Papers by Qi Peng

RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction (2023.acl-long)

Challenge:	Recent advances in large language models (LLMs) have catalyzed the development of autonomous agents capable of executing complex, multi-turn tasks.
Approach:	They propose a framework for agentic reinforcement learning that integrates turn-level tree search with tree search to address key challenges.
Outcome:	The proposed framework addresses key challenges: limited exploration diversity, sparse credit assignment, and misaligned policy optimization.

Copied to clipboard

Jun Zhao, WenYu Zhan, Xin Zhao, Qi Zhang, Tao Gui, Zhongyu Wei, Junzhe Wang, Minlong Peng, Mingming Sun

Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context (P18-1)

Challenge:	Existing methods for zero-shot relation extraction lack explicit modeling of matching pattern . et al. (2018) show that our method achieves higher matching accuracy and faster inference speed .
Approach:	They propose a fine-grained semantic matching method tailored for zero-shot relation extraction . they decompose sentence-level similarity score into entity matching score and context matching score .
Outcome:	The proposed method achieves higher matching accuracy and faster inference speed than state-of-the-art methods.

Copied to clipboard

Urvashi Khandelwal, He He, Peng Qi, Dan Jurafsky

SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval (2026.findings-acl)

Challenge:	Recent studies have shed light on the information encoded by long-term memory networks.
Approach:	They propose to use a neural caching model to model the role of context in an LSTM LM . they analyze the increase in perplexity when prior context words are shuffled, replaced, or dropped .
Outcome:	The proposed model is highly sensitive to the order of words within the most recent sentence, but ignores word order in the long-range context, suggesting the distant past is modeled only as a rough semantic field or topic.

Copied to clipboard

Xin Xie, Dongyun Xue, Wuguannan Yao, Mingxiao Feng, Wengang Zhou, Xiang Qi, Houqiang Li, Peng Zhang

FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)

Challenge:	a new framework casts LLM planning as non-parametric retrieval, but high latency of inference-time search and supervised fine-tuning are limitations.
Approach:	They propose a framework that casts LLM planning as non-parametric retrieval . they leverage Monte Carlo Tree Search to explore the solution space .
Outcome:	Empirical results show that SGA-MCTS can match the performance of SOTA systems without task-specific fine-tuning.

Copied to clipboard

Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Alexander Fabbri, Wojciech Kryscinski, Semih Yavuz, Ye Liu, Xi Lin, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Rex Ying, Arman Cohan, Dragomir Radev

Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training (2025.acl-long)

Challenge:	Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity.
Approach:	They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models.
Outcome:	The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models.

Copied to clipboard

Zheheng Luo, Xin Zhang, Xiao Liu, Haoling Li, Yeyun Gong, Qi Chen, Peng Cheng

TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs (2026.acl-long)

Challenge:	Existing methods to optimise pretraining performance have not addressed the complexities of domain-adaptive continual pretraining.
Approach:	They propose a framework that dynamically assesses learning velocity and adjusts data proportions accordingly, favouring slower learning domains while de-emphasising faster learning ones.
Outcome:	The proposed framework achieves performance gains in math and code reasoning tasks and command-line generation benchmarks.

Copied to clipboard

Ziyi Wang, Chen Zhang, Wenjun Peng, Qi Wu, Xinyu Wang

A Lexicon-Based Graph Neural Network for Chinese NER (D19-1)

Challenge:	Existing explainability methods for large language models have been limited in capturing interaction-dependent belief dynamics and multi-agent reasoning.
Approach:	They propose a tri-view explainability framework that instruments sequential decision making with aligned artifacts.
Outcome:	The proposed framework enables analysis of explanation faithfulness, belief dynamics, and evaluator reliability, revealing systematic mismatches between what agents say, what they believe, and what they do.

Copied to clipboard

Tao Gui, Yicheng Zou, Qi Zhang, Minlong Peng, Jinlan Fu, Zhongyu Wei, Xuanjing Huang

C-World: A Computer Use Agent Environment Creator (2026.acl-long)

Challenge:	Chinese named entity recognition models are vulnerable to word ambiguities due to the lack of global semantics and chain structure.
Approach:	They propose a lexicon-based graph neural network with global semantics to solve word ambiguities in Chinese named entity recognition (NER) Lexicons are used to construct the graph and provide word-level features.
Outcome:	The proposed model improves on four NER datasets on Chinese characters, potential words, and the whole-sentence semantics.

Copied to clipboard

Ziqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang, Letian Peng, Fang Nan, Meshal Nayim, Tianhui Zhang, Rishika Mundada, Lianhui Qin, Biwei Huang, Kun Zhou

Challenge:	C-World enables users to build agent environments on demand.
Approach:	They propose a system that enables users to build agent environments on demand.
Outcome:	The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution.

Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis (2020.coling-main)

Copied to clipboard

Minlong Peng, Qi Zhang

Representation Learning

Challenge:	Cross-domain sentiment analysis is a hot topic in research and industry . domain-invariant representation learning (DIRL) is used to learn a feature representation across domains . but, when label distribution P(Y) shifts across domain, it degrades performance .
Approach:	They propose a domain-invariant representation learning framework to improve cross-domain sentiment analysis performance.
Outcome:	The proposed model is easy to transfer existing models to the proposed model.

Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors (2023.findings-acl)

Copied to clipboard

Peng Qi, Yuyang Zhao, Yufeng Shen, Wei Ji, Juan Cao, Tat-Seng Chua

Hybrid Hierarchical Retrieval for Open-Domain Question Answering (2023.findings-acl)

Challenge:	Existing frameworks for detecting fake news videos are limited . a new approach is proposed to integrate neighborhood information of new videos .
Approach:	They propose a framework for automatically detecting fake news videos . it integrates neighborhood relationship of new videos belonging to same event .
Outcome:	The proposed framework improves performance of existing detectors and graph aggregation and debunking rectification modules.

Copied to clipboard

Manoj Ghuhan Arivazhagan, Lan Liu, Peng Qi, Xinchi Chen, William Yang Wang, Zhiheng Huang

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)

Challenge:	Recent work shows that dense hierarchical retrieval (DHR) can outperform dense passage retrieval.
Approach:	They propose a framework that applies sparse, dense and a combination of them to document and passage retrieval.
Outcome:	The proposed framework can outperform dense hierarchical retrieval (DHR) and sparse retrievers (BM25) on open-domain question answering (ODQA) datasets with an average improvement of 4.69% on recall@100 over DHR.

Copied to clipboard

Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum

BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language? (2024.findings-emnlp)

Challenge:	Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window.
Approach:	They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window.
Outcome:	The proposed model scales to multi-million-token effective TTC without exceeding context limits.

Copied to clipboard

Zongmeng Zhang, Jinhua Zhu, Wengang Zhou, Xiang Qi, Peng Zhang, Houqiang Li

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)

Challenge:	Dense retrieval systems focus on optimizing text embedding space while overlooking Boolean logic in language.
Approach:	They propose a task to investigate whether retrieval systems can comprehend Boolean logic in language.
Outcome:	The proposed method is based on a benchmark dataset covering complex queries containing basic Boolean logic and corresponding annotated passages.

Copied to clipboard

Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen

WildReward: Learning Reward Models from In-the-Wild Human Interactions (2026.acl-long)

Challenge:	Existing approaches to program repair are based on correctness alone.
Approach:	They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits.
Outcome:	The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing.

Copied to clipboard

Hao Peng, Yunjia Qi, Xiaozhi Wang, Zijun Yao, Lei Hou, Juanzi Li

Challenge:	Prior work focused on collecting preference pairs, requiring substantial annotation efforts.
Approach:	They propose a pipeline to extract reliable human feedback from in-the-wild interactions . they propose to use WildChat as an interaction source to train the model .
Outcome:	The proposed model achieves comparable or even superior performance compared to conventional models with improved calibration and cross-sample consistency.

Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection (2026.acl-long)

Copied to clipboard

Cui Yakun, Peng Qi, Fushuo Huo, Hang Du, Weijie Shi, Juntao Dai, Zhenghao Zhu, Sirui Han

AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning (2026.findings-acl)

Challenge:	Existing video fake news detection benchmarks focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process.
Approach:	They propose a process-oriented video fake news detection benchmark that evaluates MLLMs' perception, understanding, and reasoning capabilities in VFND.
Outcome:	The proposed model achieves sota performance on video fake news detection tasks.

Copied to clipboard

Mengzhao Jia, Zhihan Zhang, Ignacio Cases, Zheyuan Liu, Meng Jiang, Peng Qi

HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (D18-1)

Challenge:	Multimodal large language models (MLLMs) have advanced from perception tasks to complex multi-step reasoning.
Approach:	They propose a framework that integrates reinforcement learning with verifiable rewards with process-level supervision through automatically collected rubric-based generative rewards.
Outcome:	The proposed framework achieves state-of-the-art performance on six multimodal reasoning benchmarks and significantly improves reasoning faithfulness in dedicated evaluations.

Copied to clipboard

Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, Christopher D. Manning

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Challenge:	Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers.
Approach:	They propose a new dataset with 113k Wikipedia-based question-answer pairs with four key features: (1) the questions require finding and reasoning over multiple supporting documents to answer; (2) the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; (3) the questions provide sentence-level supporting facts required for reasoning; and (4) a type of factoid comparison questions to test QA systems’ ability to extract relevant facts and perform necessary comparison.
Outcome:	The proposed dataset has 113k Wikipedia-based question-answer pairs and four key features that make it challenging for the latest QA systems.

