Papers by Yin Wu

Contrastive Learning with Prompt-derived Virtual Semantic Prototypes for Unsupervised Sentence Embedding (2022.findings-emnlp)

Challenge:	e-commerce and recommender systems lack a framework for personalized generation . a new framework extracts tags from multimodal information of items that the user has interacted with .
Approach:	They propose a framework that extracts tags from multimodal information and rewrites item description . they then use a decoupled text-to-text and image-to image retriever to search for similar item text .
Outcome:	The proposed framework can generate results aligned with user preferences . it can be used in e-commerce and recommender systems to win over diverse user base .

Copied to clipboard

Jiali Zeng, Yongjing Yin, Yufan Jiang, Shuangzhi Wu, Yunbo Cao

Grafting Pre-trained Models for Multimodal Headline Generation (2022.emnlp-industry)

Challenge:	Recent studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation.
Approach:	They propose a novel Contrastive learning method with Prompt-derived Virtual semantic prototypes that constructs virtual semantic prototype to each instance and derives negative prototypes by using the negative form of the prompts.
Outcome:	The proposed method performs on semantic textual similarity, transfer, and clustering tasks compared to baselines.

Copied to clipboard

Lingfeng Qiao, Chen Wu, Ye Liu, Haoyuan Peng, Di Yin, Bo Ren

KIA: Knowledge-Guided Implicit Vision-Language Alignment for Chest X-Ray Report Generation (2025.coling-main)

Challenge:	Existing approaches to generate video headlines with pre-trained language models are labor intensive and impractical.
Approach:	They propose to graft the encoder from the pre-trained video-language model on the generative pre-trainer model and propose a consensus fusion mechanism for the integration of different components.
Outcome:	The proposed model achieves strong results on a brand-new dataset collected from real-world applications.

Copied to clipboard

Heng Yin, Shanlin Zhou, Pandong Wang, Zirui Wu, Yongtao Hao

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Challenge:	Existing reports on medical images and reports lack fine-grained cross-modal interaction, leading to insufficient understanding of detailed information.
Approach:	They propose a framework for establishing cross-modal semantic alignment in radiology report pairs using knowledge-guided implicit vision-language alignment.
Outcome:	KIA improves understanding of medical images and reports by incorporating medical knowledge to enhance pathological observation and anatomical landm.

Copied to clipboard

Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach:	They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome:	The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)

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

Copied to clipboard

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

UniLG: A Unified Structure-aware Framework for Lyrics Generation (2023.acl-long)

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

Copied to clipboard

Tao Qian, Fan Lou, Jiatong Shi, Yuning Wu, Shuai Guo, Xiang Yin, Qin Jin

RAFFLES: Reasoning-based Attribution of Faults for LLM Systems (2026.eacl-long)

Challenge:	Existing works ignore musical attributes hidden behind lyrics and structure of lyrics . existing works ignore structure of generated lyrics and do not consider structure of songs .
Approach:	They propose a framework for conditional lyrics generation that considers structure and relationship between lyrics and music.
Outcome:	The proposed framework improves the structure modeling and unifies different conditions for different types of lyrics generation.

Copied to clipboard

Chenyang Zhu, Spencer Hong, Jingyu Wu, Kushal Chawla, Yuhui Tang, Youbing Yin, Nathan Wolfe, Erin Babinsky, Daben Liu

Reasoning

Challenge:	Existing evaluation frameworks focus on simple metrics and end-to-end outcomes, but they struggle with longer contexts.
Approach:	They propose an offline evaluation architecture that incorporates iterative reasoning to evaluate the quality of the candidate faults and rationales of the Judge.
Outcome:	The proposed architecture outperforms baseline evaluation frameworks with two datasets to identify step-level faults in multi-agent systems and ReasonEval datasets.

Towards General Agentic Intelligence via Environment Scaling (2026.findings-acl)

Copied to clipboard

Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Ningyu Zhang, Fei Huang, Wentao Zhang, Jingren Zhou

DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation (2026.acl-long)

Challenge:	Diverse real-world APIs require precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments.
Approach:	They propose a framework that scales up environments to enable agentic intelligence . they use a two-phase agent fine-tuning strategy to first endow agents with basic agentic capabilities, then specializing them for domain-specific contexts.
Outcome:	Experiments on -bench, -Bench, and ACEBench show that the model significantly enhances the models’ function-calling capability.

