strategy and a coarse-to-fine mechanism to speed up inference for long videos.
Outcome:	The proposed framework accelerates inference time by 2x on Ego4D-NLQ and 15x on MAD while keeping SOTA results.

Copied to clipboard

Hangdi Xing, Feiyu Gao, Qi Zheng, Zhaoqing Zhu, Zirui Shao, Ming Yan

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning (2025.acl-long)

Challenge:	Existing methods fragment document parsing into pipeline of separated subtasks, resulting in incomplete semantics and error propagation.
Approach:	They propose an end-to-end document parsing framework that leverages vision-language priors of MLLMs.
Outcome:	The proposed method surpasses existing methods significantly in document parsing . it leverages the vision-language priors of MLLMs to decouple parse and layout grounding based on visual information.

Copied to clipboard

Jin Jiang, Yuchen Yan, Yang Liu, Jianing Wang, Shuai Peng, Xunliang Cai, Yixin Cao, Mengdi Zhang, Liangcai Gao

Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)

Challenge:	LogicPro is a data synthesis method that uses LeetCode-style algorithm problems and their corresponding Program solutions to generate complex logic data.
Approach:	They propose a new method which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize complex logic data in text format.
Outcome:	The proposed method outperforms existing models for BBH27, LogicBench, DROP, AR-LSAT, and GSM8K, and a wide range of reasoning datasets.

Copied to clipboard

Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization (2025.naacl-long)

Challenge:	Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning.
Approach:	They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning.
Outcome:	The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness.

Copied to clipboard

Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin, Ming Gao

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Challenge:	Existing approaches to optimize RAG generators fail to align with RAG requirements thoroughly.
Approach:	They propose a method for optimizing the RAG generator from multiple preference perspectives to align with RAG requirements comprehensively.
Outcome:	The proposed method improves the performance of RAG generators by incorporating retrieved documents into the prompt.

Copied to clipboard

Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong

Entrospect: Information-Theoretic Self-Reflection Elicits Better Response Refinement of Small Language Models (2025.findings-acl)

Challenge:	Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach:	They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome:	The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.

Copied to clipboard

Tianqiang Yan, Ziqiao Lin, Lin Zhang, Zhenglong Sun, Yuan Gao

Semantic Relation-aware Difference Representation Learning for Change Captioning (2021.findings-acl)

Challenge:	Existing approaches to self-reflection fail to deliver robust response refinement for models with parameter sizes of 10 billion or smaller.
Approach:	They propose to redesign Self-Refine and introduce an information-theoretic framework based on Chain-of-Thought prompt engineering to improve self-reflection in Small Language Models.
Outcome:	The proposed framework improves reasoning accuracy and computational efficiency by up to 36.2% under identical model and data settings.

Copied to clipboard

Yunbin Tu, Tingting Yao, Liang Li, Jiedong Lou, Shengxiang Gao, Zhengtao Yu, Chenggang Yan

CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation (2024.acl-long)

Challenge:	Existing methods to describe semantic change in images with distractors are difficult to learn .
Approach:	They propose a semantic relation-aware difference representation learning network to explicitly learn the difference representation in the existence of distractors.
Outcome:	The proposed network achieves state-of-the-art performance on CLEVR-Change and Spot-the -Diff datasets.

Copied to clipboard

Quan Tu, Shilong Fan, Zihang Tian, Tianhao Shen, Shuo Shang, Xin Gao, Rui Yan

Summarizing Procedural Text: Data and Approach (2022.findings-emnlp)

Challenge:	CharacterEval is a benchmark for comprehensive RPCA assessment in Chinese . authors show that Chinese LLMs exhibit more promising capabilities than GPT-4 in role-playing conversation.
Approach:	They propose a Chinese benchmark for comprehensive RPCA assessment . they use a dataset of Chinese role-playing dialogues and character profiles .
Outcome:	The proposed benchmark demonstrates that Chinese LLMs exhibit more promising capabilities than GPT-4 in Chinese role-playing conversation.

Copied to clipboard

Shen Gao, Haotong Zhang, Xiuying Chen, Rui Yan, Dongyan Zhao

Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge (2022.emnlp-main)

Challenge:	Procedural text summarization task is a popular task in the NLP field because of its long length and complexity.
Approach:	They propose a procedural text summarization task with two granularity . they propose an Entity-State Graph-based Summarizer (ESGS) which aggregates contextual information for each procedure.
Outcome:	The proposed model can summarize the entire procedural text or give an overview for each step or both . Experiments on two datasets confirm the proposed model's effectiveness.

