Papers by Hao Sun

AIDA-SEAT: Towards Reliable AI Doctor Assistant via State-Evaluation-Action Tree Enhanced LLMs in Online Hospital (2026.acl-industry)

Challenge:	Existing models for document-level language pretraining are not suitable for long documents due to their quadratically increasing memory and time consumption.
Approach:	They propose a document-level language pretraining model based on Recurrence Transformers.
Outcome:	The proposed model outperforms existing models on language understanding tasks.

Copied to clipboard

Lianxin Sun, Xiaoying Ying, Guangya Yu, Weiyan Zhang, Chenhao Guan, Hao He, Mingxi Shang, Jianhua Li, ChunMing Wang, Tong Ruan

Failures are Treasures: Constructing a Pedagogical Bridge for Agentic Strategy Distillation (2026.findings-acl)

Challenge:	Existing systems rely on large language models or retrieval-augmented generation (RAG) but these methods lack the explicit logical pathways essential for multi-step reasoning.
Approach:	They propose an AIDA-SEAT framework to provide reliable clinical decision-making support by transforming and modifying medical documents and doctors' state-evaluation-action trees.
Outcome:	The proposed framework achieves 1.01% higher than current state-of-the-art (SOTA) baselines across five departments, including common RAG-based methods.

Copied to clipboard

Jiaxin Guo, Hao Sun, Wenhao Zhang, Chunyu Yang, Yan Zhang

Rethinking Diverse Human Preference Learning through Principal Component Analysis (2025.findings-acl)

Challenge:	Existing knowledge distillation methods focus on imitating successful trajectories, whereas small language models are fragile and often collapsing after encountering errors.
Approach:	They propose a Pedagogical Bridge for Reflective Insight and Distillation of Guiding Errors that combines reflection-in-action and reflection-on-action to enable agents to diagnose and correct critical errors while abstracting transferable strategies from contrastive student–teacher trajectories.
Outcome:	Experiments show that the proposed model significantly elevates performance in large language models (SLMs) .

Copied to clipboard

Feng Luo, Rui Yang, Hao Sun, Chunyuan Deng, Jiarui Yao, Jingyan Shen, Huan Zhang, Hanjie Chen

Explainability & Interpretability in NLP

Challenge:	Decomposed Reward Models extract diverse human preferences from binary comparisons without fine-grained annotations.
Approach:	They propose a decomposed reward model that extracts diverse human preferences from binary comparisons without fine-grained annotations.
Outcome:	The proposed approach extracts diverse human preferences from binary comparisons without fine-grained annotations.

Enhancing Self-Attention with Knowledge-Assisted Attention Maps (2022.naacl-main)

Copied to clipboard

Jiangang Bai, Yujing Wang, Hong Sun, Ruonan Wu, Tianmeng Yang, Pengfei Tang, Defu Cao, Mingliang Zhang1, Yunhai Tong, Yaming Yang, Jing Bai, Ruofei Zhang, Hao Sun, Wei Shen

Contextualized Perturbation for Textual Adversarial Attack (2021.naacl-main)

Challenge:	Existing works of knowledge infusion depend on multi-task learning frameworks, which are inefficient and require large-scale retraining when new knowledge is considered.
Approach:	They propose a method which integrates knowledge-generated attention maps into the self-attention mechanism and integrates it into the model.
Outcome:	The proposed model outperforms existing methods on academic datasets and industry-scale ad relevance applications.

Copied to clipboard

Dianqi Li, Yizhe Zhang, Hao Peng, Liqun Chen, Chris Brockett, Ming-Ting Sun, Bill Dolan

FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner (2026.acl-long)

Challenge:	Existing techniques for generating adversarial examples are driven by local heuristic rules that are agnostic to the context, resulting in unnatural and ungrammatical outputs.
Approach:	They propose a ContextuaLized AdversaRial Example generation model that generates fluent and grammatical outputs through a mask-then-infill procedure.
Outcome:	The proposed model outperforms baseline models in terms of attack success rate, textual similarity, fluency and grammaticality.

Copied to clipboard

Hao Wu, Hongru Sun, Wanqing Li, Xinguo Yu, Hao Ming, Xiao Luo, Wenbin Zhang, Jiahong Zhao, Yi Guo, Jie Yang

Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL (2026.findings-acl)

Challenge:	Existing approaches to mathematical reasoning rely on static heuristics or pre-determined reasoning strategies.
Approach:	They propose an adaptive framework that integrates fuzzy theory into LLM-based mathematical reasoning.
Outcome:	The proposed framework outperforms state-of-the-art models while offering effective and interpretable diagnostics of intermediate problem-solving states.

Copied to clipboard

Zhewei Yao, Guoheng Sun, Łukasz Borchmann, Zheyu Shen, Minghang Deng, Bohan Zhai, Hao Zhang, Ang Li, Yuxiong He

Programming Languages in NLP

Challenge:	Translating natural language questions into SQL is a core challenge in natural language understanding and human-computer interaction.
Approach:	They propose a reinforcement learning framework and model family to generate accurate, executable SQL using a lightweight reward signal based solely on execution correctness.
Outcome:	The proposed framework outperforms previous versions of 70B-class systems and achieves state-of-the-art execution accuracy across six diverse Text2SQL benchmarks.

Enhancing Retrieval-Augmented Generation via Evidence Tree Search (2025.acl-long)

Copied to clipboard

Hao Sun, Hengyi Cai, Yuchen Li, Xuanbo Fan, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias (2023.findings-acl)

Challenge:	Evidence retrieval is used to enhance Large Language Models (LLMs) but in real-world applications, it often returns lengthy documents with redundant or irrelevant content, confusing downstream readers.
Approach:	They propose a framework that reformulates evidence retrieval as a dynamic tree expansion process.
Outcome:	The proposed framework outperforms existing methods on five datasets.

Copied to clipboard

Zhiyuan Zhang, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review (2025.findings-acl)

Challenge:	Existing methods to fine-tune pre-trained language models (PLMs) are not safe, since the fine-uning process is invisible to the user.
Approach:	They propose a technique to study the dynamic process of fine-tuning for finding poisonous dimensions using diffusion theory.
Outcome:	The proposed approach can detect poisonous dimensions with abnormal dynamics, purify them and fine-tune them on a clean dataset.

Copied to clipboard

Pei Fu, Tongkun Guan, Zining Wang, Zhentao Guo, Chen Duan, Hao Sun, Boming Chen, Qianyi Jiang, Jiayao Ma, Kai Zhou, Junfeng Luo

MAIN: Mutual Alignment Is Necessary for instruction tuning (2025.emnlp-main)

Challenge:	Recent advances in vision-language models have unified perception and understanding tasks within Visual Question Answering paradigms.
Approach:	They propose to outline timeline, architecture, and pipeline of nearly all TIU MLLMs and review their performance on mainstream benchmarks.
Outcome:	The proposed models perform well on mainstream benchmarks and are compared with other models.

Copied to clipboard

Fanyi Yang, Jianfeng Liu, Xin Zhang, Haoyu Liu, Xixin Cao, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration (2026.findings-acl)

Challenge:	Instruction tuning has enabled large language models to achieve remarkable performance, yet its success heavily depends on the availability of high-quality instruction-response pairs.
Approach:	They propose a mutual alignment framework which enforces coherence between instructions and responses through mutual constraints.
Outcome:	The proposed framework generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks.

Copied to clipboard

Linzhuang Sun, Tianyu Guo, Hao Liang, Ruitong Liu, Yuying Li, Qifeng Cai, Jingxuan Wei, Yuchen Wu, Bihui Yu, Xiangxiang Zhang, Wentao Zhang, Bin Cui

Programming Languages in NLP

Challenge:	Structured Query Language (SQL) is the cornerstone for data-driven decision-making.
Approach:	They propose a benchmark to rigorously evaluate Large Language Models within a dynamic interaction framework.
Outcome:	The proposed benchmark aims to rigorously evaluate LLMs within a dynamic interaction framework.

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)

Copied to clipboard

Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Challenge:	Existing presentation agents rely on predefined workflows and fixed templates to generate presentations.
Approach:	They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation.
Outcome:	The proposed framework can be used to generate presentations with environmental observations.

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline (2022.naacl-main)

Copied to clipboard

Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020.aacl-main)

Challenge:	Rather than pursuing the reachless SOTA accuracy, researchers are focusing on model efficiency and usability.
Approach:	They propose an evaluation and a public leaderboard for efficient NLP models that depicts the Pareto Frontier for various language understanding tasks.
Outcome:	The proposed model outperforms or performs on par with SOTA compressed and early exiting models.

Copied to clipboard

Xu Han, Tianyu Gao, Yankai Lin, Hao Peng, Yaoliang Yang, Chaojun Xiao, Zhiyuan Liu, Peng Li, Jie Zhou, Maosong Sun

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors (2024.findings-emnlp)

Challenge:	Existing methods for extracting relational facts from text have been successful . but with explosion of Web text, human knowledge is increasing drastically .
Approach:	They propose to improve relation extraction methods to extract relational facts from text . they analyze existing methods and show promising directions towards more powerful RE .
Outcome:	The proposed methods can extract relational facts from text, but they are still lacking in the current field.