Copied to clipboard

Li Huang, Zhongxin Liu, Yifan Wu, Tao Yin, Dong li, Jichao Bi, Nankun Mu, Hongyu Zhang, Meng Yan

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) can replicate insecure patterns from training data.
Approach:	They propose a framework that leverages distributed security-relevant cues by aggregating representations from multiple upper layers via an attention-based module.
Outcome:	Experiments show that the framework improves the secure-and-correct generation rate by 11.9% over baselines.

Recurrent Attention for Neural Machine Translation (2021.emnlp-main)

Copied to clipboard

Jiali Zeng, Shuangzhi Wu, Yongjing Yin, Yufan Jiang, Mu Li

UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations (2025.acl-long)

Challenge:	Recent research questions the importance of dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns.
Approach:	They propose a novel mechanism to replace dot-product self-attention with a recurrent atteNtion mechanism that directly learns attention weights without token-to-token interaction.
Outcome:	The proposed model outperforms the Transformer model on translation tasks with fewer parameters and inference time.

Copied to clipboard

Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, Bing Yin, Meng Jiang

Dialogue Systems & Conversational Agents

Challenge:	Existing conversational search systems are usually built with two different models . this separation restricts the system from leveraging the model's intrinsic knowledge simultaneously . Existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses.
Approach:	They propose to unify dense retrieval and response generation for large language models in conversation by fine-tuning and mitigating data discrepancy.
Outcome:	The proposed model can outperform existing models on five conversational search datasets and reduce inconsistency risks while mitigating data discrepancy.

Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text (2023.acl-long)

Copied to clipboard

Qianhui Wu, Huiqiang Jiang, Haonan Yin, Börje Karlsson, Chin-Yew Lin

Do Large Language Models Know What They Don’t Know? (2023.findings-acl)

Challenge:	Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-difference (ID) examples.
Approach:	They propose a method that integrates strengths and weaknesses of both methods . they use a fine-tuned model as the teacher to teach a randomly initialized student model .
Outcome:	The proposed method outperforms human evaluators in the pair-expert task on the Human ChatGPT Comparison Corpus.

Copied to clipboard

Zhangyue Yin, Qiushi Sun, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Xuanjing Huang

Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models (2026.findings-acl)

Challenge:	Large language models (LLMs) have vast knowledge that allows them to excel in various NLP tasks.
Approach:	They propose an automated method to detect uncertainty in the responses of large language models and a dataset to measure their self-knowledge.
Outcome:	The proposed method detects uncertainty in the responses of large language models and provides a novel measure of their self-knowledge.

Copied to clipboard

Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin, Xiang Li

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

Challenge:	Existing training paradigms rely on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process.
Approach:	They propose a framework that integrates large reasoning models with retrieval-augmented generation to improve reasoning fidelity and verification rigor.
Outcome:	Experiments on multiple benchmarks demonstrate the effectiveness of the proposed framework.

Copied to clipboard

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

Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks (2023.emnlp-main)

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

Copied to clipboard

Po-Nien Kung, Fan Yin, Di Wu, Kai-Wei Chang, Nanyun Peng

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

Challenge:	Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models on diverse tasks with instructions.
Approach:	They propose a framework to identify informative tasks and then actively tune models on selected tasks.
Outcome:	The proposed method outperforms baseline strategies for task selection on NIV2 and Self-Instruct datasets.

Copied to clipboard

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

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

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

Copied to clipboard

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

Representation Learning

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

Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)

Copied to clipboard

Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang

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

Challenge:	Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains.
Approach:	They propose several strategies for deploying RAG that balance performance and efficiency.
Outcome:	The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy.

