Papers by Yu Fu

Advancing Vision-Language Models with Adapter Ensemble Strategies (2024.findings-emnlp)

Challenge:	Experimental results show that Large Language Models can generate rule-based data in long contexts without following all specified rules.
Approach:	They propose a novel prompting strategy Multi-Lingual Prompt which automatically translates the error-prone rule that an LLM struggles to follow into another language, thus drawing greater attention to it.
Outcome:	The proposed framework outperforms state-of-the-art prompting methods on public datasets across various tasks, with a specific case study in text-to-MIP instances.

Copied to clipboard

Yue Bai, Handong Zhao, Zhe Lin, Ajinkya Kale, Jiuxiang Gu, Tong Yu, Sungchul Kim, Yun Fu

Towards Self-Evolving Agents: Enabling Autonomy through Interactive Experience Refinement (2026.findings-acl)

Challenge:	CLIP revolutes vision-language pretraining by using contrastive learning on paired web data.
Approach:	They propose to combine a "adapter ensemble" with traditional machine learning techniques to augment large-scale pretrained vision-language models.
Outcome:	The proposed model outperforms baselines and derives improvement when the number of ensemble parameters increases.

Copied to clipboard

Cheng Yang, Xuemeng Yang, Licheng Wen, Daocheng Fu, Jianbiao Mei, Rong Wu, Pinlong Cai, Yufan Shen, Nianchen Deng, Jia Xu, Botian Shi, Yu Qiao, Haifeng Li

Challenge:	Large Language Models struggle with complex, multi-step operational tasks because they remain static during inference and cannot learn from past experience.
Approach:	They propose a framework that organizes cross-domain insights to facilitate orchestration of long-horizon workflows.
Outcome:	The proposed framework outperforms existing methods on the TAC productivity benchmark and shows strong cross-task transferability.

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Copied to clipboard

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin

Challenge:	a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach:	They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome:	The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.

IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization (2025.acl-long)

Copied to clipboard

Xinghua Zhang, Haiyang Yu, Cheng Fu, Fei Huang, Yongbin Li

Challenge:	Existing algorithms to improve the ability of LLMs to follow complex instructions are lacking.
Approach:	They propose a benchmark to improve the ability to follow complex instructions by using a IOPO alignment method to take input and output preference into consideration.
Outcome:	The proposed algorithm shows 8.15%, 2.18% improvements on in-domain data and 5.91%, 2.83% on out-of-domain datasets compared to SFT and DPO respectively.

Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation (2025.findings-emnlp)

Copied to clipboard

Xing Zhang, Jiaheng Wen, Fangkai Yang, Yu Kang, Pu Zhao, Junhao Wang, Maoquan Wang, Yufan Huang, Shengyu Fu, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang

Multilinguality

Challenge:	Existing code translation benchmarks focus on individual functions, overlooking repository-level challenges like intermodule coherence and dependency management.
Approach:	They propose a framework for benchmarking Java-to-C# translation at the repository level . it uses a translation framework guided by skeletons and fine-grained quality evaluation .
Outcome:	The proposed framework improves Java-to-C# translation quality at the repository level.

Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions (D18-1)

Copied to clipboard

Qing Li, Jianlong Fu, Dongfei Yu, Tao Mei, Jiebo Luo

Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots (2022.findings-emnlp)

Challenge:	Existing approaches to visual question answering represent images using pre-trained CNNs . but they rarely provide any insight, apart from the answer, into the VQA process .
Approach:	They propose to break up the end-to-end VQA into two steps: explaining and reasoning . they first extract attributes and generate descriptions as explanations for an image . a reasoning module utilizes these explanations in place of the image to infer an answer .
Outcome:	The proposed system achieves comparable performance with baselines, but with added benefits of explanability and the ability to improve with higher quality explanations.

Copied to clipboard

Haomin Fu, Yeqin Zhang, Haiyang Yu, Jian Sun, Fei Huang, Luo Si, Yongbin Li, Cam Tu Nguyen

Dialogue Systems & Conversational Agents

Challenge:	Documents contain various structures that hinder the ability of machines to comprehend . user information needs are often underspecified, and the nature of heterogeneous documents poses challenges.
Approach:	They propose a dataset for building machines that help users seek information via conversations . their dataset contains over 100,000 turns based on Chinese documents from five domains .
Outcome:	The proposed tasks are challenging and worthy of further research.

FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks (2021.emnlp-main)

Copied to clipboard

Chen Liu, Zhang Mengchao, Fu Zhibing, Panpan Hou, Yu Li

Information Retrieval

Challenge:	obtaining large amounts of labeled data is expensive.
Approach:	They develop a semi-supervised learning framework called FLiText which improves text classification accuracy.
Outcome:	The proposed framework improves accuracy of lightweight models on IMDb, Yelp-5, and Yahoo! Answer . the framework improve accuracy by 6.59%, 3.94%, and 3.22% on the datasets of IMDa, Yep-5 and Yahoo. Answer compared with the fully supervised method on the full dataset .

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack (2024.acl-long)

Copied to clipboard

Yu Fu, Yufei Li, Wen Xiao, Cong Liu, Yue Dong

Text Generation

Challenge:	Recent developments in balancing usefulness and safety of large language models raise a critical question . current attacks, especially adversarial ones that manipulate malicious prompts, often aim to manipulate the input .
Approach:	They show that LLMs can effectively summarize malicious long documents but often refuse to translate them.
Outcome:	The findings highlight a vulnerability in LLMs that can't translate or summarize documents . the study focuses on LLM models, Gemini and GPT-4, which can' be exploited .

Sparse Black-Box Multimodal Attack for Vision-Language Adversary Generation (2023.findings-emnlp)

Copied to clipboard

Zhen Yu, Zhou Qin, Zhenhua Chen, Meihui Lian, Haojun Fu, Weigao Wen, Hui Xue, Kun He

SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework (2024.emnlp-main)

Challenge:	Existing adversarial attacks using imperceptible perturbations are challenging to simulate . e-commerce product restrictions and hate speech monitoring are examples of such attacks .
Approach:	They propose a black-box adversarial attack that leverages sparse perturbations to simulate adversarials exhibited by illegal merchants in the black- box scenario.
Outcome:	The proposed method outperforms existing attacks and unimodal attacks by treating images and text in discrete space and outperforming existing models.

Copied to clipboard

Fu Zhang, Qi Miao, Jingwei Cheng, Hongsen Yu, Yi Yan, Xin Li, Yongxue Wu

LaTeX2Solver: a Hierarchical Semantic Parsing of LaTeX Document into Code for an Assistive Optimization Modeling Application (2023.acl-demo)

Challenge:	Existing methods for document-level relation extraction ignore bidirectional mention interaction when generating relational features for entity pairs.
Approach:	They propose a document-level relation extraction model that incorporates bidirectional mention fusion and a simple yet effective evidence extraction module for relation prediction.
Outcome:	The proposed model achieves SOTA performance and the proposed method is effective and general when integrated into existing models.

Copied to clipboard

Rindra Ramamonjison, Timothy Yu, Linzi Xing, Mahdi Mostajabdaveh, Xiaorui Li, Xiaojin Fu, Xiongwei Han, Yuanzhe Chen, Ren Li, Kun Mao, Yong Zhang

NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language Models (2025.findings-acl)

Challenge:	Existing systems that translate optimization formulas manually are cumbersome and time-consuming.
Approach:	They propose a system that converts optimization formulas from TeX document to solver language.
Outcome:	The proposed system helps operations research practitioners convert optimization formulations into solver modeling languages.

Copied to clipboard

Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang, Zhikun Li, Renjun Xu, Yu Lu, Yaochu Jin, Lili Pan, Zhenzhong Lan

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Challenge:	Existing approaches to generate research ideas rely on retrieval or prompt engineering to generate ideas.
Approach:	They propose a method that uses iterative planning and search to boost creative potential of LLMs by integrating external knowledge with broader and deeper insights.
Outcome:	The proposed method outperforms the current state-of-the-art in generating 2.5 times more top-rated ideas based on 170 seed papers in a Swiss Tournament evaluation.

Copied to clipboard

Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang

Responsible & Trustworthy NLP

Challenge:	Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach:	AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome:	Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .

Mulan: A Multi-Level Alignment Model for Video Question Answering (2023.findings-emnlp)

Copied to clipboard

Yu Fu, Cong Cao, Yuling Yang, Yuhai Lu, Fangfang Yuan, Dakui Wang, Yanbing Liu

Visual Data in NLP

Challenge:	Existing methods focus on visual-language alignment at the video level, but they do not account for fine-grained semantic interaction between video and text.
Approach:	They propose a multi-level Alignment Model for Video Question Answering that establishes alignment between visual and textual modalities at the object-level, frame-level and video-level.
Outcome:	The proposed model outperforms state-of-the-art methods even with a small amount of extra visual-language pre-training data and a reduced number of trainable parameters.