Copied to clipboard

Longxu Dou, Yan Gao, Xuqi Liu, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Min-Yen Kan, Jian-Guang Lou

Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair (2025.emnlp-industry)

Challenge:	Existing approaches to text-to-SQL require domain knowledge to parse expert questions into SQL queries.
Approach:	They propose a framework to leverage domain knowledge during parsing by building a new benchmark KnowSQL with domain-specific questions.
Outcome:	The proposed framework improves the performance of the proposed benchmark by 28.2%.

Copied to clipboard

Bojian Xiong, Yikun Lei, Xikai Liu, Shaowei Zhang, Pengyun Zhu, Yan Liu, Yongqi Leng, Ling Shi, Meizhi Zhong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

TestAgent: An Adaptive and Intelligent Expert for Human Assessment (2025.findings-acl)

Challenge:	Large language models suffer from multiple-file coding scenarios with strong inter-file dependencies . experimental results show that large language models exhibit inadequate performance in multi-file scenarios .
Approach:	They propose a retrieval-augmented reasoning framework for repository-level code repair . they use a dataset to generate standardized patches based on the key snippets .
Outcome:	The proposed framework improves retrieval accuracy and repair success on SWE-bench Lite . it surpasses models with larger size in managing extensive code contexts and fixing bugs spanning across multiple files.

Copied to clipboard

Junhao Yu, Yan Zhuang, Yuxuan Sun, Weibo Gao, Qi Liu, Mingyue Cheng, Zhenya Huang, Enhong Chen

Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study (2021.naacl-main)

Challenge:	Existing adaptive testing methods face several challenges due to mechanized nature of most algorithms and noisy response data.
Approach:	They propose to use large language models to enhance adaptive testing through interactive engagement to capture test-takers’ responses and anomalies.
Outcome:	The proposed agent achieves more accurate results with 20% fewer questions than state-of-the-art baselines and testers preferred it in speed, smoothness, and other dimensions.

Copied to clipboard

Chongyang Tao, Shen Gao, Juntao Li, Yansong Feng, Dongyan Zhao, Rui Yan

Challenge:	Existing approaches to encode natural languages without orders are lacking.
Approach:	They conduct a comprehensive analysis of the ability of neural models to organize sentences from a bag of words under three typical scenarios.
Outcome:	The proposed models can reorder or reconstruct sentences from a bag of words under three typical scenarios.

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios (2025.emnlp-main)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Yunkai Dang, Mengxi Gao, Yibo Yan, Xin Zou, Yanggan Gu, Jungang Li, Jingyu Wang, Peijie Jiang, Aiwei Liu, Jia Liu, Xuming Hu

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)

Challenge:	Existing studies have focused mainly on visual–textual misalignment, leaving largely unexplored the MLLMs’ ability to preserve an original correct answer when confronted with misleading information.
Approach:	They propose a two-stage evaluation pipeline to quantify the response uncertainty phenomenon by eliciting each model’s original response on unperturbed inputs and injecting explicit (false-answer hints) and implicit (contextual contradictions) misleading instructions.
Outcome:	The proposed model overturns a correct answer in 65% of cases after receiving a single deceptive cue.

Copied to clipboard

Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen

Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification (2023.findings-emnlp)

Challenge:	Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities.
Approach:	They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance.
Outcome:	The proposed method achieves a superior balance between downstream learning and general capability retention.

Copied to clipboard

Jiahuan Yan, Haojun Gao, Zhang Kai, Weize Liu, Danny Chen, Jian Wu, Jintai Chen

StraGo: Harnessing Strategic Guidance for Prompt Optimization (2024.findings-emnlp)

Challenge:	Existing approaches to medical text classification are struggling with imbalanced data distribution and rare labels.
Approach:	They propose a framework-agnostic algorithm that only utilizes internal label hierarchy in training deep learning models.
Outcome:	The proposed approach performs better on public datasets and real-world medical records than existing methods.

Copied to clipboard

Yurong Wu, Yan Gao, Bin Zhu, Zineng Zhou, Xiaodi Sun, Sheng Yang, Jian-Guang Lou, Zhiming Ding, Linjun Yang

Multilingual Generative Retrieval via Cross-lingual Semantic Compression (2025.findings-emnlp)

Challenge:	Existing methods for prompt optimization often lead to prompt drifting, wherein newly generated prompts canadversely impact previously successful cases while addressing failures.
Approach:	They propose a method to mitigate prompt drifting by integrating in-context learning to formulate specific, actionable strategies for prompt optimization.
Outcome:	The proposed approach mitigates prompt drifting by leveraging insights from both successful and failed cases to identify critical factors for achieving optimization objectives.