Copied to clipboard

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

AttnPO: Attention-Guided Process Supervision for Efficient Reasoning (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

Shuaiyi Nie, null Dingsiyu, Wenyuan Zhang, Linhao Yu, Tianmeng Yang, Yao Chen, Weichong Yin, Yu Sun, Hua Wu, Tingwen Liu

Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning (2026.eacl-industry)

Challenge:	Existing trajectory-level length penalties fail to effectively shorten reasoning length and degrade accuracy, as they treat all reasoning steps uniformly and lack fine-grained signals to distinguish redundancy from necessity.
Approach:	They propose a low-overhead process-supervised RL framework that leverages the model’s intrinsic attention signals for step-level credit assignment.
Outcome:	The proposed framework reduces reasoning length while improving performance across 9 benchmarks.

Copied to clipboard

Minseok Kim, Jingxiang Chen, Seong-Gyun Leem, Yin Huang, Rashi Rungta, Zhicheng Ouyang, Haibin Wu, Surya Teja Appini, Ankur Bansal, Yang Bai, Yue Liu, Florian Metze, Ahmed A Aly, Anuj Kumar, Ariya Rastrow, Zhaojiang Lin

AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning (2024.emnlp-main)

Challenge:	Using paralinguistic cues is challenging for speech large language models, authors say . limited training data, annotation difficulty, and models exploiting lexical shortcuts are challenges . a recent study shows that modeling paralinguistic reasoning with multitask RL improves paralinguistics understanding .
Approach:	They propose multi-task reinforcement learning with chain-of-thought prompting that elicits explicit affective reasoning.
Outcome:	The proposed model improves paralinguistics understanding over baselines and strong proprietary models by 8-12% on Expresso, IEMOCAP, and RAVDESS.

Copied to clipboard

Hao Sun, Jiayi Wu, Hengyi Cai, Xiaochi Wei, Yue Feng, Bo Wang, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System (2025.acl-long)

Challenge:	Recent advances in large language models have been remarkable . users face a choice between using cloud-based LLMs for generation quality or local-based ones for lower computational cost .
Approach:	They propose a new LLM utilization paradigm that facilitates collaborative operation . they evaluate AdaSwitch across 7 benchmarks and compare it to other LLMs .
Outcome:	The proposed model improves performance of local and cloud agents across 7 benchmarks . it achieves competitive results compared to the cloud agent while utilizing less computational overhead.

Copied to clipboard

Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, Nanqing Dong

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)

Challenge:	Recent AI methods have shown promise in tasks such as hypothesis generation and experimental design, but they fail to replicate the collaborative nature of real-world scientific practices.
Approach:	They propose a virtual scientific system that mimics the collaborative nature of scientific research by organizing a team of agents to generate, evaluate, and refine research ideas.
Outcome:	The proposed system outperforms the state-of-the-art method in producing new scientific ideas and offers valuable insights to guide future research.

Copied to clipboard

Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking (2025.emnlp-main)

Challenge:	Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.
Approach:	They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls.
Outcome:	The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents.

Copied to clipboard

Zekun Xi, Wenbiao Yin, Jizhan Fang, Jialong Wu, Runnan Fang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in machine writing such as open domain long-form generation.
Approach:	They propose a slow-thinking machine writing framework that emulates the human-like process of iterative expansion and reflection to improve the knowledge density of generated articles.
Outcome:	The proposed framework improves the knowledge density of generated articles without compromising metrics such as coherence and depth.

Copied to clipboard

Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen

Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization (2024.lrec-main)

Challenge:	Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models.
Approach:	They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model.
Outcome:	The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD.

Copied to clipboard

Linzhi Wu, Xingyu Zhang, Yakun Zhang, Changyan Zheng, Tiejun Liu, Liang Xie, Ye Yan, Erwei Yin

Negation Scope Refinement via Boundary Shift Loss (2023.findings-acl)

Challenge:	Lip reading is a process of interpreting silent speech from visual lip movements . but lip reading in cross-speaker scenarios poses a challenging problem due to inter-speech variability .
Approach:	They propose to exploit lip landmark-guided visual clues instead of mouth-cropped images as input features.
Outcome:	Experimental results show that the proposed approach reduces speaker-specific appearance characteristics in cross-speaker scenarios.