Recurrent Knowledge Identification and Fusion for Language Model Continual Learning (2025.acl-long)

Copied to clipboard

Yujie Feng, Xujia Wang, Zexin Lu, Shenghong Fu, Guangyuan Shi, Yongxin Xu, Yasha Wang, Philip S. Yu, Xu Chu, Xiao-Ming Wu

Towards Provably Secure Generative AI: Reliable Consensus Sampling (2026.findings-acl)

Challenge:	Continual learning (CL) is crucial for large language models without costly retraining.
Approach:	They propose a framework for recurrent knowledge identification and fusion that enables dynamic estimation of parameter importance distributions to enhance knowledge transfer.
Outcome:	The proposed framework mitigates catastrophic forgetting and enhances knowledge transfer.

Copied to clipboard

Yu Cui, Hang Fu, Sicheng Pan, Zhuoyu Sun, Yifei Liu, Yuhong Nie, Bo Ran, Baohan Huang, Xufeng Zhang, Haibin Zhang, Cong Zuo, Licheng Wang

Robustness in NLP

Challenge:	Existing research on generative AI security is driven by mutually reinforcing attack and defense methodologies grounded in empirical experience.
Approach:	They propose a new algorithm that uses a random sampling algorithm to control risk.
Outcome:	The proposed algorithm improves robustness and utility while maintaining latency comparable to existing algorithms.

Unified Language Representation for Question Answering over Text, Tables, and Images (2023.findings-acl)

Copied to clipboard

Bowen Yu, Cheng Fu, Haiyang Yu, Fei Huang, Yongbin Li

PROBE: PROcess-Based BEnchmark for Hallucination Detection (2026.findings-acl)

Challenge:	Existing approaches to answer complex questions are limited to text or structured data.
Approach:	They propose a paradigm that transforms images and tables into unified language representations to simplify QA problems.
Outcome:	The proposed framework outperforms existing methods on two datasets and the WebQA leaderboard.

Copied to clipboard

Yu Zhang, Peter Belcak, Shizhe Diao, Yonggan Fu, Shaona Ghosh, Morteza Mardani, Eileen Margaret Peters Long, Bei Yu, Pavlo Molchanov

On Large Language Models’ Hallucination with Regard to Known Facts (2024.naacl-long)

Challenge:	Existing agentic applications rely on LLMs to self-assess the factuality of outputs . but current LLM systems fail to detect hallucinations .
Approach:	They propose a benchmark that breaks down hallucination detection into four critical steps . they show that when halluciation detection is treated as a multi-step process, all models achieve considerably better performance.
Outcome:	The proposed benchmark breaks down hallucination detection into four critical steps . it shows that when halluciation detection is treated as a multi-step process, all models achieve considerably better performance.

Copied to clipboard

Che Jiang, Biqing Qi, Xiangyu Hong, Dayuan Fu, Yang Cheng, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou

Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs (2025.findings-emnlp)

Challenge:	Large language models are successful in answering factoid questions but are also prone to hallucination.
Approach:	They propose self-reporting to the model when faced with such limitations.
Outcome:	The proposed classifier can detect hallucinations with an 88% success rate and can be used to answer factoid questions with correct answer knowledge.

Copied to clipboard

Yao Fu, Runchao Li, Xianxuan Long, Haotian Yu, Xiaotian Han, Yu Yin, Pan Li

Challenge:	Neural network pruning disrupts LLMs’ internal activation features crucial for lie detection . layer-wise pruning sparsity inadvertently removes crucial weights, failing to improve lie detection performance despite its reliance on the most crucial LLM layer.
Approach:	They propose a pruning approach that places greater emphasis on layers with more activation outliers and stronger discriminative features simultaneously.
Outcome:	The proposed approach improves the hallucination detection for pruned LLMs (achieving 88% accuracy at 50% sparsity) and enhances their performance on TruthfulQA.