Copied to clipboard

Yuxin Huang, Simeng Wu, Ran Song, Yan Xiang, Yantuan Xian, Shengxiang Gao, Zhengtao Yu

Multilinguality

Challenge:	Existing methods for multilingual retrieval still face cross-lingual identifier misalignment and identifiere inflation.
Approach:	They propose a framework that unifies semantically equivalent multilingual keywords into shared atoms to align semantics and compresses the identifier space.
Outcome:	The proposed framework improves cross-lingual alignment and reduces redundancy.

DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? (2024.findings-emnlp)

Copied to clipboard

Zhouhong Gu, Lin Zhang, Xiaoxuan Zhu, Jiangjie Chen, Wenhao Huang, Yikai Zhang, Shusen Wang, Zheyu Ye, Yan Gao, Hongwei Feng, Yanghua Xiao

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (2026.findings-acl)

Challenge:	Existing LLMs' abilities to detect evidence in long contexts are far inferior to humans.
Approach:	They propose a benchmark to assess LLMs' abilities in evidence and multi-step commonsense reasoning within a long context.
Outcome:	The proposed method improves the performance of LLMs in evidence detection and commonsense reasoning.

Copied to clipboard

Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, PS Tan, Jie Zhang, Xuming Hu

TACR: A Table Alignment-based Cell Selection Method for HybridQA (2023.findings-acl)

Challenge:	Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains.
Approach:	They propose a training framework that operationalizes this principle through coarse-to-fine budgeting.
Outcome:	Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines.

Copied to clipboard

Jian Wu, Yicheng Xu, Yan Gao, Jian-Guang Lou, Börje Karlsson, Manabu Okumura

Structured Data in NLP

Challenge:	Hybrid Question-Answering datasets lack a robust reasoning model for text-based QA.
Approach:	They propose a table-question-alignment-based cell-selection and reasoning model for hybrid text and table QA.
Outcome:	The proposed model outperforms baselines on HybridQA and WikiTableQuestions datasets on cell selection and argumentation.

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Weihang Wang, Xinhao Li, Ziyue Wang, Yan Pang, Jielei Zhang, Peiyi Li, Qiang Zhang, Longwen Gao

Dialogue Summarization with Static-Dynamic Structure Fusion Graph (2023.acl-long)

Challenge:	Existing benchmarks focus on coarse-grained hallucination detection and fail to capture hallucinics . vision encoders exhibit unique hallucinian characteristics, but suboptimal of simple feature fusion.
Approach:	They propose a visual encoder that employs different training paradigms to instill inductive biases in visual encoded models.
Outcome:	The proposed system reduces hallucinations and improves model performance.

Copied to clipboard

Shen Gao, Xin Cheng, Mingzhe Li, Xiuying Chen, Jinpeng Li, Dongyan Zhao, Rui Yan

EpLSA: Synergy of Expert-prefix Mixtures and Task-Oriented Latent Space Adaptation for Diverse Generative Reasoning (2024.lrec-main)

Challenge:	Dialogue summarization is a challenging task since it has dynamic interaction nature and inconsistent information flow among various speakers.
Approach:	They propose a Static-Dynamic graph-based Dialogue Summarization model which fuses prior knowledge from human expertise and adaptively learns the graph structure in an end-to-end learning fashion.
Outcome:	The proposed model can help people capture the highlights of a semi-structured and multi-participant dialogue without reviewing the complex dialogue context.

Copied to clipboard

Fujun Zhang, Xiangdong Su, Jiang Li, Rong Yan, Guanglai Gao

DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision (2025.emnlp-industry)

Challenge:	Existing models for diverse generative reasoning struggle to generate multiple unique and plausible results.
Approach:	They propose a model based on expert-prefix mixtures and task-oriented latent space adaptation for diverse generative reasoning.
Outcome:	The proposed model outperforms existing models on three types of generative reasoning tasks.

Copied to clipboard

Yongqi Leng, Yikun Lei, Xikai Liu, Meizhi Zhong, Bojian Xiong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria (2025.naacl-long)

Challenge:	Recent advances in outcome-supervised reinforcement learning (RL) have shown strong performance, but this approach still suffers from inefficient exploration, sparse reward signals, and ambiguous global reward feedback.
Approach:	They propose a model that models RAG as a Markov Decision Process (MDP) and introduces an efficient pruning strategy to optimize data expansion.
Outcome:	The proposed model outperforms existing methods and achieves an average performance improvement of 6.2% across six datasets.