Copied to clipboard

Yin Wu, Aixin Sun

Challenge:	Negation detection is a complex linguistic phenomenon with long spans . existing methods tend to make wrong predictions around the scope boundaries .
Approach:	They propose a model which engages the Boundary Shift Loss to refine the predicted boundary.
Outcome:	The proposed model refines the predicted boundary on multiple datasets.

Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis (2021.naacl-main)

Copied to clipboard

Xiao Liu, Da Yin, Yansong Feng, Yuting Wu, Dongyan Zhao

Structured Data in NLP

Challenge:	Existing studies focus on analyzing structured data, while mining causal relationship among factors from unstructured data is of great importance.
Approach:	They propose a graph-based causal inference framework which builds causal graphs from fact descriptions without much human involvement.
Outcome:	The proposed framework can capture nuance from fact descriptions among confusing charges and provide explainable discrimination in few-shot settings.

EvolveSearch: An Iterative Self-Evolving Search Agent (2025.emnlp-main)

Copied to clipboard

Ding-Chu Zhang, Yida Zhao, Jialong Wu, Liwen Zhang, Baixuan Li, Wenbiao Yin, Yong Jiang, Yu-Feng Li, Kewei Tu, Pengjun Xie, Fei Huang

Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models (2026.acl-long)

Challenge:	Existing approaches to enabling LLM web search proficiency struggle with data production in open-search domains, while supervised fine-tuning struggles with data utilization efficiency.
Approach:	They propose an iterative self-evolution framework that combines SFT and RL to enhance agentic web search capabilities without external human-annotated reasoning data.
Outcome:	EvolveSearch achieves 4.7% improvement over current state-of-the-art in seven benchmarks . supervised fine-tuning struggles with data production in open-search domains compared with RL .

Copied to clipboard

Eric Hanchen Jiang, Levina Li, Frank Wan, Xiao Liang, Sophia Yin, Yuchen Wu, Xinfeng Li, Yizhou Sun, Wei Wang, Kai-Wei Chang, Ying Nian Wu

Green & Sustainable NLP

Challenge:	Existing frameworks rely on static or rule-based topologies that fail to adapt to task requirements.
Approach:	They propose a generative framework that generates highly task-adaptive topologies . they validated the framework on multiple benchmarks and validated it on multiple platforms .
Outcome:	The proposed framework outperforms existing frameworks in task-adaptive communication topologies.

Training-free LLM Merging for Multi-task Learning (2025.acl-long)

Copied to clipboard

Zichuan Fu, Xian Wu, Yejing Wang, Wanyu Wang, Shanshan Ye, Hongzhi Yin, Yi Chang, Yefeng Zheng, Xiangyu Zhao

Nested Browser-Use Learning for Agentic Information Seeking (2026.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing tasks.
Approach:	They propose a training-free method for unifying different specialized LLMs into a single model using model-wise and layer-wise pruning and scaling.
Outcome:	The proposed method outperforms existing merging techniques and surpasses models fine-tuned on combined datasets in most scenarios.

Copied to clipboard

Baixuan Li, Jialong Wu, Wenbiao Yin, Kuan Li, Zhongwang Zhang, Huifeng Yin, Zhengwei Tao, Liwen Zhang, Pengjun Xie, Jingren Zhou, Yong Jiang, Wentao Zhang, Zhiqiang Gao

Challenge:	Existing information-seeking (IS) agents rely on the web for their information acquisition.
Approach:	They propose a browser-action framework that decouples interaction control from page exploration through a nested structure.
Outcome:	Empirical results show that NestBrowse offers clear benefits in practice.

WebWalker: Benchmarking LLMs in Web Traversal (2025.acl-long)

Copied to clipboard

Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, Fei Huang

Can Intelligent Agents Revolutionize Scale Generation? (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks.
Approach:	They propose a benchmark to assess the ability of LLMs to perform web traversal by using an explore-critic paradigm.
Outcome:	The proposed framework mimics human-like web navigation through an explore-critic paradigm and demonstrates the effectiveness of RAG combined with WebWalker in real-world scenarios.