Context-Aware Interaction Network for Question Matching (2021.emnlp-main)

Copied to clipboard

Zhe Hu, Zuohui Fu, Yu Yin, Gerard de Melo

Challenge:	Existing models focus on word-level local matching and neglect the importance of contextual information.
Approach:	They propose a context-aware interaction network to properly align two sequences and infer their semantic relationship by using gate fusion layers.
Outcome:	The proposed model can accurately align two sequences and infer their semantic relationship on two question matching datasets.

MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Weikang Shi, Aldrich Yu, Rongyao Fang, Houxing Ren, Ke Wang, Aojun Zhou, Changyao Tian, Xinyu Fu, Yuxuan Hu, Zimu Lu, Linjiang Huang, Si Liu, Rui Liu, Hongsheng Li

Design Challenges in Low-resource Cross-lingual Entity Linking (2020.emnlp-main)

Challenge:	Existing approaches to visual chain-of-thought are limited by external tools or fail to generate high-fidelity diagrams.
Approach:	They propose a framework to enable large multimodal models with VCoT capabilities . they pre-train a model on a 15.2M-pair corpus and teach it how to leverage visual aids .
Outcome:	The proposed framework unlocks complex, human-like visual reasoning in large language models . it pre-trains the model on a 15.2M-pair corpus and fine-tunes it on MathCanvas-Instruct .

Copied to clipboard

Xingyu Fu, Weijia Shi, Xiaodong Yu, Zian Zhao, Dan Roth

Low-Resource NLP

Challenge:	Existing techniques for grounding mentions of entities in a foreign language do not rise to the challenges introduced by text in low-resource languages (LRL) and fail to generalize to text not taken from Wikipedia, on which they are usually trained.
Approach:	They propose a cross-lingual XEL technique that uses search engines to locate and search for foreign language entries in Wikipedia.
Outcome:	The proposed system shows an increase of 25% in gold candidate recall and 13% in end-to-end linking accuracy over state-of-the-art baselines.

Cautious Next Token Prediction (2025.findings-acl)

Copied to clipboard

Yizhou Wang, Lingzhi Zhang, Yue Bai, Mang Tik Chiu, Zhengmian Hu, Mingyuan Zhang, Qihua Dong, Yu Yin, Sohrab Amirghodsi, Yun Fu

Challenge:	Existing methods for decoding autoregressive models are temperature scaling and nucleus sampling to balance diversity and coherence.
Approach:	They propose a training-free decoding strategy that uses a model with a low perplexity score to select the trial with the lowest perplexities as the most probable and reliable path.
Outcome:	The proposed approach outperforms existing standard decoding strategies consistently by a clear margin.

FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression (2025.findings-emnlp)

Copied to clipboard

Runchao Li, Yao Fu, Mu Sheng, Xianxuan Long, Haotian Yu, Pan Li

Entity Pair-guided Relation Summarization and Retrieval in LLMs for Document-level Relation Extraction (2025.findings-naacl)

Challenge:	Current compression strategies, including token eviction and learned projections, often lead to biased representations and may require costly model retraining.
Approach:	They propose a training-free KV cache compression framework that equalizes the contribution of all tokens to the compressed representation.
Outcome:	The proposed framework ensures unbiased information retention in the KV cache.

Copied to clipboard

Fu Zhang, Hongsen Yu, Jingwei Cheng, Huangming Xu

Vulnerabilities of Large Language Models to Adversarial Attacks (2024.acl-tutorials)

Challenge:	Document-level relation extraction (DocRE) aims to extract relations between entities in a document.
Approach:	They propose an entity pair-guided relation summarization and retrieval model for DocRE . the model uses entity pairs to guide relation summaries and retrievals .
Outcome:	The proposed model achieves state-of-the-art (SOTA) performance on three datasets.

Copied to clipboard

Yu Fu, Erfan Shayegan, Md. Mamun Al Abdullah, Pedram Zaree, Nael Abu-Ghazaleh, Yue Dong

Robustness in NLP

Challenge:	This tutorial focuses on the vulnerabilities of Large Language Models to adversarial attacks . the tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity .
Approach:	This tutorial lays the foundation by explaining safety-aligned LLMs and concepts in cybersecurity.
Outcome:	The tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity.