Copied to clipboard

Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang

Soft Syntactic Reinforcement for Neural Event Extraction (2025.naacl-long)

Challenge:	Existing tools for detecting safety issues in LLMs are expensive and inefficient.
Approach:	They propose an LLM-based safety detector which annotates the safety of queries and provides explanations for its decisions.
Outcome:	The proposed detector outperforms baselines on four sets of query-response pairs and is effective as a safety evaluator for advanced LLMs.

Copied to clipboard

Anran Hao, Jian Su, Shuo Sun, Teo Yong Sen

Syntactic Text Processing

Challenge:	Recent event extraction methods rely on pre-trained language models but still suffer from errors due to a lack of syntactic knowledge.
Approach:	They propose a method to incorporate syntactic information into PLM-based models for event extraction (EE) this method uses a standard dependency corpus to select syntax-related dimensions of the model's representation.
Outcome:	The proposed method outperforms baseline models and existing syntactic reinforcement methods on sentence-level and document-level EE benchmark datasets.

DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling (2025.emnlp-main)

Copied to clipboard

Hao Sun, Zile Qiao, Bo Wang, Guoxin Chen, Yingyan Hou, Yong Jiang, Pengjun Xie, Fei Huang, Yan Zhang

Span-based Localizing Network for Natural Language Video Localization (2020.acl-main)

Challenge:	Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs).
Approach:	They propose a framework that decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding.
Outcome:	The proposed framework decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding.

Copied to clipboard

Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou

Visual Data in NLP

Challenge:	Existing approaches to NLVL are either ranking tasks or regressing the target video span.
Approach:	They propose a video span localizing network to solve a natural language video localization task using a span-based QA approach.
Outcome:	The proposed network outperforms the state-of-the-art methods on three benchmark datasets.

InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning (2023.findings-emnlp)

Copied to clipboard

Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Minlie Huang

UniRE: A Unified Label Space for Entity Relation Extraction (2021.acl-long)

Challenge:	Existing safety detection systems have limitations in terms of their versatility and interpretability.
Approach:	They introduce a safety detection framework that unifies 7 common sub-tasks into a uniform formulation and process 39 human-annotated datasets for instruction tuning.
Outcome:	The proposed framework unifies 7 common sub-tasks into a uniform formulation and then runs on 39 human-annotated datasets to fine-tune it.

Copied to clipboard

Yijun Wang, Changzhi Sun, Yuanbin Wu, Hao Zhou, Lei Li, Junchi Yan

ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning (2025.emnlp-main)

Challenge:	Existing joint entity relation extraction models setup two separate label spaces for the two sub-tasks .
Approach:	They propose to eliminate the different treatment on the two sub-tasks’ label spaces by applying a unified classifier to predict each cell’s label.
Outcome:	The proposed model achieves competitive accuracy with the best extractor and is faster.

Copied to clipboard

Yu Sun, Xingyu Qian, Weiwen Xu, Hao Zhang, Chenghao Xiao, Long Li, Deli Zhao, Wenbing Huang, Tingyang Xu, Qifeng Bai, Yu Rong

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

Challenge:	Existing medical reasoning datasets are limited in scale and typically rely on incomplete data.
Approach:	They propose to use ReasonMed to train medical reasoning models using a multi-agent generation, verification, and refinement pipeline.
Outcome:	The largest medical reasoning dataset to date surpasses the prior best sub-10B models by 4.17% and even exceeds LLaMA3.1-70B on PubMedQA by 4.60%.

Copied to clipboard

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

Exploring Conditional Variational Mechanism to Pinyin Input Method for Addressing One-to-Many Mappings in Low-Resource Scenarios (2024.acl-short)

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

Copied to clipboard

Bin Sun, Jianfeng Li, Hao Zhou, Fandong Meng, Kan Li, Jie Zhou

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs (2025.acl-long)

Challenge:	Experimental results demonstrate the superior performance of our method.
Approach:	They propose to leverage conditional variational mechanism to simplify pinyin IME . they employ a strategy that facilitates interaction between pinyan and Chinese character information .
Outcome:	The proposed method improves the performance of pinyin input method engine (IME) under low-resource conditions.

Copied to clipboard

Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Sun Ao, Hao Zhou, Jie Zhou, Zhiyuan Liu, Maosong Sun

Se2: Sequential Example Selection for In-Context Learning (2024.findings-acl)

Challenge:	Long-context inference is crucial for advancing large language models, but its prefill speed remains a bottleneck.
Approach:	They propose an efficient long-context inference framework that leverages multi-host approximate attention to enhance prefill speed.
Outcome:	The proposed framework achieves speedups of 9.2, 4.2, and 1.6 without any degradation in performance.

Copied to clipboard

Haoyu Liu, Jianfeng Liu, Shaohan Huang, Yuefeng Zhan, Hao Sun, Weiwei Deng, Furu Wei, Qi Zhang

Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments (2026.acl-long)

Challenge:	Prior work has explored the selection of examples for in-context learning, neglecting the internal relationships between examples and exist an inconsistency between training and inference.
Approach:	They propose a sequential-aware method that leverages the LLM’s feedback on varying context, aiding in capturing inter-relationships and sequential information among examples.
Outcome:	Experiments on 23 NLP tasks show that Se2 surpasses baselines and achieves 42% relative improvement over random selection.

Copied to clipboard

Hao Mi, Qiang Sheng, Shaofei Wang, Beizhe Hu, Yifan Sun, Zhengjia Wang, Hengqi Zeng, Yang Li, Danding Wang, Juan Cao

To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion (2023.acl-long)

Challenge:	Existing methods for hallucination detection focus on implicit neural uncertainty or explicit symbolic reasoning, ignoring factual hallucinosities.
Approach:	They propose a framework that bridges neural features and symbolic judgments for hallucination detection by leveraging a "meta-judgment" process to map symbolic labels back into the feature space.
Outcome:	Extensive experiments on 4 public datasets, across 4 LLMs, against 8 baselines demonstrate the superiority of LaaB.

Copied to clipboard

Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, Xing Xie

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension (2025.acl-long)

Challenge:	Existing methods for embedding knowledge graphs implicitly memorize relation rules to infer missing links, but they are difficult to memorize due to the inherent deficiencies of such implicit memorization strategy.
Approach:	They propose a vertical learning paradigm that allows to explicitly copy target information from related factual triples for more accurate prediction.
Outcome:	The proposed model improves generalization ability and makes distant link prediction significantly easier.

Copied to clipboard

Kun Ouyang, Yuanxin Liu, Shicheng Li, Yi Liu, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

VQA-Augmented Machine Translation with Cross-Modal Contrastive Learning (2025.findings-emnlp)

Challenge:	Existing benchmarks on punchline comprehension suffer from language shortcuts that allow models to rely on text, lack of question diversity, and narrow focus on a specific domain of multimodal content.
Approach:	They propose a multimodal punchline comprehension benchmark to assess models' ability to comprehend punchlines.
Outcome:	The proposed model surpasses in-context learning and chain-of-thought in punchline comprehension.

Copied to clipboard

Zhihui Zhang, Shiliang Sun, Jing Zhao, Tengfei Song, Hao Yang

RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)

Challenge:	Existing multimodal machine translation methods often extract visual features using pre-trained models while learning text features from scratch, leading to representation imbalance.
Approach:	They propose a cross-modal VQA-augmented multimodal machine translation method . it aligns image-source text pairs and image-question text pairs through dual-text contrastive learning .
Outcome:	The proposed method outperforms state-of-the-art methods on multiple evaluation metrics.

Copied to clipboard

Hao Xiang, Tianyi Tang, Yang Su, Bowen Yu, An Yang, Fei Huang, Yichang Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Jingren Zhou, Junyang Lin, Le Sun

Reliable Use of Lemmas via Eligibility Reasoning and Section-Aware Reinforcement Learning (2026.acl-short)

Challenge:	Existing benchmarks focus on character-centric approach and fail to reflect real-world applications.
Approach:	RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.
Outcome:	RMTBench features 80 diverse characters and over 8,000 dialogue rounds.

Copied to clipboard

Zhikun Xu, Xiaodong Yu, Ben Zhou, Jiang Liu, Jialian Wu, Ze Wang, Ximeng Sun, Hao Chen, Zicheng Liu

Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance (2025.emnlp-industry)

Challenge:	Recent large language models (LLMs) perform strongly on mathematical benchmarks but often import conclusions without validating assumptions.
Approach:	They propose a model that encodes a lemma specification and trains with reinforcement learning and section-aware loss masking to assign penalty to the section responsible for errors.
Outcome:	The proposed model performs well on benchmarks but often misapplyes lemmas . the model is able to encode the specification and train with reinforcement learning .