Copied to clipboard

Chenghao Jia, Zhitao Yuan, Zhaokang Zong, YiFei Yin, Zhe Chen, Man Lan, Shengjun Wu

Challenge:	Existing measurement scales require extensive manual labor and require extensive validation and validation.
Approach:	They propose a multi-agent framework that automates scale development by leveraging collaborative AI agents.
Outcome:	The proposed framework automates scale development while maintaining rigorous quality standards.

From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models (2026.findings-acl)

Copied to clipboard

Junlong Tong, Zilong Wang, YuJie Ren, Peiran Yin, Hao Wu, Wei Zhang, Xiaoyu Shen

KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation (2024.findings-acl)

Challenge:	Existing definitions of streaming LLMs are fragmented and lack a systematic taxonomy . large language models are pre-trained on static and full-context corpora .
Approach:	They propose a systematic taxonomy of current streaming Large Language Models and propose underlying methodologies for streaming LLMs.
Outcome:	The proposed model is based on data flow and dynamic interaction to clarify existing ambiguities.

Copied to clipboard

Di Wu, Da Yin, Kai-Wei Chang

Term Extraction

Challenge:	Existing evaluation methods for keyphrase extraction and generation rely on exact matching with human references.
Approach:	They propose a framework for evaluation that includes four critical aspects: reference agreement, faithfulness, diversity, utility and semantic-based metrics.
Outcome:	The proposed evaluation framework correlates better with human preferences than previously proposed metrics.

Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning (2023.acl-long)

Copied to clipboard

Fan Yin, Jesse Vig, Philippe Laban, Shafiq Joty, Caiming Xiong, Chien-Sheng Wu

Graph-based Multilingual Product Retrieval in E-Commerce Search (2021.naacl-industry)

Challenge:	Large language models have shown impressive performance in following natural language instructions to solve unseen tasks.
Approach:	They propose two strategies to help large language models better leverage task instructions . they propose to remove 60% of tokens from the task definitions while maintaining model performance .
Outcome:	The proposed approach achieves 4.2 Rouge-L improvement over 119 unseen test tasks.

Copied to clipboard

Hanqing Lu, Youna Hu, Tong Zhao, Tony Wu, Yiwei Song, Bing Yin

Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing (2025.acl-industry)

Challenge:	Modern e-commerce search systems require product retrieval under multilingual scenarios.
Approach:	They propose a universal multilingual retrieval system that captures interactions between search queries and items in e-commerce search.
Outcome:	The proposed system outperforms state-of-the-art retrieval models on five countries and has been deployed in production for multiple countries.

Copied to clipboard

Chen Wu, Yin Song

Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification (2026.acl-long)

Challenge:	a new language model that supports 512K context lengths addresses practical limitations in long-context training . a competitive 35% score on 512k-token BABILong tasks without RAG or task-specific tuning is achieved .
Approach:	They present a language model that supports 512K-token context length . they evaluated its long-context learning performance on three benchmarks .
Outcome:	The model outperforms open-source models on three long-context benchmarks . it achieves a competitive 35% score on 512K-token BABILong tasks without RAG or fine-tuning .

Copied to clipboard

Zenghao Duan, Zhiyi Yin, Zhichao Shi, Liang Pang, Shaoling Jing, Zihe Huang, Jiayi Wu, Yu Yan, Jingcheng Deng, Huawei Shen, Xueqi Cheng

Challenge:	Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content.
Approach:	They propose a method that removes toxic subspaces from FFN parameters . they propose to use a lightweight method to eliminate toxic subespaces .
Outcome:	The proposed method achieves SOTA detoxification while preserving general capabilities without large-scale retraining.

Benchmarking Hallucination in Large Language Models Based on Unanswerable Math Word Problem (2024.lrec-main)

Copied to clipboard

YuHong Sun, Zhangyue Yin, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Hui Zhao

Reasoning

Challenge:	Large language models (LLMs) are highly effective in various natural language processing tasks, but can produce unreliable conjectures in ambiguous contexts, which is known as hallucination.
Approach:	They propose a method to evaluate LLM hallucination in Question Answering based on the unanswerable math word problem (UMWP) . they combine text similarity and mathematical expression detection to determine whether LLM considers the question unanswered.
Outcome:	The proposed method combines text similarity and mathematical expression detection to determine whether the LLM considers the question unanswerable.