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

When Truthful Representations Flip Under Deceptive Instructions? (2025.emnlp-main)

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

Xianxuan Long, Yao Fu, Runchao Li, Mu Sheng, Haotian Yu, Xiaotian Han, Pan Li

Representation Learning

Challenge:	Large language models (LLMs) follow maliciously crafted instructions to generate deceptive responses, posing safety challenges.
Approach:	They use Sparse Autoencoders to analyze LLM's internal representations to determine when and how they "flip" from truthful to deceptive under deceptively crafted instructions.
Outcome:	The proposed model's True/False output is predictable across all conditions based on the model''s representation, and the Deceptive instructions induce significant representational shifts compared to Truthful/Neutral representations.

Non-autoregressive Text Editing with Copy-aware Latent Alignments (2023.emnlp-main)

Copied to clipboard

Yu Zhang, Yue Zhang, Leyang Cui, Guohong Fu

GLGE: A New General Language Generation Evaluation Benchmark (2021.findings-acl)

Challenge:	Seq2Edit approaches still face several challenges such as inflexibility in generation and difficulty in generalizing to other languages.
Approach:	They propose a non-autoregressive text editing method that models the edit process with latent CTC alignments and introduces the copy operation into the edit space.
Outcome:	The proposed method outperforms existing Seq2Edit models and achieves similar or even better results than Seq1Edit with over 4 speedup.

Copied to clipboard

Dayiheng Liu, Yu Yan, Yeyun Gong, Weizhen Qi, Hang Zhang, Jian Jiao, Weizhu Chen, Jie Fu, Linjun Shou, Ming Gong, Pengcheng Wang, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Ruofei Zhang, Winnie Wu, Ming Zhou, Nan Duan

RikiNet: Reading Wikipedia Pages for Natural Question Answering (2020.acl-main)

Challenge:	Multi-task benchmarks focus on a range of Natural Language Understanding (NLU) tasks without considering the Natural Language Generation (NLG) models.
Approach:	They propose a multi-task benchmark for evaluating the generalization capabilities of NLG models across eight language generation tasks.
Outcome:	The proposed benchmarks are based on GLUE and Su-perGLUE for English and several other languages.

Copied to clipboard

Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Nan Duan

Natural Language Interfaces

Challenge:	Using Wikipedia pages to answer open-domain questions remains challenging in natural language understanding.
Approach:	They propose a model which reads Wikipedia pages for natural question answering . it uses a dynamic paragraph dual-attention reader and a cascaded answer predictor .
Outcome:	The proposed model outperforms the human model on the Natural Questions dataset . it achieves 74.3 F1 and 57.9 F1 on long-answer and short-answer tasks .

Learning Retrieval Augmentation for Personalized Dialogue Generation (2023.emnlp-main)

Copied to clipboard

Qiushi Huang, Shuai Fu, Xubo Liu, Wenwu Wang, Tom Ko, Yu Zhang, Lilian Tang

Dialogue Systems & Conversational Agents

Challenge:	Personalized dialogue generation is a popular approach for conversational AI applications . however, persona profiles may not provide comprehensive descriptions of the persona .
Approach:	They propose a method that leverages persona profiles and dialogue context to generate personalized dialogues by leveraging personas and persona profile.
Outcome:	The proposed method outperforms baselines on the CONVAI2 dataset . it is expected to generate personalized dialogues based on persona profiles and dialogue context .

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA (2024.emnlp-main)

Copied to clipboard

Minzheng Wang, Longze Chen, Fu Cheng, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li

Effective Unsupervised Constrained Text Generation based on Perturbed Masking (2022.findings-acl)

Challenge:	Existing benchmarks for evaluating long-context language models employ irrelevant noise texts to artificially extend the length of test cases, diverging from the real-world scenarios of long-constituency applications.
Approach:	They propose a long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA) .
Outcome:	The proposed model can scale up the context window of large language models to perform in-depth analysis of multiple long documents.

Copied to clipboard

Yingwen Fu, Wenjie Ou, Zhou Yu, Yue Lin

Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data (2024.findings-acl)

Challenge:	Existing methods for constrained text generation stochastically sample edit positions and actions, which cause unnecessary search steps.
Approach:	They propose to extend perturbed masking technique to search for most incongruent token to edit and introduce four multi-aspect scoring functions to select edit action to further reduce search difficulty.
Outcome:	The proposed method achieves state-of-the-art in two representative tasks . it does not require supervised data, so it could be applied to different generation tasks.