Copied to clipboard

Wentao Ge, Shunian Chen, Hardy Chen, Nuo Chen, Junying Chen, Zhihong Chen, Wenya Xie, Shuo Yan, ChenghaoZhu ChenghaoZhu, Ziyue Lin, Dingjie Song, Xidong Wang, Anningzhe Gao, Zhang Zhiyi, Jianquan Li, Xiang Wan, Benyou Wang

MoDification: Mixture of Depths Made Easy (2025.naacl-long)

Challenge:	Existing evaluation methodologies for multimodal large language models are limited in evaluating objective queries without considering real-world user experiences.
Approach:	They propose to evaluate multimodal large language models with per-sample criteria using potent MLLM as the judge.
Outcome:	The proposed evaluation paradigm shows that it can be used to evaluate multimodal large language models with per-sample criteria.

Copied to clipboard

Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song

Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective (2025.coling-main)

Challenge:	Long-context efficiency is a trending topic in large language model (LLM) serving.
Approach:	They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory.
Outcome:	The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications.

Copied to clipboard

Meizhi Zhong, Chen Zhang, Yikun Lei, Xikai Liu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment (2024.findings-acl)

Challenge:	Enabling LLMs to handle lengthy context is currently a research hotspot . a notable challenge limiting further customization is the inability of LLM to utilize context beyond pretrained length due to the inherent flaw of rotary position embedding (RoPE).
Approach:	They propose to extend the RoPE from an attention perspective and on two benchmarking tasks.
Outcome:	The proposed extension of the RoPE improves extrapolation and retrieval errors.

Copied to clipboard

Jixiang Hong, Quan Tu, Changyu Chen, Gao Xing, Ji Zhang, Rui Yan

Incorporating Causal Analysis into Diversified and Logical Response Generation (2022.coling-1)

Challenge:	Existing language models that generate harmful responses are constrained by their inherent capability.
Approach:	They propose to align large language models with human preferences from AI feedback.
Outcome:	The proposed framework improves the alignment of large language models with human preferences from AI feedback.

Copied to clipboard

Jiayi Liu, Wei Wei, Zhixuan Chu, Xing Gao, Ji Zhang, Tan Yan, Yulin Kang

Text Generation

Challenge:	Existing generation-based models generate generic and safe responses such as "So am I" or "I don't know"
Approach:	They propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediator into generating process.
Outcome:	The proposed model generates relevant and informative responses and outperforms the state-of-the-art in terms of automatic metrics and human evaluations.

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Persona-E²: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events (2026.acl-long)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Yuqin Yang, Haowu Zhou, Haoran Tu, Zhiwen Hui, Shiqi Yan, HaoYang Li, Dong She, Xianrong Yao, Yang Gao, Zhanpeng Jin

Challenge:	A critical bottleneck is the lack of ground-truth human data to link personality traits to emotional shifts.
Approach:	They propose a large-scale dataset to capture reader-based emotional variations across news, social media, and life narratives.
Outcome:	The proposed model captures reader-based emotional variations across news, social media, and life narratives.

HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation (2022.acl-long)

Copied to clipboard

Zhoujun Cheng, Haoyu Dong, Zhiruo Wang, Ran Jia, Jiaqi Guo, Yan Gao, Shi Han, Jian-Guang Lou, Dongmei Zhang

Natural Language Interfaces

Challenge:	Existing studies on table reasoning focus on flat tables and hierarchical tables . a new dataset, HiTab, aims to examine numerical reasoning over hierarchic tables based on hierarchically structured tables - a strong challenge for existing baselines and a valuable benchmark for future research.
Approach:	They propose a hierarchical question answering and natural language generation dataset to study hierarchic tables.
Outcome:	The proposed model shows that it is effective in QA and natural language generation over hierarchical tables.

Translating Headers of Tabular Data: A Pilot Study of Schema Translation (2021.emnlp-main)

Copied to clipboard

Kunrui Zhu, Yan Gao, Jiaqi Guo, Jian-Guang Lou

Multilinguality

Challenge:	Schema translation is not well studied in the community because of morphological difference and context difference between plain text and tabular data.
Approach:	They propose a schema translation model augmented with schema context . they model a target header and its context as a directed graph to represent their entities .
Outcome:	The proposed model outperforms state-of-the-art models on schema translation . it uses a graph to represent entity types and relations, and a relational-aware transformer .