Copied to clipboard

Zixuan Wang, Yu Sun, Hongwei Wang, Baoyu Jing, Xiang Shen, Xin Dong, Zhuolin Hao, Hongyu Xiong, Yang Song

Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation (2022.findings-emnlp)

Challenge:	Existing approaches to identifying inappropriate content require extensive human-labeled data and lack cross-issue generalization.
Approach:	They propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection.
Outcome:	The proposed model improves the MLLM's performance in both zero-shot and supervised fine-tuning settings and shows strong generalization capabilities to emergent, previously unseen issues.

Copied to clipboard

Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Fei Mi, Yasheng Wang, Lifeng Shang, Minlie Huang

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities (2025.naacl-long)

Challenge:	Existing methods to detect toxic generation of pretrained language models rely on templates, data extraction, crowdsourcing workers or automatic generation.
Approach:	They propose a method to construct adversarial contexts conditioned on a given response . they augment existing dataset BAD+ and construct a new dataset B AD+ .
Outcome:	The proposed method can detect toxic or biased content in large pretrained language models.

Copied to clipboard

Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao

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

Challenge:	Recent research shows that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks.
Approach:	They propose a framework that crafts adversarial LLMs with enhanced jailbreak ability.
Outcome:	ADV-LLM significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs.

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

GeAR: Generation Augmented Retrieval (2025.findings-acl)

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% .

Copied to clipboard

Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang

Reverse Modeling in Large Language Models (2025.naacl-short)

Challenge:	Document retrieval techniques are used to compute semantic similarity between a query and documents, but the scalar similarity fails to reflect enough information, hindering the interpretation of retrieval results.
Approach:	They propose a method which improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules.
Outcome:	The proposed method improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules.

Copied to clipboard

Sicheng Yu, Xu Yuanchen, Cunxiao Du, Yanying Zhou, Minghui Qiu, Qianru Sun, Hao Zhang, Jiawei Wu

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

Challenge:	Using pre-trained LLMs with reversed text inputs can improve their performance across multiple languages.
Approach:	They propose a way to determine whether LLMs can understand reversed text inputs by reversing entire paragraphs or documents at the token level.
Outcome:	The proposed model can be used to improve understanding across multiple languages.

Copied to clipboard

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

Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards (2022.findings-emnlp)

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

Yekun Chai, Shuohuan Wang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

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

Challenge:	Existing work does not take full advantage of over-parameterized characteristics of large pre-trained language models.
Approach:	They propose a method that uses frozen "thinned" networks to obtain a mixture of rewards and advance the derivative-free prompt learning.
Outcome:	The proposed method outperforms previous gradient-free prompt learning methods and achieves parity with gradient-based counterparts on seven language understanding benchmarks under few-shot settings.

Copied to clipboard

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

LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts (2025.findings-emnlp)

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

Junhao Chen, Jingbo Sun, Xiang Li, Haidong Xin, Yuhao Xue, Yibin Xu, Hao Zhao

MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction (2023.acl-long)

Challenge:	Large language models (LLMs) are increasingly important for their intelligence evaluation.
Approach:	They propose a game theory-based evaluation platform that measures LLMs’ decision-making strategies and social behaviors in classic game-theoretic settings.
Outcome:	The proposed system cross-evaluates 15 leading LLMs using leaderboard rankings and scoring mechanisms.

Copied to clipboard

Wang Jing, Aixin Sun, Hao Zhang, Xiaoli Li

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (D18-1)

Challenge:	Natural language video localization (NLVL) aims to localize a temporal moment from an untrimmed video that semantically corresponds to a given text query.
Approach:	They propose a proposal-based solution that generates proposals and selects the best matching proposal.
Outcome:	The proposed solution is faster than existing approaches on three public datasets.

Copied to clipboard

Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, Maosong Sun

Rethinking Document-level Neural Machine Translation (2022.findings-acl)

Challenge:	Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans.
Approach:	They propose a Few-Shot Relation Classification Dataset consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers.
Outcome:	The proposed methods perform well on the most competitive few-shot learning models, especially as compared with humans.

Copied to clipboard

Zewei Sun, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Shujian Huang, Jiajun Chen, Lei Li

Incorporating Chinese Characters of Words for Lexical Sememe Prediction (P18-1)

Challenge:	Neural machine translation models are weak enough for document-level translation . current models only translate sentences individually, resulting in poor document coherence .
Approach:	They propose to use the original Transformer model to test document-level neural machine translation . they find that the original transformer models can achieve strong results for document translation if trained properly .
Outcome:	The proposed model outperforms sentence-level models on nine datasets and two sentence- level datasets across six languages.

Copied to clipboard

Huiming Jin, Hao Zhu, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin

ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora (2021.emnlp-main)

Challenge:	Existing methods of lexical sememe prediction rely on external context information of words to represent meaning.
Approach:	They propose a character-enhanced sememe prediction framework for Chinese language that takes advantage of internal character information and external context information.
Outcome:	The proposed framework outperforms state-of-the-art methods on a Chinese sememe knowledge base and maintains robust performance even for low-frequency words.

Copied to clipboard

Xuan Ouyang, Shuohuan Wang, Chao Pang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark (2022.findings-acl)

Challenge:	Existing methods for pretraining cross-lingual models are limited in their size due to the limited amount of parallel corpora.
Approach:	They propose a method that encourages the model to align multiple languages with monolingual corpora to overcome the constraint of the parallel corpus size.
Outcome:	The proposed method outperforms existing cross-lingual models and delivers new state-of-the-art results in various cross-linguistic downstream tasks.

Copied to clipboard

Hao Sun, Guangxuan Xu, Jiawen Deng, Jiale Cheng, Chujie Zheng, Hao Zhou, Nanyun Peng, Xiaoyan Zhu, Minlie Huang

PAL: Persona-Augmented Emotional Support Conversation Generation (2023.findings-acl)

Challenge:	Dialogue safety problems severely limit the real-world deployment of generative conversational models.
Approach:	They propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings.
Outcome:	The proposed taxonomy captures unsafe behaviors in human-bot dialogue settings with rich context-sensitive unsafe examples.

Copied to clipboard

Jiale Cheng, Sahand Sabour, Hao Sun, Zhuang Chen, Minlie Huang

APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention (2026.acl-long)

Challenge:	Recent work has demonstrated the effectiveness of dialogue models in providing emotional support due to the lack of human resources for mental health support.
Approach:	They propose a framework for dynamically inferring and modeling seekers’ persona from the conversation history and a model that leverages persona information to provide personalized emotional support.
Outcome:	The proposed model outperforms baseline models on the studied benchmark.

Copied to clipboard

Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Ao Sun, Ziqi Yuan, Hao Zhou, Fandong Meng, Zhiyuan Liu

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification (D19-1)

Challenge:	Existing methods for long-video inference use compression or sparse attention . existing methods restrict LMMs from handling longer, more complex videos .
Approach:	They propose a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs.
Outcome:	The proposed framework delivers speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB without significant performance loss.

Copied to clipboard

Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Imagination and Contemplation: A Balanced Framework for Semantic-Augmented Multimodal Machine Translation (2025.findings-emnlp)

Challenge:	Few-shot domain adaptation and NOTA detection are two real-world challenges for few-shot relation classification models.
Approach:	They propose a task to investigate two aspects of few-shot relation classification models . they build upon the FewRel dataset by adding a new test set in a different domain .
Outcome:	The proposed task can evaluate few-shot domain adaptation and few- shot none-of-the-above detection on a new domain and NOTA relation choice.

Copied to clipboard

Zhuang Yu, Shiliang Sun, Jing Zhao, Tengfei Song, Hao Yang

Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents (2025.emnlp-main)

Challenge:	Multimodal Machine Translation (MMT) is effective in resolving linguistic ambiguities, but visual information often introduces redundancy or noise, potentially impairing translation quality.
Approach:	They propose a semantic-augmented framework that integrates "Imagination" and "Contemplation" they first generate synthetic images from source text and align them with authentic images via an optimal transport loss .
Outcome:	The proposed framework outperforms baselines on translation datasets with visually ambiguous or weakly correlated content.

Copied to clipboard

Haochen Sun, Shuwen Zhang, Lujie Niu, Lei Ren, Hao Xu, Hao Fu, Fangkun Zhao, Caixia Yuan, Xiaojie Wang

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

Challenge:	Large Language Models (LLMs) based agent systems have made great strides in real-world applications beyond traditional NLP tasks.
Approach:	They propose a new LLM-based Multi-Agent System benchmark, Collab-Overcooked, built on the popular Overcooked-AI game with more applicable and challenging tasks in interactive environments.
Outcome:	The proposed benchmark provides a multi-agent framework supporting diverse tasks and objectives and encourages collaboration through natural language communication.

Copied to clipboard

Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li

Enhancing Byzantine-Resistant Aggregations with Client Embedding (2024.findings-emnlp)

Challenge:	Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach:	They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome:	The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.

Copied to clipboard

Zhiyuan Zhang, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Cross-lingual Lexical Sememe Prediction (D18-1)

Challenge:	Existing Byzantine-resistant aggregations detect poisonous clients but cannot defend against backdoor injection by malicious attackers in natural language tasks.
Approach:	They propose to embed client parameters to enhance Byzantine-resistant aggregations.
Outcome:	The proposed client embeddings detect poisonous clients and discard them . the proposed algorithms can't defend against backdoor injection by malicious attackers in natural language tasks .