Copied to clipboard

Yanda Li, Chi Zhang, Gang Yu, Wanqi Yang, Zhibin Wang, Bin Fu, Guosheng Lin, Chunhua Shen, Ling Chen, Yunchao Wei

Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension (2023.findings-acl)

Challenge:	OpenAI's GPT-4 has demonstrated remarkable multimodal capabilities, but specific mechanics of GPT4 remain unknown.
Approach:	They propose a data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning.
Outcome:	The proposed method improves on ten commonly assessed models and provides greater flexibility compared to existing methods.

Copied to clipboard

Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie Zhou

Natural Language Interfaces

Challenge:	Compared to standard RC tasks, dialogue reading comprehension (DRC) has raised challenges because of the complex speaker information and noisy dialogue context.
Approach:	They propose a new method for dialogue reading comprehension that extracts answers from dialogues by using key-utterances-extracting methods and a Question-Interlocutor Scope Realized Graph.
Outcome:	The proposed method achieves state-of-the-art performance against previous works.

Digest the Knowledge: Large Language Models empowered Message Passing for Knowledge Graph Question Answering (2025.acl-long)

Copied to clipboard

Junhong Wan, Tao Yu, Kunyu Jiang, Yao Fu, Weihao Jiang, Jiang Zhu

Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement (2026.findings-eacl)

Challenge:	Existing methods to augment large language models (LLMs) with external knowledge are unorganized and unorganized.
Approach:	They propose a method that learns a concise facts graph and encodes it into multi-level lists of texts to augment LLMs.
Outcome:	The proposed method improves on all 5 knowledge graph question answering datasets and offers human-level semantic explainability.

Copied to clipboard

Wangyang Ying, Yanchi Liu, Xujiang Zhao, Wei Cheng, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen

Structured Data in NLP

Challenge:	Recent advances in large language models (LLMs) show potential for graph extraction, but often yield ill-formed structures or misinterpret logical constructs such as gateways.
Approach:	They propose a framework that treats procedural graph extraction as a multi-round reasoning process with structural and logical refinement agents.
Outcome:	The proposed framework achieves significant improvements in structural correctness and logical consistency over strong baselines.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models (2026.acl-long)

Copied to clipboard

Tingchen Fu, Yafu Li, Jiawei Gu, Xiaoye Qu, Yu Cheng

MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework (2025.findings-emnlp)

Challenge:	Recent advances in reasoning-oriented models have demonstrated impressive capabilities in mathematical reasoning, but their ability to adhere to user directives remains underexplored.
Approach:	They propose a benchmark to evaluate instruction-following in mathematical reasoning tasks.
Outcome:	The proposed model degrades in instruction adherence when generation length increases, but can partially recover obedience, despite increasing generation length.

Copied to clipboard

Md Shahidul Salim, Lian Fu, Arav Adikesh Ramakrishnan, Zonghai Yao, Hong Yu

Tracking Satisfaction States for Customer Satisfaction Prediction in E-commerce Service Chatbots (2022.coling-1)

Challenge:	MedCOD integrates domain-specific structured knowledge into large language models . evaluators evaluated four open-source LLMs with structured prompts .
Approach:	They propose a framework that integrates domain-specific structured knowledge into large language models . they constructed a parallel corpus of 2,999 English-Spanish MedlinePlus articles .
Outcome:	The proposed framework improves translation quality across four open-source LLMs.

Copied to clipboard

Yang Sun, Liangqing Wu, Shuangyong Song, Xiaoguang Yu, Xiaodong He, Guohong Fu

Natural Language Interfaces

Challenge:	Existing models for customer satisfaction prediction (CSP) focus on analyzing subjective customer satisfaction in conversational service, but they are hard to represent the important dynamic satisfaction states throughout the customer journey.
Approach:	They propose a model to track customer satisfaction in chatbots using a dialogue-level classification module to represent the dynamic satisfaction states at each turn.
Outcome:	The proposed model outperforms baselines and shows that it significantly outperformed multiple baselines.

MixLLM: Dynamic Routing in Mixed Large Language Models (2025.naacl-long)

Copied to clipboard

Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen

JW-SVD: Bridging the Cross-Modal Mismatch in Post-Training MLLM Compression (2026.acl-long)

Challenge:	Large Language Models (LLMs) exhibit potential artificial generic intelligence, however, their usage is costly with high response latency.
Approach:	They develop a dynamic contextual-bandit-based routing system for query-LLM assignment that leverages query tags to enhance query embeddings.
Outcome:	The proposed model maximizes response quality and minimizes cost and latency.