Know What I don’t Know: Handling Ambiguous and Unknown Questions for Text-to-SQL (2023.findings-acl)

Copied to clipboard

Bing Wang, Yan Gao, Zhoujun Li, Jian-Guang Lou

Uncovering and Categorizing Social Biases in Text-to-SQL (2023.acl-long)

Challenge:	Existing text-to-SQL parsers generate a plausible SQL query for arbitrary user questions, thereby failing to handle problematic user questions.
Approach:	They propose a weakly supervised DTE model for error detection, localization, and explanation.
Outcome:	The proposed model achieves the best result on real-world examples and generated examples compared with baselines.

Copied to clipboard

Yan Liu, Yan Gao, Zhe Su, Xiaokang Chen, Elliott Ash, Jian-Guang Lou

AMPO: Automatic Multi-Branched Prompt Optimization (2024.emnlp-main)

Challenge:	Existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQl, but these models contain social bias at different rates.
Approach:	They propose to use data to map natural language utterances to SQL queries.
Outcome:	The proposed model can contain social bias at different rates in the downstream Text-to-SQL task.

Copied to clipboard

Sheng Yang, Yurong Wu, Yan Gao, Zineng Zhou, Bin Zhu, Xiaodi Sun, Jian-Guang Lou, Zhiming Ding, Anbang Hu, Yuan Fang, Yunsong Li, Junyan Chen, Linjun Yang

Rˆ3Net:Relation-embedded Representation Reconstruction Network for Change Captioning (2021.emnlp-main)

Challenge:	Existing prompt engineering techniques are limited to producing single flow instructions, struggling with handling diverse patterns.
Approach:	They propose an automatic prompt optimization method that iteratively develops a multi-branched prompt using failure cases as feedback.
Outcome:	The proposed method achieves the best results across five tasks and demonstrates significant optimization efficiency due to adoption of a minimal search strategy.

Copied to clipboard

Yunbin Tu, Liang Li, Chenggang Yan, Shengxiang Gao, Zhengtao Yu

Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval (2024.findings-acl)

Challenge:	Existing work on change captioning uses a natural language sentence to describe disagreement between two images.
Approach:	They propose a Relation-embedded Representation Reconstruction Network to distinguish real change from clutter and irrelevant changes.
Outcome:	The proposed method achieves state-of-the-art on two public datasets.

Copied to clipboard

Yan Gao, Zhiwei Cao, Zhongjian Miao, Baosong Yang, Shiyu Liu, Min Zhang, Jinsong Su

MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (2025.acl-long)

Challenge:	Existing models for non-parametric domain adaptation lack kNN retrieval at each timestep, leading to substantial time overhead.
Approach:	They propose a kNN-MT-based model that uses a domain-specific translation knowledge store to interpolate the prediction distribution of the model.
Outcome:	The proposed model significantly extends kNN-MT with dynamic retrieval on widely-used datasets.

Copied to clipboard

Qizhi Pei, Lijun Wu, Zhuoshi Pan, Yu Li, Honglin Lin, Chenlin Ming, Xin Gao, Conghui He, Rui Yan

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) have shown impressive progress in mathematical problem-solving . current approaches to enhance mathematical reasoning focus on instance-level modifications .
Approach:	They propose a framework that enhances mathematical reasoning through cross-problem instruction synthesis.
Outcome:	The proposed framework boosts mathematical reasoning by 18.0 points while maintaining high data efficiency.

Copied to clipboard

Yan Liu, Feng Zhang, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Han Liu, Yangdong Deng

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection (2026.acl-long)

Challenge:	Existing approaches to mitigate inference inefficiency and optimization difficulty are fragmented and constrained by inherent trade-offs.
Approach:	They propose a framework that reconceptualizes discrete reasoning steps as a continuous probabilistic flow, quantifying the contribution of each step toward the ground-truth answer.
Outcome:	The proposed framework achieves a superior balance between inference efficiency and reasoning performance on challenging benchmarks.

Copied to clipboard

Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen

Robustness in NLP

Challenge:	Personalized MGT detection remains largely underexplored due to personalization challenges . large language models (LLMs) can imitate personal writing styles, but they can generate fake news and misinformation.
Approach:	They propose a benchmark to evaluate detector robustness under personalization . they attribute this limitation to a feature-inversion trap that flips the effect in personalized contexts .
Outcome:	The proposed framework predicts detector robustness under personalization with an 85% correlation to actual results.