CTR-Guided Generative Query Suggestion in Conversational Search (2025.emnlp-industry)

Copied to clipboard

Erxue Min, Hsiu-Yuan Huang, Xihong Yang, Min Yang, Xin Jia, Yunfang Wu, Hengyi Cai, Junfeng Wang, Shuaiqiang Wang, Dawei Yin

Natural Language Interfaces

Challenge:	Generating effective query suggestions requires aligning model outputs with user click preferences.
Approach:	They propose a generative framework that leverages click modeling to denoise implicit feedback and enables reliable preference optimization for improving real-world user engagement.
Outcome:	The proposed framework outperforms strong baselines in CTR, relevance, diversity and diversity.

Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization (2025.emnlp-main)

Copied to clipboard

Jiulong Wu, Zhengliang Shi, Shuaiqiang Wang, Jizhou Huang, Dawei Yin, Lingyong Yan, Min Cao, Min Zhang

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026.acl-long)

Challenge:	Existing preference alignment methods focus on aligning model responses with human preferences while neglecting image-text modality alignment.
Approach:	They propose Entity-centric Multimodal Preference Optimization to improve modality alignment . they use open-source instruction datasets to automatically construct high-quality preference data .
Outcome:	The proposed approach reduces hallucination rates by 80.4% on Object HalBench and 52.6% on MM HalBech.

Copied to clipboard

Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong

Challenge:	Existing methods for detecting unsafe mobile GUI agents are underexplored.
Approach:	They propose a mobile agent safety detection framework that integrates a formal verifier and a VLM-based contextual judge to detect system-level violations.
Outcome:	The proposed framework achieves 10%–30% improvements over existing approaches across multiple metrics.

Task-guided Disentangled Tuning for Pretrained Language Models (2022.findings-acl)

Copied to clipboard

Jiali Zeng, Yufan Jiang, Shuangzhi Wu, Yongjing Yin, Mu Li

Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach (2025.findings-emnlp)

Challenge:	Pretrained language models are fine-tuned on task-specific datasets, but fail to capture task- specific patterns.
Approach:	They propose a method which disentangles task-relevant signals from entangled representations.
Outcome:	The proposed method improves generalization of representations by disentangling task-relevant signals from the entangled representations.

Copied to clipboard

Xiaoran Yin, Xu Luo, Hao Wu, Lianli Gao, Jingkuan Song

Challenge:	Current approaches to automating complex tasks focus on reactive policies and focus on visual observations.
Approach:	They propose a framework that prioritizes natural language understanding and structured reasoning to enhance the agent’s global understanding of the environment by developing a task-oriented, refinable world model at the outset of the task.
Outcome:	The proposed framework outperforms existing approaches in simulated environments and on real mobile devices.

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

Copied to clipboard

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

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022.emnlp-main)

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

Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu

PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation (2022.emnlp-industry)

Challenge:	Structured knowledge grounding (SKG) uses structured knowledge to complete user requests . since inputs and outputs of SKG tasks are heterogeneous, they have been studied separately .
Approach:	They propose a framework that unifies 21 SKG tasks into a text-to-text format . they use unifiedSKG to benchmark T5 with different sizes .
Outcome:	The proposed framework unifies 21 SKG tasks into a text-to-text format . it achieves state-of-the-art performance on almost all of the 21 tasks, the authors show .

Copied to clipboard

Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan, Daiting Shi, Yi Wu, Zhicong Cheng, Simiu Gu, Dawei Yin

Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning (2026.acl-long)

Challenge:	Pre-trained language models have been a key part of ranking systems . knowledge distillation is widely used to maintain high performance while keeping efficient computations.
Approach:	They propose an algorithm to combine knowledge from multi-teachers and label information to achieve competitive performance in offline and online experiments.
Outcome:	The proposed method has been deployed in a real-world commercial search system.