Copied to clipboard

Runchao Li, Yao Fu, Mu Sheng, Haotian Yu, Xianxuan Long, Kenneth A. Loparo

Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments (2022.coling-1)

Challenge:	Existing methods for compression of Multimodal Large Language Models lack multimodal adaptation to preserve cross-modal synergy.
Approach:	They propose a framework that aligns vision and language manifolds via a Joint Covariance basis and propose Global Spectrum-Aware Truncation to dynamically transfer parameter budget to the sensitive Backbone.
Outcome:	Experiments on Qwen2.5-VL and Llama-3-Next confirm that JW-SVD retains both text and image capabilities.

Copied to clipboard

Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Guohong Fu, Min Zhang

Syntactic Text Processing

Challenge:	Recent works of SRL mainly fall into two lines: 1) BIO-based; 2) span-based.
Approach:	They propose to regard flat argument spans as latent subtrees, thus reducing SRL to a tree parsing task.
Outcome:	The proposed model performs better than previous syntax-agnostic models on CoNLL05 and CoNll12 benchmarks.

CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks (2026.acl-long)

Copied to clipboard

Lingyue Fu, Hao Guan, Bolun Zhang, Haowei Yuan, Yaoming Zhu, Lin Qiu, ZongYu Wang, Xuezhi Cao, Xunliang Cai, Weiwen Liu, Weinan Zhang, Yong Yu

Challenge:	Existing large language models for software engineering rely on coarse-grained pass rates obscuring specific cognitive bottlenecks.
Approach:	They propose a repository-level benchmark that dissects coding capabilities through atomized tasks.
Outcome:	The proposed framework achieves a 78.55% validity yield, surpassing the 31.7% retention rate of SWE-bench-Verified.

Scene Graph Modification as Incremental Structure Expanding (2022.coling-1)

Copied to clipboard

Xuming Hu, Zhijiang Guo, Yu Fu, Lijie Wen, Philip S. Yu

Speaker-Aware Discourse Parsing on Multi-Party Dialogues (2022.coling-1)

Challenge:	Scene graphs are used in cross-modal tasks such as image retrieval, image captioning, and visual question answering.
Approach:	They propose a model that iterates between nodes prediction and edges prediction . they frame scene graph modification as a graph expansion task by introducing incremental structure expanding .
Outcome:	The proposed model surpasses the state-of-the-art model by large margins on four benchmarks.

Copied to clipboard

Nan Yu, Guohong Fu, Min Zhang

Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation (2020.emnlp-main)

Challenge:	Discourse parsing on multi-party dialogues is an important but difficult task in dialogue systems and conversational analysis.
Approach:	They propose a speaker-aware model for parsing on multi-party dialogues using interaction features between different speakers.
Outcome:	The proposed model achieves the best-reported performance on two standard benchmark datasets.

Copied to clipboard

Dayiheng Liu, Yeyun Gong, Yu Yan, Jie Fu, Bo Shao, Daxin Jiang, Jiancheng Lv, Nan Duan

Text Generation

Challenge:	Existing methods for news headline generation focus on producing a single short sentence . et al., 2017; Gehrmann e.t., 2018; Zhong ee., 2019) focus on single-headline generation.
Approach:	They propose a method to generate multiple headlines with keyphrases of user interests . they propose generating multiple keyphrase-relevant headlines using a transformer decoder .
Outcome:	The proposed method achieves state-of-the-art in terms of quality and diversity.

Rethinking the Role of LLMs for Document-level Relation Extraction: a Refiner with Task Distribution and Probability Fusion (2025.naacl-long)

Copied to clipboard

Fu Zhang, Xinlong Jin, Jingwei Cheng, Hongsen Yu, Huangming Xu

Rectifying the Emotional Flow: Aligning Priors and Dynamic Guidance for High-Arousal Text-to-Speech (2026.acl-long)

Challenge:	Document-level relation extraction (DocRE) provides a broad context for extracting relations for entities.
Approach:	They propose a method that utilizes LLMs as a refiner and task distribution and probability fusion to refine LLM-based relation extraction methods.
Outcome:	The proposed method outperforms existing LLM-based methods without fine-tuning by 25.2% F1.