Topic Memory Networks for Short Text Classification (D18-1)

Copied to clipboard

Jichuan Zeng, Jing Li, Yan Song, Cuiyun Gao, Michael R. Lyu, Irwin King

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

Challenge:	Existing classification models for short texts are weak due to data sparsity .
Approach:	They propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels.
Outcome:	The proposed model outperforms state-of-the-art models on short text classification, while generating coherent topics.

Copied to clipboard

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

CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion (2024.findings-acl)

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

Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Wai Lam, Lizhuang Ma

OTExtSum: Extractive Text Summarisation with Optimal Transport (2022.findings-naacl)

Challenge:	Large Language Models exhibit remarkable generative capabilities but can be misused for harmful purposes.
Approach:	They propose a framework that transforms natural language inputs into code inputs.
Outcome:	The proposed framework bypasses the safety guardrails of all models more than 80% of the time.

Copied to clipboard

Peggy Tang, Kun Hu, Rui Yan, Lei Zhang, Junbin Gao, Zhiyong Wang

CEDAR: A Chinese Evaluation Dataset for Computational Argumentation (2026.acl-long)

Challenge:	Extractive text summarisation aims to select salient sentences from a document to form a short yet informative summary.
Approach:	They propose to formulate extractive text summarisation as an Optimal Transport (OT) problem and use it to obtain an optimal summary that minimises the transportation cost to a given document.
Outcome:	The proposed method outperforms state-of-the-art methods and learning-based methods on multiNews, PubMed, BillSum, and CNN/DM datasets.

Copied to clipboard

Tian Lan, Jiang Li, Rong Yan, Feilong Bao, Weihua Wang, Guanglai Gao, Xiangdong Su

Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation (2025.acl-industry)

Challenge:	Existing debate datasets neglect important labels for argument mining, generation, and evaluation.
Approach:	They propose a Chinese Evaluation Dataset for Computational Argumentation that includes key arguments and key rhetorical figures, debater roles, modal words, debate results and transcripts.
Outcome:	The proposed dataset covers 600 debates about 318 topics from Chinese debate competitions.

Copied to clipboard

Shuxian Bi, Chongming Gao, Wenjie Wang, Yueqi Mou, Chenxu Wang, Tang Biao, Peng Yan, Fuli Feng

VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles (2020.emnlp-main)

Challenge:	Existing methods fail to reconcile click-through rate (CTR) optimization with topic expansion.
Approach:	They propose a query generation framework that aligns click-through rate and topic expansion goals through an online DPO paradigm.
Outcome:	The proposed approach achieves significant CTR gains (+2.3%) and higher human-rated query quality compared to state-of-the-art methods.

Copied to clipboard

Mingzhe Li, Xiuying Chen, Shen Gao, Zhangming Chan, Dongyan Zhao, Rui Yan

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models (2024.findings-emnlp)

Challenge:	Existing studies show that multimodal news can significantly improve users' sense of satisfaction for informativeness.
Approach:	They propose a task of Video-based Multimodal Summarization with Multimodal Output to solve this problem.
Outcome:	The proposed method can generate multimodal summaries with a single input . it can model the temporal dependency of video with semantic meaning of article .

Copied to clipboard

Shitian Zhao, Renrui Zhang, Xu Luo, Yan Wang, Shanghang Zhang, Peng Gao

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

Challenge:	Existing multi-modal language models with different architectures, parameter sizes, training datasets, and pipelines exhibit varying strengths across different tasks.
Approach:	They propose a framework for fusing heterogeneous models off-the-shell, which they call likelihood composition, and introduce basic operations to compose multiple models’ likelihood distribution when doing a multi-choice visual-question-answering task.
Outcome:	The proposed framework can be used to fusing heterogeneous models off-the-shell.

Copied to clipboard

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

How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing (D19-1)

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

Copied to clipboard

Shen Gao, Xiuying Chen, Piji Li, Zhangming Chan, Dongyan Zhao, Rui Yan

Text Generation

Challenge:	Extensive experiments on a large-scale real-world text summarization dataset show that PESG achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations.
Approach:	They propose a model that learns summary patterns and prototype facts from a prototype document . they use a fact checker to estimate mutual information between the input document and generated summary .
Outcome:	Experiments on a large-scale real-world text summarization dataset show that PESG achieves state-of-the-art performance.