Copied to clipboard

Jiacheng Hua, Yishu Yin, Yuhang Wu, Tai Wang, Yifei Huang, Miao Liu

Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration (2021.emnlp-main)

Challenge:	Existing Multimodal Large Language Models struggle with 3D spatial reasoning as they fail to construct structured abstractions of the 3D environment depicted in video inputs.
Approach:	They propose a prompting method that induces MLLMs to generate 3D representations as reasoning traces for more accurate spatial question answering.
Outcome:	Extensive experiments on VSI-Bench and OST-Bech show that TRACE improves over prior prompting strategies across a diverse range of MLLM backbones.

Copied to clipboard

Xinmeng Li, Qian Li, Wansen Wu, Quanjun Yin

Knowledge Representation

Challenge:	Current models are not satisfactory for solving out-of-vocabulary problems . current models assume that the task ontology is well defined in advance .
Approach:	They propose to enhance the interrelation between slots with masked hierarchical attention.
Outcome:	The proposed model yields a significant performance gain over current state-of-the-art model and is more robust to out-ofvocabulary problem compared with other methods.

Weights-Rotated Preference Optimization for Large Language Models (2025.emnlp-main)

Copied to clipboard

Chenxu Yang, Ruipeng Jia, Mingyu Zheng, Naibin Gu, Zheng Lin, Siyuan Chen, Weichong Yin, Hua Wu, Weiping Wang

NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation (2023.acl-long)

Challenge:	Existing methods to align large language models with high reward hacking are limited by the complexity of the parameter space and the complexity.
Approach:	They propose a weights-rotated preference optimization algorithm that constrains the output layer logits with the KL divergence inherited from DPO and fine-tunes the intermediate hidden states.
Outcome:	The proposed algorithm achieves a 3.27-point improvement on AlpacaEval 2 and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters.

Copied to clipboard

Shengming Yin, Chenfei Wu, Huan Yang, Jianfeng Wang, Xiaodong Wang, Minheng Ni, Zhengyuan Yang, Linjie Li, Shuguang Liu, Fan Yang, Jianlong Fu, Ming Gong, Lijuan Wang, Zicheng Liu, Houqiang Li, Nan Duan

"I Don’t Know What to Say": A Fact-Filling Questionnaire Method to Help Non-Experts Talk to LegalAI Assistant (2026.findings-acl)

Challenge:	Existing work generates long videos segment by segment sequentially, which is inefficient.
Approach:	They propose a Diffusion over Difference architecture for eXtremely Long video generation.
Outcome:	The proposed architecture reduces the average inference time from 7.55min to 26s (94.26%) and generates high-quality long videos with both global and local coherence.

Copied to clipboard

Yuting Huang, Yiquan Wu, Meitong Guo, Ang Li, Xiaozhong Liu, Keting Yin, Fei Wu, Kun Kuang

Natural Language Interfaces

Challenge:	Recent advances in large language models (LLMs) have greatly expanded the scope of legal AI.
Approach:	They propose a method that generates questionnaires to help users refine queries . they leverage an iterative training process that collects valuable questionnaires .
Outcome:	The proposed method improves the completeness of queries and ensures the performance of domain-specific models in downstream legal tasks.

BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents (2026.findings-acl)

Copied to clipboard

Litu Ou, Kuan Li, Huifeng Yin, Liwen Zhang, Zhongwang Zhang, Xixi Wu, Rui Ye, Zile Qiao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

Challenge:	Existing work on confidence in LLMs is limited.
Approach:	They propose to use confidence scores to determine model answer quality and encourage model to try again until it reaches satisfactory confidence level.
Outcome:	The proposed methods significantly reduce token consumption while demonstrating competitive performance compared to baseline fixed budget methods.

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

MAR: Matching-Augmented Reasoning for Enhancing Visual-based Entity Question Answering (2024.emnlp-main)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Zhengxuan Zhang, Yin Wu, Yuyu Luo, Nan Tang

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation (2024.emnlp-main)

Challenge:	Multimodal large language models (MLLMs) struggle with visual-based entity questions (VEQA) MLLM can identify A, but may refrain from answering due to privacy concerns.
Approach:	They propose a method that uses vector representations to analyze visual-based entity questions (VEQA) they use visual cues and textual information to integrate visual cus and visual information .
Outcome:	The proposed method significantly improves visual-based entity question answering (VEQA) it can identify faces, names, and alignments within visual objects, and then derive the answer over this matching graph.