Copied to clipboard

Fanchao Qi, Yankai Lin, Maosong Sun, Hao Zhu, Ruobing Xie, Zhiyuan Liu

Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages (2022.acl-long)

Challenge:	Sememes are defined as the minimum semantic units of human languages . but most languages do not have sememe-based linguistic knowledge bases . a new framework is proposed to predict sememes for words in other languages based on semems .
Approach:	They propose a framework to model correlations between sememes and multi-lingual words in low-dimensional semantic space for sememe prediction.
Outcome:	The proposed model improves on baseline methods on real-world datasets.

Copied to clipboard

Xu Han, Yuqi Luo, Weize Chen, Zhiyuan Liu, Maosong Sun, Zhou Botong, Hao Fei, Suncong Zheng

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Experimental results show that by applying our framework, we can easily learn effective FGET models for low-resource languages.
Approach:	They propose a cross-lingual contrastive learning framework to learn FGET models for low-resource languages.
Outcome:	The proposed framework can learn effective FGET models for low-resource languages even without human-labeled data.

Copied to clipboard

Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun

COSY: COunterfactual SYntax for Cross-Lingual Understanding (2021.acl-long)

Challenge:	Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning .
Approach:	a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path .
Outcome:	Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness.

Copied to clipboard

Sicheng Yu, Hao Zhang, Yulei Niu, Qianru Sun, Jing Jiang

Syntactic Text Processing

Challenge:	Pre-trained multilingual language models suffer from a large performance gap between source and target languages . e.g., multilingual-BERT models are widely used in cross-lingual tasks .
Approach:	They propose a language-agnostic approach to integrate universal syntax into language models . they use SYntax-aware networks and a COunterfactual training method .
Outcome:	The proposed model achieves state-of-the-art performance on natural language inference and question answering without auxiliary training data.

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling (2025.acl-long)

Copied to clipboard

Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu

Rethinking Data Mixing from the Perspective of Large Language Models (2026.acl-short)

Challenge:	Speculative sampling is an efficient way to accelerate the auto-regressive generation process of large language models.
Approach:	They propose a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression.
Outcome:	Experiments show that FR-Spec reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution.

Copied to clipboard

Yuanjian Xu, Tianze Sun, Changwei Xu, XinLong Zhao, Jianing Hao, Ran Chen, Yang Liu, Ruijie Xu, Stephen Chen, Guang Zhang

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters (2026.acl-long)

Challenge:	Existing methods to mix data with LLMs have relied on domain definitions derived from intuition.
Approach:	They propose a reweighting framework that restructures data scheduling as a graph-constrained optimization problem.
Outcome:	The proposed framework achieves competitive performance on GPT-2 models.

Copied to clipboard

Zhiyu Xu, Lean Wang, Yuanxin Liu, Lei Li, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Translate-Train Embracing Translationese Artifacts (2022.acl-short)

Challenge:	Existing research lacks systematic analysis of the applicability and methodology of cross-modal skill injection.
Approach:	They investigate the applicability and methodology of cross-modal skill injection by integrating a domain-expert LLM into a VLM.
Outcome:	The proposed method enables transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational overhead.

Copied to clipboard

Sicheng Yu, Qianru Sun, Hao Zhang, Jing Jiang

Multilinguality

Challenge:	Existing approaches to train multilingual tasks are based on translationese and translatetrain.
Approach:	They propose to use translationese to mitigate the gap between the source and target languages to train the translator.
Outcome:	The proposed method outperforms baselines on the multilingual QA dataset TyDiQA.

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection (2024.emnlp-main)

Copied to clipboard

Hao Sun, Hengyi Cai, Bo Wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Challenge:	Large language models (LLMs) often produce factually incorrect information, also known as hallucination.
Approach:	They propose a framework for verifiable text generation with evolving memory and self-reflection that incorporates long-term memory to retain documents and recent documents.
Outcome:	The proposed framework outperforms baselines on five datasets across three knowledge-intensive tasks.

Copied to clipboard

Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach:	They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome:	The proposed model outperforms baselines on three real-world datasets.

Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models (2024.lrec-main)

Copied to clipboard

Zhuoqun Li, Hongyu Lin, Yaojie Lu, Hao Xiang, Xianpei Han, Le Sun

Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers (2023.findings-acl)

Challenge:	Recent advances in large language models have push NLP into a new era, moving away from traditional task-specific pre-train finetuning paradigm.
Approach:	They provide a comprehensive analysis of declarative and procedural knowledge for large language models and evaluate their effectiveness.
Outcome:	The proposed model can perform better with both kinds of knowledge, but at different speeds.

Copied to clipboard

Damai Dai, Yutao Sun, Li Dong, Yaru Hao, Shuming Ma, Zhifang Sui, Furu Wei

Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study (2025.emnlp-main)

Challenge:	Large pretrained language models have shown surprising in-context learning ability . despite the great success in performance, its working mechanism remains unclear .
Approach:	They explain language models as meta-optimizers and understand in-context learning as implicit finetuning . they find that Transformer attention has a dual form of gradient descent .
Outcome:	The proposed model can predict labels for unseen inputs without parameter updates . the proposed model outperforms smaller models with a single parameter update .

Copied to clipboard

Yizheng Sun, Hao Li, Chang Xu, Hongpeng Zhou, Chenghua Lin, Riza Batista-Navarro, Jingyuan Sun

Learning Logic Rules for Document-Level Relation Extraction (2021.emnlp-main)

Challenge:	Current acceleration evaluations focus on minimal overall performance degradation . however, accelerated models can exhibit significant changes in instance-level predictions .
Approach:	They investigate whether accelerated vision-Language Models can still give the same answers as before . they found that accelerated models changed original answers up to 20% of the time .
Outcome:	The results show that accelerated models changed their original answers up to 20% of the time.

Copied to clipboard

Dongyu Ru, Changzhi Sun, Jiangtao Feng, Lin Qiu, Hao Zhou, Weinan Zhang, Yong Yu, Lei Li

PromptRank: Unsupervised Keyphrase Extraction Using Prompt (2023.acl-long)

Challenge:	Existing models for document-level relation extraction relied on implicitly powerful representations, which makes the model less transparent.
Approach:	They propose a probabilistic model for document-level relation extraction by learning logic rules.
Outcome:	The proposed model outperforms baseline models in relation performance and logical consistency.

Copied to clipboard

Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xiaoyan Bai

AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2025.acl-long)

Challenge:	Existing keyphrase extraction methods struggle with document and candidate length discrepancies or fail to fully utilize the pre-trained language model without further fine-tuning.
Approach:	They propose an unsupervised keyphrase extraction approach that uses a pre-trained language model to rank candidates based on document embeddings.
Outcome:	The proposed approach outperforms the existing keyphrase extraction approach on six benchmarks.

Copied to clipboard

Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang, Jie Tang, Yuxiao Dong

PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption (2026.findings-acl)

Challenge:	Existing studies on Android agents lack systematic research on open-source and closed-source models.
Approach:	They propose a framework for Android agents that includes an operation environment and a reproducible benchmark.
Outcome:	The proposed framework lifts the success rate of open-source LLMs and LMMs from 4.59% to 21.50% for LLM and 1.93% to 13.28% for LMM.

Copied to clipboard

Xue Tan, Yi Zheng, Chang Huo, Yunruo Zhang, Yu Liu, Hao Luan, Zhuyang Yu, Jun Dai, Xiaoyan Sun, Ping Chen

Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching (2025.coling-main)

Challenge:	Existing defense mechanisms lack theoretical robustness guarantees and perform unreliably when the LLM has limited knowledge of the retrieved content.
Approach:	They propose a provably robust retrieval aggregation algorithm designed to defend against poisoning attacks on retrieved texts.
Outcome:	Experiments show that PRA-RAG reduces the attack success rate to as low as 1% while maintaining an accuracy of 71%, significantly outperforming representative state-of-the-art (SOTA) methods.

Copied to clipboard

Tianshu Wang, Xiaoyang Chen, Hongyu Lin, Xuanang Chen, Xianpei Han, Le Sun, Hao Wang, Zhenyu Zeng

Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding (2024.findings-acl)

Challenge:	Entity matching (EM) is a critical step in entity resolution (ER).
Approach:	They propose a method that incorporates record interactions from different perspectives.
Outcome:	The proposed framework improves on 8 ER datasets and 10 LLMs and achieves higher efficiency and effectiveness.

Copied to clipboard

Fanyi Qu, Hao Sun, Yunfang Wu

Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models (2025.findings-acl)

Challenge:	Recent studies show that large-scale models can generate unsupervised DG without expensive distractor annotations.
Approach:	They propose a dual task training framework that integrates pseudo distractors from LLMs and answer information as the objective target with a two-stage training process.
Outcome:	The proposed method surpasses GPT-3.5-turbo zero-shot performance with 200 fewer model parameters.