Empirical Prior for Text Autoencoders (2024.findings-emnlp)

Copied to clipboard

Yongjing Yin, Wenyang Gao, Haodong Wu, Jianhao Yan, Yue Zhang

Com2 : A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models (2025.acl-long)

Challenge:	Variational Autoencoders (VAE) are used to train generative models with latent variables.
Approach:	They propose a transition from Variational Autoencoders (VAE) to text autoencodeurs (AE) which model a compact latent space and preserves the capability of the language model itself.
Outcome:	The proposed method generates higher quality and more diverse text than the VAE-based Transformer baselines, and is more efficient than previous approaches.

Copied to clipboard

Kai Xiong, Xiao Ding, Yixin Cao, Yuxiong Yan, Li Du, Yufei Zhang, Jinglong Gao, Jiaqian Liu, Bing Qin, Ting Liu

Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding (2025.emnlp-main)

Challenge:	Existing works focus on complex tasks like math and code, while complex commonsense reasoning remains underexplored due to its uncertainty and lack of structure.
Approach:	They propose to build a benchmark for large language models based on complex commonsense reasoning based upon causal event graphs and causal theory.
Outcome:	The proposed benchmark combines a complex commonsense reasoning benchmark with a detective story to achieve a more challenging subset.

Copied to clipboard

Zirui Shao, Feiyu Gao, Zhaoqing Zhu, Chuwei Luo, Hangdi Xing, Zhi Yu, Qi Zheng, Ming Yan, Jiajun Bu

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems (2020.acl-demos)

Challenge:	Multimodal large language models (MLLMs) have shown impressive capabilities in document understanding due to different types of annotation noise in training.
Approach:	They propose a method to reduce C&P knowledge conflicts across all tested MLLMs . they propose to use annotation noise to train models to understand document content .
Outcome:	The proposed method reduces C&P knowledge conflicts across all tested MLLMs and enhances their performance in both cognitive and perceptual tasks.

Copied to clipboard

Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang

Natural Language Interfaces

Challenge:	ConvLab-2 inherits Convlab's framework but integrates more powerful dialogue models and supports more datasets.
Approach:	They present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models and perform an end-to-end evaluation.
Outcome:	The new tool inherits ConvLab's framework and extends it by integrating many recently proposed state-of-the-art dialogue models.

ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty (2025.coling-main)

Copied to clipboard

Meizhi Zhong, Xikai Liu, Chen Zhang, Yikun Lei, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

IAD: In-Context Learning Ability Decoupler of Large Language Models in Meta-Training (2024.lrec-main)

Challenge:	Existing methods to accelerate inference of Large Language models (LLMs) are limited in their ability to retain key tokens as input length increases.
Approach:	They propose a method that leverages layer uncertainty to allocate budget size for each layer to reduce memory usage.
Outcome:	The proposed method reduces memory usage of the KV caches to only 20% when compared to full KV inference while achieving nearly lossless performance.

Copied to clipboard

Yuhan Liu, Xiuying Chen, Gao Xing, Ji Zhang, Rui Yan

SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages (2024.emnlp-main)

Challenge:	In-context Learning (ICL) is a paradigm in which LLMs acquire task-specific knowledge by processing input-output pairs provided as prompts.
Approach:	They propose an In-context learning Ability Decoupler to separate ICL ability from general ability of LLMs in meta-training phase . they first identify parameters suitable for ICL by transference-driven gradient importance and propose a new max-margin loss to emphasize the separation of the two abilities.
Outcome:	The proposed model separates the ICL ability from the general ability of LLMs in the meta-training phase, where the I-related parameters are tuned to adapt for ICL tasks.

Copied to clipboard

Holy Lovenia, Rahmad Mahendra, Salsabil Akbar, Lester James Miranda, Jennifer Santoso, Elyanah Aco, Akhdan Fadhilah, Jonibek Mansurov, Joseph Marvin Imperial, Onno Kampman, Joel Moniz, Muhammad Habibi, Frederikus Hudi, Jann Montalan, Ryan Hadiwijaya, Joanito Lopo, William Nixon, Börje Karlsson, James Jaya, Ryandito Diandaru, Yuze Gao, Patrick Irawan, Bin Wang, Jan Christian Blaise Cruz, Chenxi Whitehouse, Ivan Parmonangan, Maria Khelli, Wenyu Zhang, Lucky Susanto, Reynard Ryanda, Sonny Hermawan, Dan Velasco, Muhammad Kautsar, Willy Hendria, Yasmin Moslem, Noah Flynn, Muhammad Adilazuarda, Haochen Li, Johanes Lee, R. Damanhuri, Shuo Sun, Muhammad Qorib, Amirbek Djanibekov, Wei Qi Leong, Quyet V. Do, Niklas Muennighoff, Tanrada Pansuwan, Ilham Firdausi Putra, Yan Xu, Tai Chia, Ayu Purwarianti, Sebastian Ruder, William Tjhi, Peerat Limkonchotiwat, Alham Aji, Sedrick Keh, Genta Winata, Ruochen Zhang, Fajri Koto, Zheng Xin Yong, Samuel Cahyawijaya