Copied to clipboard

Fangming Feng, Dongjie Fu, Zequn Xie, Yu Zhang, Yangyang Wu, Zhou Zhao, Tao Jin

BeamLoRA: Beam-Constraint Low-Rank Adaptation (2025.acl-long)

Challenge:	Existing systems suffer from linguistic collapse when pursuing high intensity or fail to meet target emotional levels.
Approach:	They propose an inference framework that introduces a neutral prosody bias and a uniform Classifier-Free Guidance that distorts the acoustic manifold, leading to artifacts.
Outcome:	The proposed framework achieves superior linguistic accuracy and expressiveness without model retraining.

Copied to clipboard

Naibin Gu, Zhenyu Zhang, Xiyu Liu, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang

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

Challenge:	Low-Rank Adaptation (LoRA) is one of the most efficient parameter-efficient fine-tuning methods.
Approach:	They propose to conceptualize each LoRA module as a beam where each rank corresponds to a potential sub-solution.
Outcome:	The proposed method improves performance on three base models and 12 datasets.

Copied to clipboard

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

Responsible & Trustworthy NLP

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

The Best of Both Worlds: Combining Parallel and Sequential Inference Scaling via Aggregation Fine-Tuning (2026.findings-acl)

Copied to clipboard

Yafu Li, Zhilin Wang, Tingchen Fu, Ganqu Cui, Sen Yang, Yu Cheng

Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs (2025.emnlp-main)

Challenge:	Empirical results show that AFT-trained models achieve substantial gains with test-time scaling.
Approach:	They introduce a supervised fine-tuning paradigm where models synthesize multiple draft responses into a single, refined answer.
Outcome:	Empirical results show that AFT-trained models outperform baseline models while eliminating external guidance.

Copied to clipboard

Yao Fu, Xianxuan Long, Runchao Li, Haotian Yu, Mu Sheng, Xiaotian Han, Yu Yin, Pan Li

Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)

Challenge:	Quantization enables efficient deployment of large language models in resource-constrained environments . but impact on truthfulness remains largely unexplored .
Approach:	They propose a framework to assess the truthfulness of quantized large language models . they find quantized models retain internally truthful representations but produce false outputs .
Outcome:	The framework assesses the truthfulness of quantized models across three dimensions . it finds that quantized model models retain internally truthful representations but are more susceptible to false outputs .

Copied to clipboard

YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin

RST Discourse Parsing with Second-Stage EDU-Level Pre-training (2022.acl-long)

Challenge:	supervised fine-tuning (SFT) is crucial for multimodal large language models, yet a comprehensive scaling law is lacking . et al.: scaling laws focus on model size, pre-training tokens, and MLLM SFT data volumes .
Approach:	They propose two scaling laws to guide optimal model-data configuration . they propose one applicable when training data volumes are well defined by researchers .
Outcome:	The proposed scaling laws provide valuable recommendations for optimal resource allocation . they show that the proposed laws are more accurate than existing models .

Copied to clipboard

Nan Yu, Meishan Zhang, Guohong Fu, Min Zhang

A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversation (2021.findings-emnlp)

Challenge:	Existing pre-trained language models (PLMs) are based on sentence-level pre-training, which is different from the basic processing unit, i.e. element discourse unit (EDU).
Approach:	They propose a second-stage EDU-level pre-training approach to learn effective EDU representations continually based on well pre-trained language models.
Outcome:	The proposed method improves F1 score by 2.1 points on a benckmark dataset.

Copied to clipboard

Yang Sun, Nan Yu, Guohong Fu

Free-MAD: Consensus-Free Multi-Agent Debate (2026.findings-acl)

Challenge:	Prior research focuses on exploring sequential information but ignores the discourse structures of conversations.
Approach:	They propose a discourse-aware graph neural network (ERMC-DisGCN) that leverages contextual cues and speaker-specific features for ERMC.
Outcome:	The proposed method outperforms multiple baselines showing that discourse structures are of great value to ERMC.

Copied to clipboard

Yu Cui, Hang Fu, Haibin Zhang, Licheng Wang, Cong Zuo

Inverse Reinforcement Learning for Text Summarization (2023.findings-emnlp)

Challenge:	Existing multi-agent debate methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is decided by majority voting in the last round.
Approach:	They propose a multi-agent debate framework that eliminates the need for consensus among agents and reconstructs the debate phase by introducing anti-conformity.
Outcome:	Experiments on eight benchmark datasets show that Free-MAD significantly improves reasoning performance while requiring only a single-round debate and thus reducing token costs.

Copied to clipboard

Yu Fu, Deyi Xiong, Yue Dong