Copied to clipboard

Hao Xiang, Bowen Yu, Hongyu Lin, Keming Lu, Yaojie Lu, Xianpei Han, Ben He, Le Sun, Jingren Zhou, Junyang Lin

Graph Neural Networks with Generated Parameters for Relation Extraction (P19-1)

Challenge:	Prior research focused on developing data generation methods, while insufficient attention has been paid to quality control mechanisms and often produces inaccurate and unhelpful data.
Approach:	They propose an algorithm that automatically generates high-quality preference data, eliminating manual annotation requirements.
Outcome:	The proposed algorithm outperforms baselines in human preference alignment and reward optimization.

Copied to clipboard

Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-Seng Chua, Maosong Sun

Parallel Attention Network with Sequence Matching for Video Grounding (2021.findings-acl)

Challenge:	Existing graph neural networks can only process multi-hop relational reasoning on pre-defined graphs and cannot be directly applied in natural language relational reasoning.
Approach:	They propose a graph neural network with generated parameters using natural language sentences as inputs.
Outcome:	The proposed model can process relational reasoning on graphs and in natural language processing tasks.

Copied to clipboard

Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Siow Mong Rick Goh

LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models (2025.findings-naacl)

Challenge:	Existing approaches to video grounding are sensitive to quality of proposals and inefficient because all proposal-query pairs are compared.
Approach:	They propose a Parallel Attention Network with Sequence matching to capture selfmodal contexts and cross-modal attentive information between video and text.
Outcome:	The proposed approach is superior to state-of-the-art methods on three datasets.

Copied to clipboard

Yizheng Sun, Yanze Xin, Hao Li, Jingyuan Sun, Chenghua Lin, Riza Batista-Navarro

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)

Challenge:	Multi-modal Large Language Models (MLLMs) incur significant computational overhead due to the large number of vision tokens processed, limiting their practicality in resource-constrained environments.
Approach:	They propose a language-guided vision token pruning method that can be integrated into existing MLLMs with minimal architectural changes.
Outcome:	The proposed method reduces vision tokens by 90% and preserves model performance.

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu

AutoAlign: Get Your LLM Aligned with Minimal Annotations (2025.acl-demo)

Challenge:	Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning.
Approach:	They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs.
Outcome:	The proposed benchmarks demonstrate the stability of the proposed system and its caching system.

Copied to clipboard

Xinyu Lu, Dong Xu, Chunkang Zhang, Xinyan Guan, Junxiang Wang, Qingyu Zhang, Pengbo Wang, Yingzhi Mao, Hao Xiang, Xueru Wen, Zichao Li, Yaojie Lu, Hongyu Lin, Le Sun, Xianpei Han

Training Verifier to Assessing Complex Real-World Tool-Use Trajectories (2026.findings-acl)

Challenge:	Automated Alignment (ALM) is a set of algorithms designed to align Large Language Models (LLMs) with human intentions and values while minimizing manual intervention.
Approach:	They propose an open-source toolkit that integrates mainstream automated algorithms through a consistent interface and an accessible workflow supporting one-click execution for prompt synthesis and automatic alignment signal construction.
Outcome:	The proposed framework enables easy reproduction of existing results through extensive benchmarks and facilitates the development of novel approaches via modular components.

Copied to clipboard

Linzhuang Sun, Mingyang Chen, Hao Liang, Tianpeng Li, Zhou Yijie, Chenzheng Zhu, Tianyu Guo, Huanyao Zhang, Jingxuan Wei, Bihui Yu, Fan Yang, Wentao Zhang

Challenge:	Existing methods for training effective AI agents often resort to synthetic data generation.
Approach:	They propose a plug-and-play framework for data quality control in tool-use scenarios . they construct a tool-verify dataset and release a benchmark to assess its performance .
Outcome:	The proposed framework surpasses Qwen2.5-72B-Instruct on Tool-V-Bench and the previous APIGen-MT dataset.

Heuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A Survey (2025.findings-acl)

Copied to clipboard

Wendi Cui, Jiaxin Zhang, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika Das, Bradley A. Malin, Sricharan Kumar

History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling (2023.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have led to remarkable achievements across a variety of NLP tasks.
Approach:	They propose a taxonomy of automatic prompt optimization methods that explore and improve prompts with minimal human oversight.
Outcome:	The proposed methods can explore and improve prompts with minimal human oversight.

Copied to clipboard

Hao Sun, Yang Li, Liwei Deng, Bowen Li, Binyuan Hui, Binhua Li, Yunshi Lan, Yan Zhang, Yongbin Li

A Neural Question Answering Model Based on Semi-Structured Tables (C18-1)

Challenge:	Existing methods for conversational KBQA assume the independence of utterances and model them in isolation.
Approach:	They propose a History Semantic Graph Enhanced KBQA model that models long-range semantic dependencies in conversation history while maintaining low computational cost.
Outcome:	The proposed model outperforms baselines on a widely used question type dataset.

Copied to clipboard

Hao Wang, Xiaodong Zhang, Shuming Ma, Xu Sun, Houfeng Wang, Mengxiang Wang

MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions (2023.acl-long)

Challenge:	Existing question answering systems rely on raw text and structured knowledge graphs.
Approach:	They build an end-to-end system to answer multiple choice questions with semi-structured tables as its knowledge.
Outcome:	The proposed system improves on the state-of-the-art question answering system with tabMCQ dataset.

Copied to clipboard

Hao Sun, Zhexin Zhang, Fei Mi, Yasheng Wang, Wei Liu, Jianwei Cui, Bin Wang, Qun Liu, Minlie Huang

Probabilistic Graph Reasoning for Natural Proof Generation (2021.findings-acl)

Challenge:	A moral dialogue system aligned with users’ values could enhance conversation engagement and user connections.
Approach:	They propose a framework to train and evaluate moral dialogue systems based on communication mechanisms of morality and a method to construct moral discussions between simulated users and the dialogue system.
Outcome:	The proposed framework can train and evaluate moral dialogue systems based on simulated users and their values .

Copied to clipboard

Changzhi Sun, Xinbo Zhang, Jiangjie Chen, Chun Gan, Yuanbin Wu, Jiaze Chen, Hao Zhou, Lei Li

Structured Data in NLP

Challenge:	Existing approaches to reasoning over formal representations do not explicitly consider inter-dependency between answers and proofs.
Approach:	They propose a novel approach for joint answer prediction and proof generation using an induced graphical model.
Outcome:	The proposed approach achieves 10%-30% improvement on QA accuracy in evaluations under diverse conditions.

Token-level Proximal Policy Optimization for Query Generation (2025.emnlp-main)

Copied to clipboard

Yichen Ouyang, Lu Wang, Fangkai Yang, Pu Zhao, Chenghua Huang, Jianfeng Liu, Bochen Pang, Yaming Yang, Yuefeng Zhan, Hao Sun, Qingwei Lin, Saravan Rajmohan, Weiwei Deng, Dongmei Zhang, Feng Sun

Text Generation

Challenge:	Large Language Models (LLMs) have improved search engines and recommendation systems through their text understanding capabilities.
Approach:	They propose a token-level proximal policy optimization approach to empower LLMs to perform better in query generation through fine-tuning.
Outcome:	The proposed approach outperforms existing LLMs on an open-source and industrial dataset.

Beyond Output Confidence: Epistemic-Aware Hallucination Detection with Answer-Level Signals (2026.findings-acl)

Copied to clipboard

Jieran Li, Xiuyuan Hu, Yang Zhao, Dongbiao Sun, Hao Zhang

End-to-End Learnable Psychiatric Scale Guided Risky Post Screening for Depression Detection on Social Media (2025.emnlp-main)

Challenge:	Existing methods for detecting hallucinations are confounded by epistemic uncertainty and cannot distinguish genuine uncertainty from fabricated content.
Approach:	They propose a model-agnostic metric that captures epistemic boundary deviations by measuring answer-level stability across multiple stochastic forward passes.
Outcome:	The proposed metric outperforms strong uncertainty-only baselines and can be used to detect hallucinations on open-domain question answering, dialogue generation, and code completion.

Copied to clipboard

Bichen Wang, Yuzhe Zi, Yixin Sun, Hao Yang, Yanyan Zhao, Bing Qin

Challenge:	Existing methods to detect depression from social media posting history are limited by frozen screening models and lack of learning.
Approach:	They propose to use a frozen screening model to train a risky post detection model with psychiatric scales to enable a learnable end-to-end learning process.
Outcome:	The proposed model outperforms several strong baseline methods and qualitative analysis confirms that it better captures users’ mental states than others.

Copied to clipboard

Weize Chen, Hao Zhu, Xu Han, Zhiyuan Liu, Maosong Sun

Retrieved In-Context Principles from Previous Mistakes (2024.emnlp-main)

Challenge:	a conceptually simple and effective method to quantify the similarity between relations is presented . identifying relations is a crucial problem for several information extraction tasks.
Approach:	They propose a method to quantify the similarity between relations in knowledge bases . they use a neural network to parameterize conditional probability distributions over entity pairs .
Outcome:	The proposed method significantly correlates with human judgments, the authors show . it could be incorporated into negative sampling and softmax classification to alleviate these mistakes.