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language (2025.findings-acl)

Challenge:	Southeast Asia (SEA) is home to over 1,300 indigenous languages and 671 million people . prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA .
Approach:	They propose to provide a resource center that provides standardized corpora in nearly 1,000 SEA languages across three modalities.
Outcome:	a new benchmark assesses the quality of AI models on 36 SEA languages across 13 tasks . the results highlight the importance of SEA as a culturally diverse region .

Copied to clipboard

Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao, Ruoyu Li, Yong Jiang

SSP: Self-Supervised Post-training for Conversational Search (2023.findings-acl)

Challenge:	Existing methods to bypass security defenses of large language models (LLMs) are not effective, but QueryAttack can be jailbroken.
Approach:	They propose a framework to examine generalizability of safety alignment by translating malicious queries into structured non-natural query languages.
Outcome:	The proposed framework can achieve high attack success rates and jailbreak various defense methods on mainstream LLMs.

Copied to clipboard

Quan Tu, Shen Gao, Xiaolong Wu, Zhao Cao, Ji-Rong Wen, Rui Yan

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization (2023.acl-long)

Challenge:	Existing methods to search for information are limited by data scarcity and lack contextual semantic understanding.
Approach:	They propose a new post-training paradigm with three self-supervised tasks to initialize the conversational search model to enhance dialogue structure and contextual semantic understanding.
Outcome:	The proposed method can initialize the conversational search model to enhance dialogue structure and contextual semantic understanding.

Copied to clipboard

SongYang Gao, Shihan Dou, Yan Liu, Xiao Wang, Qi Zhang, Zhongyu Wei, Jin Ma, Ying Shan

Robustness in NLP

Challenge:	Existing adversarial training methods require multi-step gradient ascents or word substitutions to obtain adversarials, which impairs the effectiveness of adversariarial training.
Approach:	They propose a procedure for instead adversarial training with only clean data that estimates the adversarials loss by perturbing the input data’s probability distribution rather than their embeddings.
Outcome:	The proposed procedure reduces time consumption by up to 70% compared to current best-performing adversarial training methods.

BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning (2024.findings-acl)

Copied to clipboard

Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, Rui Yan

Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs (2024.findings-emnlp)

Challenge:	BioT5+ is an extension of the BioT5, but lacked a nuanced understanding of molecular structures.
Approach:	They propose a new bio-entity modeling framework, BioT5+, which integrates IUPAC names and molecule data.
Outcome:	The proposed model bridges the gap between molecular representations and textual descriptions and improves the grounded reasoning of bio-text and bio-sequences.

Copied to clipboard

Fengzhu Zeng, Wenqian Li, Wei Gao, Yan Pang

NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries (2024.findings-eacl)

Challenge:	Obtaining large-scale, high-quality real-world fact-checking datasets is costly . generalizability of detectors trained on synthetic data to real-life scenarios remains unclear .
Approach:	They propose to use synthetic data to learn from real-world data to detect multimodal misinformation . they propose to combine model-agnostic data selection methods with real-life data distributions .
Outcome:	The proposed method improves the performance of a small MLLM on real-world fact-checking datasets, surpassing GPT-4V.

Copied to clipboard

Wei Zhao, Zhitao Hou, Siyuan Wu, Yan Gao, Haoyu Dong, Yao Wan, Hongyu Zhang, Yulei Sui, Haidong Zhang

Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (P19-1)

Challenge:	Creating spreadsheet formulas remains a tedious and error-prone task for many end-users . a novel task is proposed to generate spreadsheet formulae from a user's NL query .
Approach:	They propose a task to generate formulas that are grounded on a spreadsheet table given a Natural Language query as input.
Outcome:	The proposed task generates formulas that are grounded on a spreadsheet table, given a natural language query as input.

Copied to clipboard

Jiaqi Guo, Zecheng Zhan, Yan Gao, Yan Xiao, Jian-Guang Lou, Ting Liu, Dongmei Zhang