Copied to clipboard

Di Wu, Jia-Chen Gu, Fan Yin, Nanyun Peng, Kai-Wei Chang

Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models (2025.acl-long)

Challenge:	Existing studies show that RALMs generate baseless information or contradicts with the retrieved context.
Approach:	They propose a lightweight monitor that leverages fine-grained decoding dynamics to synchronously detect unfaithful sentences.
Outcome:	Empirical results show that SynCheck outperforms baseline faithfulness detection and FOD outperformed traditional strategies in terms of faithfulness.

Copied to clipboard

Huifeng Yin, Yu Zhao, Minghao Wu, Xuanfan Ni, Bo Zeng, Huaiyu.wh Huaiyu.wh, Tianqi Shi, Liangying Shao, Chenyang Lyu, Longyue Wang, Weihua Luo, Kaifu Zhang

AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs (2026.acl-long)

Challenge:	Recent efforts to distill large reasoning models into smaller lightweight models have shown competitive performances.
Approach:	They propose to distill long Chain-of-Thought data to improve SFT and RL methods by constructing data from scratch using Monte Carlo Tree Search.
Outcome:	The proposed method significantly improves reasoning performance on various benchmarks such as math (GSM8K, MATH, AIME).

Copied to clipboard

Qingqing Lyu, Linjuan Wu, Yongliang Shen, Hengwei Liu, Hao Li, Shengpei Jiang, Yin Zhang, Weiming Lu

Challenge:	Existing automated approaches operate within fixed task schemas and often fail to autonomously discover new evaluation dimensions.
Approach:	They propose an automated framework that constructs domain-specific benchmarks directly from unstructured corpora using Bloom’s Taxonomy.
Outcome:	The proposed framework uncovers a broader and more fine-grained task space than expert-curated benchmarks while producing high-quality instances that preserve established model-level evaluation trends.

LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models (2025.findings-naacl)

Copied to clipboard

Zhenyue Qin, Yu Yin, Dylan Campbell, Xuansheng Wu, Ke Zou, Ninghao Liu, Yih Chung Tham, Xiuzhen Zhang, Qingyu Chen

DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation (2026.findings-eacl)

Challenge:	Existing benchmarks for large vision-language models (LVLMs) are limited to ophthalmology-specific applications.
Approach:	They introduce a large-scale multimodal ophthalmology benchmark consisting of 21,993 instances across five ocular imaging modalities and 13 state-of-the-art LVLM representatives from closed-source, open-source and medical domains.
Outcome:	The proposed model shows significant performance drop in ophthalmology compared to other domains.

Copied to clipboard

Saadat Hasan Khan, Spencer Hong, Jingyu Wu, Kevin Lybarger, Youbing Yin, Erin Babinsky, Daben Liu

ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)

Challenge:	Retrieval-augmented generation (RAG) is a common technique for grounding language models in domain-specific information.
Approach:	They propose a new retrieval technique that incorporates diversity into the retrieval step to improve performance on reasoning-intensive QA benchmarks.
Outcome:	The proposed method outperforms baselines on reasoning-intensive QA benchmarks by 4–10%.

Copied to clipboard

Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

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

Challenge:	Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness .
Approach:	They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image.
Outcome:	The proposed model outperforms existing models on key downstream tasks.

Copied to clipboard

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

MAIR: A Massive Benchmark for Evaluating Instructed Retrieval (2024.emnlp-main)

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

Weiwei Sun, Zhengliang Shi, Wu Long, Lingyong Yan, Xinyu Ma, Yiding Liu, Min Cao, Dawei Yin, Zhaochun Ren

Meta-Semantics Augmented Few-Shot Relational Learning (2025.emnlp-main)

Challenge:	Existing IR benchmarks focus on a limited scope of tasks, making them insufficient for evaluating the latest IR models.
Approach:	They propose a multi-task instruction-tuned IR benchmark that includes 126 distinct IR tasks across 6 domains.
Outcome:	The proposed model performs better on instruction-tuned models than non-instruction-tunned models on MAIR.

Copied to clipboard

Han Wu, Jie Yin