Copied to clipboard

Hao Sun, Yong Jiang, Bo Wang, Yingyan Hou, Yan Zhang, Pengjun Xie, Fei Huang

Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning (2023.emnlp-main)

Challenge:	Recent advances in in-context learning (ICL) have limited customization and inadequate error coverage.
Approach:	They propose a method to retrieve in-context principles from mistakes to improve model performance.
Outcome:	The proposed framework enhances model performance when applied to various prompting strategies.

Copied to clipboard

Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)

Challenge:	In-context learning (ICL) is a promising capability for large language models (LLMs) but its underlying mechanism remains unexplored.
Approach:	They propose a demonstration compression technique to expedite inference and an analysis framework for diagnosing ICL errors in GPT2-XL.
Outcome:	The proposed method improves ICL performance and expedites inference.

Copied to clipboard

Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu

Better Zero-Shot Reasoning with Role-Play Prompting (2024.naacl-long)

Challenge:	Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent.
Approach:	They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs.
Outcome:	The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models.

Copied to clipboard

Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xin Zhou, Enzhi Wang, Xiaohang Dong

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides (2025.emnlp-main)

Challenge:	Recent years have witnessed a paradigm shift in natural language processing, driven by large language models such as GPT-3, PaLM, and Llama.
Approach:	They propose a strategy for role-play prompting and assess its performance under the zero-shot setting.
Outcome:	The proposed method outperforms the standard zero-shot prompting approach across 12 reasoning benchmarks.

Copied to clipboard

Hao Zheng, Xinyan Guan, Hao Kong, Wenkai Zhang, Jia Zheng, Weixiang Zhou, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

CAPC-CG: A Large-Scale, Expert-Directed LLM-Annotated Corpus of Adaptive Policy Communication in China (2026.acl-long)

Challenge:	Existing methods for generating presentations from documents focus on improving and evaluating content quality in isolation, overlooking visual appeal and structural coherence.
Approach:	They propose an edit-based presentation generation system that analyzes and iterates on slides to create new slides.
Outcome:	The proposed presentation generation tool outperforms existing methods in three dimensions . it analyzes slides, iterates and generates edit actions based on selected slides .

Copied to clipboard

Bolun Sun, Charles Chang, Yuen Yuen Ang, Ruotong Mu, Yuchen Xu, Zhengxin Zhang, Pingxu Hao

Challenge:	Adaptive policy communication is a theory of governance in large, decentralized organizations where leaders exercise influence rather than precise control by combining clear and ambiguous instructions to calibrate discipline and flexibility.
Approach:	They propose an expert-directed annotation method that integrates codebook design, structured training, a two-step workflow, and LLM-based scaling.
Outcome:	The proposed method achieves a Fleiss’ kappa of 0.86 on directive labels, indicating high reliability.

Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models (2024.acl-long)

Copied to clipboard

Longze Chen, Ziqiang Liu, Wanwei He, Yinhe Zheng, Hao Sun, Yunshui Li, Run Luo, Min Yang

Parameter-Efficient Conversational Recommender System as a Language Processing Task (2024.eacl-long)

Challenge:	Long-context modeling capabilities are important for large language models (LLMs) however, training LLMs with long context windows is insufficient since some samples do not exhibit strong semantic dependencies across long contexts.
Approach:	They propose a data mining framework ProLong that assigns each training sample with a long dependency score and ranks and filters them according to their results.
Outcome:	The proposed framework can rank and filter training samples that exhibit more powerful long-context modeling abilities.

Copied to clipboard

Mathieu Ravaut, Hao Zhang, Lu Xu, Aixin Sun, Yong Liu

Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning (2025.acl-long)

Challenge:	Existing methods to recommend items are categorized into attribute-based and generation-based methods.
Approach:	They propose to represent items in natural language and formulate a conversational recommender system that can be optimized in a single stage without relying on non-textual metadata.
Outcome:	The proposed model can be optimized in a single stage, without relying on non-textual metadata such as a knowledge graph.

Copied to clipboard

Hui Liu, Wenya Wang, Hao Sun, Chris Xing Tian, Chenqi Kong, Xin Dong, Haoliang Li

Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation (2026.findings-acl)

Challenge:	Recent learning-based demonstration selection methods have proven beneficial to in-context learning (ICL) by choosing more useful exemplars.
Approach:	They propose two methods to capture task-agnostic similarities between input and output of LLMs.
Outcome:	The proposed methods integrate task-agnostic similarities of different levels between input and output of exemplars and test cases to eliminate costly data collection.

Copied to clipboard

Shuoyang Sun, Jiaxin Hong, Yv Zhang, Kuofeng Gao, Hao Fang, Fan Mo, Bin Chen, Shu-Tao Xia

Estimating Soft Labels for Out-of-Domain Intent Detection (2022.emnlp-main)

Challenge:	3D Vision-Language Models (VLMs) are critical cognitive backbone for spatial intelligence, but their reliance on autoregressive decoding introduces a fundamental vulnerability regarding inference efficiency.
Approach:	They propose a framework that triggers computational and economic exhaustion in 3D-VLMs by injecting imperceptible noise that forces the model into a state of pathological verbosity.
Outcome:	The proposed framework amplifies output length and energy consumption by up to 6.45, demonstrating a potent capability to drain system resources.

Copied to clipboard

Hao Lang, Yinhe Zheng, Jian Sun, Fei Huang, Luo Si, Yongbin Li

Sentiment Analysis

Challenge:	Existing methods to detect out-of-dominance (OOD) intents are limited by the lack of OOD samples.
Approach:	They propose an adaptive soft pseudo labeling method that can estimate soft labels for pseudo OOD samples when training OOD detectors.
Outcome:	The proposed method outperforms competing methods on three benchmark datasets and consistently outperformed previous methods.

One2Set + Large Language Model: Best Partners for Keyphrase Generation (2024.emnlp-main)

Copied to clipboard

Liangying Shao, Liang Zhang, Minlong Peng, Guoqi Ma, Hao Yue, Mingming Sun, Jinsong Su

Unveiling the Implicit Toxicity in Large Language Models (2023.emnlp-main)

Challenge:	Existing selection methods make redundant selections, causing poor recall and accuracy.
Approach:	They propose a framework to generate keyphrases from a one2set-based model and an LLM as selector.
Outcome:	The proposed framework surpasses state-of-the-art models in absent keyphrase prediction.

Copied to clipboard

Jiaxin Wen, Pei Ke, Hao Sun, Zhexin Zhang, Chengfei Li, Jinfeng Bai, Minlie Huang

MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter (2024.acl-long)

Challenge:	Recent studies focus on probing toxic outputs that can be easily detected with existing toxicity classifiers, but LLMs can generate diverse implicit toxic output that are difficult to detect via simply zero-shot prompting.
Approach:	They propose a reinforcement learning based attacking method to induce the implicit toxic outputs in large language models by fine-tuning toxicity classifiers.
Outcome:	The proposed method generates implicit toxic outputs that are difficult to detect via zero-shot prompting on five widely-adopted toxicity classifiers.

Copied to clipboard

Jitai Hao, Weiwei Sun, Xin Xin, Qi Meng, Zhumin Chen, Pengjie Ren, Zhaochun Ren

AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)

Challenge:	Parameter-Efficient Fine-tuning (PEFT) methods are limited on knowledge-intensive tasks due to the limited number of trainable parameters.
Approach:	They propose a mechanism that fine-tunes Large Language Models with larger adapters . they store and update the parameters of larger adapter adapters on the CPU .
Outcome:	The proposed method achieves comparable results to those obtained with larger memory capacities over the limited bandwidth of PCI Express (PCIe).

Copied to clipboard

Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu

SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization (2025.acl-long)

Challenge:	Significant concerns emerge when addressing cultural sensitivity and local values.
Approach:	They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models.
Outcome:	The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks.

Copied to clipboard

Wendi Cui, Jiaxin Zhang, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika Das, Bradley A. Malin, Sricharan Kumar

Advancing Sequential Numerical Prediction in Autoregressive Models (2025.acl-short)

Challenge:	Existing approaches separate the optimization of prompt instructions and in-context learning examples, leading to incohesive, suboptimal results.
Approach:	They propose a framework that refines both prompt instructions and in-context learning examples.
Outcome:	The proposed framework outperforms state-of-the-art prompt optimization methods on 35 benchmark tasks.

Copied to clipboard

Xiang Fei, Jinghui Lu, Qi Sun, Hao Feng, Yanjie Wang, Wei Shi, An-Lan Wang, Jingqun Tang, Can Huang

Challenge:	Autoregressive models are the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences.
Approach:	They propose a novel approach to entropy loss by extending the Earth Mover’s Distance to preserve ordinal relationships between numerical values and sequence-level to penalize the overall discrepancy between predicted and actual sequences.
Outcome:	Extensive experiments show that NTIL improves numerical prediction and integrates effectively with LLMs/MLLMs.

SciAgent: Tool-augmented Language Models for Scientific Reasoning (2024.emnlp-main)

Copied to clipboard

Yubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu, Shuohang Wang, Liangming Pan, Yujiu Yang, Yixin Cao, Aixin Sun

Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking (2024.findings-acl)

Challenge:	SciAgent surpasses other LLMs with the comparable size by more than 8.0% in absolute accuracy.
Approach:	They propose a tool-augmented scientific reasoning setting that supplements LLMs with scalable toolsets and builds a benchmark to evaluate LLM’s abilities with tool assistance.
Outcome:	The proposed setting augments LLMs with scalable toolsets and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user.

Copied to clipboard

Ming Dong, Yujing Chen, Miao Zhang, Hao Sun, Tingting He

ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages (2023.findings-acl)

Challenge:	Chinese Spell Checking (CSC) is a widely used technology for speech to text and optical character recognition.
Approach:	They propose to use Chinese rich semantic information to introduce large language models as the foundation model.
Outcome:	The proposed framework performs better on few-shot CSC task than existing methods.

Copied to clipboard

Yekun Chai, Shuohuan Wang, Chao Pang, Yu Sun, Hao Tian, Hua Wu

Multilinguality

Challenge:	ERNIE-Code is a unified pre-trained language model for 116 NLs and 6 PLs.
Approach:	They propose a unified pre-trained language model for 116 NLs and 6 PLs . they employ span-corruption language modeling that learns patterns from monolingual NL or PL .
Outcome:	The proposed model outperforms previous multilingual models for NL or NL across end tasks.

WebDP: Understanding Discourse Structures in Semi-Structured Web Documents (2023.findings-acl)

Copied to clipboard

Peilin Liu, Hongyu Lin, Meng Liao, Hao Xiang, Xianpei Han, Le Sun

Language Modeling with Sparse Product of Sememe Experts (D18-1)

Challenge:	Web documents are one of the most primary and biggest data resources in current era, and understanding their discourse structure will benefit various downstream document processing applications.
Approach:	They propose a web document discourse structure representation schema by extending classical discourse theories and adding special features to well represent discourse characteristics of web documents.
Outcome:	The proposed task is feasible but challenging for current models.

Copied to clipboard

Yihong Gu, Jun Yan, Hao Zhu, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin

MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification (2025.acl-long)

Challenge:	Existing language modeling methods rely on large-scale text data to learn the sequential patterns of words.
Approach:	They propose to use sememes to represent the implicit semantics behind words for language modeling . they propose to employ sememe-driven language models to fine-grained semem-level semantics .
Outcome:	Experiments on language modeling and the downstream application of headline generation show the effectiveness of SDLM.

Copied to clipboard

Linzhuang Sun, Hao Liang, Jingxuan Wei, Bihui Yu, Tianpeng Li, Fan Yang, Zenan Zhou, Wentao Zhang

UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (2023.emnlp-main)

Challenge:	MM-Verifier and MM Reasoner are a powerful multimodal reasoning model . large language models (LLMs) have demonstrated exceptional performance across tasks spanning myriad domains.
Approach:	They propose a method which combines tree search and verification to generate high-quality chain-of-thought data.
Outcome:	The proposed method outperforms all larger models on the MathCheck, MathVista, and MathVerse benchmarks.

Copied to clipboard

Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, Qi Zhang

Reinforced Dynamic Reasoning for Conversational Question Generation (P19-1)

Challenge:	Large Language Models (LLMs) have impressive capabilities but need for task-specific prompt engineering can hinder their generalization.
Approach:	They propose a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input.
Outcome:	The proposed model is universally applicable across tasks and models . it mitigates hallucination problem in chatGPT, and it improves even the strongest LLMs.

Copied to clipboard

Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, Huan Sun

Put It Back: Entity Typing with Language Model Enhancement (D18-1)

Challenge:	Empirical results on the recently released CoQA dataset demonstrate the effectiveness of our method . large-scale highquality conversational question answering datasets such as CoQA and QuAC can help train models to answer sequential questions.
Approach:	They propose a task called Conversational Question Generation which generates a question based on a passage and a conversation history to generate the next question.
Outcome:	The proposed method is based on a question-answering style conversation dataset . it can be used to generate meaningful questions on QA and SQuAD datasets .

Copied to clipboard

Ji Xin, Hao Zhu, Xu Han, Zhiyuan Liu, Maosong Sun

A Multi-answer Multi-task Framework for Real-world Machine Reading Comprehension (D18-1)

Challenge:	Existing Entity typing models suffer from noisy labels due to distant supervision .
Approach:	They propose to enhance existing entity typing models with language model enhancement to measure compatibility between context sentences and labels.
Outcome:	The proposed model significantly outperforms the state-of-the-art model on benchmark datasets and is available on github.

Copied to clipboard

Jiahua Liu, Wan Wei, Maosong Sun, Hao Chen, Yantao Du, Dekang Lin

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)

Challenge:	Existing models of machine reading comprehension (MRC) are based on cloze style questions or crowdworkers given a short passage from well-edited sources.
Approach:	They propose a multi-answer multi-task framework that uses multiple reference answers for multiple questions.
Outcome:	The proposed model increases the ROUGE-L score on the DuReader dataset from 44.18, the previous state-of-the-art, to 51.09 .

Copied to clipboard

Yi Sun, Han Wang, Jiaqiang Li, Jiacheng Liu, Xiangyu Li, Hao Wen, Yizhen Yuan, Huiwen Zheng, Yan Liang, Yuanchun Li, Yunxin Liu

Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints.
Approach:	They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking .
Outcome:	The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints.

Copied to clipboard

Chenming Tang, Zhixiang Wang, Hao Sun, Yunfang Wu

Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval (2025.findings-emnlp)

Challenge:	In-context learning has improved performance of large language models, but descriptive instructions are still under-explored.
Approach:	They propose an ensemble prompt framework to describe selection criteria of multiple in-context examples. preliminary experiments on machine translation confirm that this framework boosts ICL performance.
Outcome:	The proposed framework improves on commonsense, math, logical reasoning and hallucination tasks with three LLMs.

Copied to clipboard

Haotong Bao, Jianjin Zhang, Qi Chen, Weihao Han, Zhengxin Zeng, Ruiheng Chang, Mingzheng Li, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

Improving Contextual Query Rewrite for Conversational AI Agents through User-preference Feedback Learning (2023.emnlp-industry)

Challenge:	Recent studies reveal query out-of-distribution issues degrading ANN performance . a distribution regularizer is introduced into the encoder training objective to encourage alignment between query and base embeddings.
Approach:	They introduce a distribution regularizer into the encoder training objective to encourage alignment between query and base embeddings.
Outcome:	The proposed method consistently improves retrieval performance across multiple datasets.

Copied to clipboard

Zhongkai Sun, Yingxue Zhou, Jie Hao, Xing Fan, Yanbin Lu, Chengyuan Ma, Wei Shen, Chenlei Guo

COLD: A Benchmark for Chinese Offensive Language Detection (2022.emnlp-main)

Challenge:	Contextual query rewriting (CQR) is a crucial component in Conversational AI agents, leveraging contextual information from previous user-agent conversations to improve comprehension of current user intent.
Approach:	They propose a framework to enhance the CQR model's capability in generating user preference-aligned rewrites.
Outcome:	The proposed framework improves the CQR model's ability to generate user preference-aligned rewrites.

Copied to clipboard

Jiawen Deng, Jingyan Zhou, Hao Sun, Chujie Zheng, Fei Mi, Helen Meng, Minlie Huang

Ethical NLP

Challenge:	Offensive language detection is crucial for maintaining a civilized social media platform and deploying pre-trained language models.
Approach:	They propose a benchmark benchmark for Chinese offensive language analysis including a Chinese Offensive Language Dataset and a baseline detector which is trained on the dataset.
Outcome:	The proposed benchmark contributes to Chinese offensive language detection which is challenging for existing resources.

ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding (2021.naacl-main)

Copied to clipboard

Dongling Xiao, Yu-Kun Li, Han Zhang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement (2026.acl-long)

Challenge:	Existing methods to model coarse-grained linguistic information do not integrate coarse-gram information into pre-training.
Approach:	They propose an explicitly n-gram masking method to enhance integration of coarse-grained linguistic information into pre-training.
Outcome:	The proposed method outperforms existing models on English and Chinese text corpora and fine-tunes on 19 downstream tasks.

Copied to clipboard

Hao Li, Yizheng Sun, Viktor Schlegel, Kailai Yang, Riza Batista-Navarro, Goran Nenadic

Text Generation

Challenge:	Existing approaches to argument summarization rely on single-pass generation, offering limited support for factual correction or structural refinement.
Approach:	They propose a large language diffusion framework that iteratively improves argument summarization by sufficiency-guided remasking and regeneration.
Outcome:	Empirical results show that Arg-LLaDA surpasses state-of-the-art baselines in 7 out of 10 evaluation metrics.

PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support (2021.findings-acl)

Copied to clipboard

Hao Sun, Zhenru Lin, Chujie Zheng, Siyang Liu, Minlie Huang

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models (2025.naacl-long)

Challenge:	Existing research on text-based mental health counseling is limited due to the lack of relevant corpora in Chinese language.
Approach:	They propose a Chinese dataset of psychological health support in the form of question and answer pair that is crawled from a mental health service platform and contains 22K questions and 56K long and wellstructured answers.
Outcome:	The proposed dataset contains 22K questions and 56K long and wellstructured answers.

Copied to clipboard

Ying Nie, Binwei Yan, Tianyu Guo, Hao Liu, Haoyu Wang, Wei He, Binfan Zheng, Weihao Wang, Qiang Li, Weijian Sun, Yunhe Wang, Dacheng Tao

TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation (2026.acl-long)

Challenge:	Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored.
Approach:	They propose a benchmark to assess the financial knowledge of large language models (LLMs) in China.
Outcome:	The proposed benchmark is the most comprehensive evaluation benchmark to date for LLMs in finance.

Copied to clipboard

Zhihao Gong, Zeyu Sun, Dong Huang, Qingyuan Liang, Jie M. Zhang, Dan Hao

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have improved the functional correctness of code translation, but execution efficiency remains overlooked.
Approach:	They propose a benchmark to explicitly assess execution efficiency in LLM-translated code.
Outcome:	The proposed benchmark identifies that execution efficiency is an essential dimension of code translation . the results highlight that correctness and efficiency are often misaligned .

Copied to clipboard

Xue Tan, Hao Luan, Mingyu Luo, Xiaoyan Sun, Ping Chen, Jun Dai

Learning from Context or Names? An Empirical Study on Neural Relation Extraction (2020.emnlp-main)

Challenge:	Retrieval-Augmented Generation (RAG) enriches the input to LLMs by retrieving information from the relevant knowledge database.
Approach:	They propose to use a knowledge database to enrich the input of LLMs by retrieving information from the relevant knowledge database.
Outcome:	The proposed approach can achieve 98% true positive rate while maintaining a false positive rate close to 1%.

Copied to clipboard

Hao Peng, Tianyu Gao, Xu Han, Yankai Lin, Peng Li, Zhiyuan Liu, Maosong Sun, Jie Zhou

Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval (2025.acl-long)

Challenge:	Existing datasets may leak shallow heuristics via entity mentions, thus contributing to the high performance on RE benchmarks.
Approach:	They propose an entity-masked contrastive framework for relation extraction to gain a deeper understanding on textual context and type information while avoiding rote memorization of entities.
Outcome:	The proposed framework improves the effectiveness and robustness of neural models in different RE scenarios.

Copied to clipboard

Hao Sun, Yingyan Hou, Jiayan Guo, Bo Wang, Chunyu Yang, Jinsong Ni, Yan Zhang

Inverse Reinforcement Learning Meets Large Language Model Alignment (2025.acl-tutorials)

Challenge:	Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities.
Approach:	They propose a visual-textual embedding framework that integrates textual and visual features for robust document representation.
Outcome:	The proposed visual-textual embedding framework surpasses existing methods while preserving semantic fidelity.

Copied to clipboard

Mihaela van der Schaar, Hao Sun

LMDX: Language Model-based Document Information Extraction and Localization (2024.findings-acl)

Challenge:	This tutorial will provide a comprehensive review of recent advances in LLM alignment . it will highlight the necessity of constructing neural reward models from human data .
Approach:	This tutorial will provide a comprehensive review of recent advances in LLM alignment through the lens of inverse reinforcement learning.
Outcome:	This tutorial will provide a comprehensive review of recent advances in LLM alignment through the lens of inverse reinforcement learning (IRL).

Copied to clipboard

Vincent Perot, Kai Kang, Florian Luisier, Guolong Su, Xiaoyu Sun, Ramya Sree Boppana, Zilong Wang, Zifeng Wang, Jiaqi Mu, Hao Zhang, Chen-Yu Lee, Nan Hua

Allies: Prompting Large Language Model with Beam Search (2023.findings-emnlp)

Challenge:	Large Language Models have revolutionized Natural Language Processing but their application in extracting information from visually rich documents has not been successful.
Approach:	They propose a language model-based document information extraction and localization methodology to reframe the document information extract task for a LLM.
Outcome:	The proposed method enables extraction of singular, repeated, and hierarchical entities with and without training data.

Copied to clipboard

Hao Sun, Xiao Liu, Yeyun Gong, Yan Zhang, Daxin Jiang, Linjun Yang, Nan Duan

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

Challenge:	Existing methods to build LLMs with stacking are limited by their information coverage and low fault tolerance.
Approach:	They propose a method that leverages large language models to iteratively generate new queries from an input query.
Outcome:	The proposed method outperforms baselines on open-domain question answering benchmarks.

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

Speak No Evil, Just Prompt: Low-resource Multilingual Toxic Speech Detection with Audio Language Model (2026.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

Mingzi Zuo, Lei Zhang, Hailiang Sun, Shengzhi Huo, Changyu Dong, Xin Wang, Bo Wang, Hao Liu

ENPAR:Enhancing Entity and Entity Pair Representations for Joint Entity Relation Extraction (2021.eacl-main)

Challenge:	Existing methods for toxic speech detection rely on high-resource languages and lack acoustic cues.
Approach:	They propose a prompt-based adaptation framework that performs end-to-end toxicity detection without ASR.
Outcome:	The proposed framework achieves a micro-averaged ROC-AUC of 98.07% on polySpeechTox . it is based on a frozen audio language model and can perform end-to-end toxicity detection without ASR .

Copied to clipboard

Yijun Wang, Changzhi Sun, Yuanbin Wu, Hao Zhou, Lei Li, Junchi Yan

NSP-BERT: A Prompt-based Few-Shot Learner through an Original Pre-training Task —— Next Sentence Prediction (2022.coling-1)

Challenge:	Existing methods for joint entity relation extraction use multitask learning frameworks, but annotations for additional tasks are hard to obtain.
Approach:	They propose a pre-training method to improve the joint extraction performance with just extra entity annotations.
Outcome:	The proposed method outperforms existing methods on ACE05, SciERC, and NYT and outperformed BERT on other tasks.

Copied to clipboard

Yi Sun, Yu Zheng, Chao Hao, Hangping Qiu

MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents (2026.acl-long)

Challenge:	Recent studies have shown that using prompts to utilize language models to perform downstream tasks is more effective than using token-level methods such as PET.
Approach:	They propose to use a BERT original pre-training task abandoned by RoBERTa and other models to construct a sentence-level prompt-based method that does not need to fix the length of the prompt or the position to be predicted.
Outcome:	The proposed method performs better than PET and EFL on a BERT pre-training task and is comparable to other prompt-based methods.

Copied to clipboard

Hao Sun, Yu Song, Teng Shiyu, Ziwei Niu, Yen-wei Chen

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation (2026.findings-acl)

Challenge:	a recent study shows that VLA models suffer from temporal myopia that discards historical dynamics and reasoning gaps between high-level instructions and low-level motor commands.
Approach:	They propose a framework to address temporal myopia and autoregressive scalar decoding in VLAs . they propose two memory hubs that compress long-term scene evolution and short-term motion trends .
Outcome:	The proposed framework achieves state-of-the-art performance and exhibiting emergent error recovery capabilities.

Copied to clipboard

Tianyu Liu, Qitan Lv, Hao Li, Xing Gao, Xiao Sun, Xiaoyan Sun

Imitation Learning for Non-Autoregressive Neural Machine Translation (P19-1)

Challenge:	Speculative decoding (SD) is a promising technique for LLM inference acceleration.
Approach:	They propose a method to generate draft tokens in a retrieval-based manner to reduce drafting overhead and improve inference speed.
Outcome:	Extensive tests show that LogitSpec can achieve 2.61 speedup and 3.28 mean accepted tokens per decoding step.

Copied to clipboard

Bingzhen Wei, Mingxuan Wang, Hao Zhou, Junyang Lin, Xu Sun

Machine Translation

Challenge:	Existing non-autoregressive translation models lack parallel decoding, which is a bottleneck for NMT decoding.
Approach:	They propose a framework for non-autoregressive machine translation that emulates the autoregressive model by sampling sentence length in parallel.
Outcome:	The proposed model achieves 31.85 BLEU on WMT16 RoEn and 30.68 BLUE on IWSLT16 EnDe on the IWSLD16, WMT14 and WMT15 datasets.

JumpCoder: Go Beyond Autoregressive Coder via Online Modification (2024.acl-long)

Copied to clipboard

Mouxiang Chen, Hao Tian, Zhongxin Liu, Xiaoxue Ren, Jianling Sun

Challenge:	Existing code large language models lack reversibility and autoregressive sequential generation is incapable of correcting previous missing statements as humans do.
Approach:	They propose a model-agnostic framework that enables human-like online modification and non-sequential generation to augment code large language models.
Outcome:	The proposed framework enables human-like modification and non-sequential generation to augment code large language models.

Multimodal Machine Translation with Text-Image In-depth Questioning (2025.findings-acl)

Copied to clipboard

Yue Gao, Jing Zhao, Shiliang Sun, Xiaosong Qiao, Tengfei Song, Hao Yang