Copied to clipboard

Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang

LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)

Challenge:	Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach:	They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome:	The proposed framework improves instruction following performance without compromising general performance.

Copied to clipboard

Ming Zhang, Yujiong Shen, Jingyi Deng, Yuhui Wang, Huayu Sha, Kexin Tan, Qiyuan Peng, Yue Zhang, Junzhe Wang, Shichun Liu, Yueyuan Huang, Jingqi Tong, Changhao Jiang, Yilong Wu, Zhihao Zhang, Mingqi Wu, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following (2025.emnlp-main)

Challenge:	Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting.
Approach:	LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data .
Outcome:	LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm .

Copied to clipboard

Hao Peng, Yunjia Qi, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li

Challenge:	Best practices for RL in instruction following remain underexplored.
Approach:	They propose a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model.
Outcome:	The proposed method achieves state-of-the-art performance among models of comparable size and generalizes well to unseen constraints.

Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification (2021.naacl-main)

Copied to clipboard

Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He, Bowen Zhou

Sentiment Analysis

Challenge:	Recent work on aspect-level sentiment classification has shown that syntactic information is effective in capturing long-range syntaktic relations that are obscure from the surface form.
Approach:	They propose a graph ensemble technique that integrates syntactic structures with GNNs to better leverage syntaktic information in the face of parsing errors.
Outcome:	The proposed model outperforms models with single dependency tree and beats other models without adding model parameters.

Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging (D18-1)

Copied to clipboard

Tao Gui, Qi Zhang, Jingjing Gong, Minlong Peng, Di Liang, Keyu Ding, Xuanjing Huang

Syntactic Text Processing

Challenge:	Existing POS tagging methods for Twitter use labeled newswire text . however, Twitter users tend to mimic formal media expressions and develop linguistically informal styles.
Approach:	They propose to use newswire text to learn POS tagging for Twitter while twitter users are developing linguistically informal styles.
Outcome:	The proposed method achieves better performance than state-of-the-art methods on three different datasets.

Answering Open-Domain Questions of Varying Reasoning Steps from Text (2021.emnlp-main)

Copied to clipboard

Peng Qi, Haejun Lee, Tg Sido, Christopher Manning

RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering (2023.findings-acl)

Challenge:	a new benchmark is developed to answer open-domain questions from text . the system uses a single multi-task transformer model to perform all the necessary subtasks .
Approach:	They develop a unified system to answer directly from open-domain questions . they use a single multi-task transformer model to perform all the necessary subtasks .
Outcome:	The proposed system can answer open-domain questions on any text collection without prior knowledge of reasoning complexity.

Copied to clipboard

Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth

Hard Sample Aware Prompt-Tuning (2023.acl-long)

Challenge:	Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains.
Approach:	They propose a benchmark to evaluate ODQA's domain robustness using Wikipedia corpus . they annotate QA pairs in retrieval datasets with rigorous quality control .
Outcome:	The proposed benchmark improves model performance on annotated QA pairs in retrieval datasets with rigorous quality control.

Copied to clipboard

Yuanjian Xu, Qi An, Jiahuan Zhang, Peng Li, Zaiqing Nie

LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)

Challenge:	Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability.
Approach:	They propose a framework to distinguish informative hard samples from misleading ones in model training.
Outcome:	The proposed framework achieves new SOTA results on a series of NLP tasks pushing the SST-5 accuracy to 49.5% (1.1% point absolute improvement), QNLI accuracy to 74.6% (1.9% absolute improvement)

Copied to clipboard

Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu

Challenge:	Large language model (LLM) routing assigns each query to the best suitable model from an ensemble.
Approach:	They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation .
Outcome:	The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing.

Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations (2020.findings-emnlp)

Copied to clipboard

Peng Qi, Yuhao Zhang, Christopher D. Manning

Toward Recognizing More Entity Types in NER: An Efficient Implementation using Only Entity Lexicons (2020.findings-emnlp)

Challenge:	Existing work on question generation assumes knowledge of what the answer might be . instead, questioner must reason pragmatically about how to acquire new information .
Approach:	They propose a question generation system that generates pragmatically relevant questions in information-asymmetric conversations.
Outcome:	The proposed questioner significantly improves the informativeness and specificity of questions generated over a baseline model as evaluated by metrics as well as humans.

Copied to clipboard

Minlong Peng, Ruotian Ma, Qi Zhang, Lujun Zhao, Mengxi Wei, Changlong Sun, Xuanjing Huang

TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection (2025.emnlp-main)

Challenge:	Existing named entity recognition systems require large scale labeled data to perform, while annotation of NER data is laborious and time-consuming.
Approach:	They propose to adjust an existing named entity recognition system to recognize entity types not defined in the system.
Outcome:	The proposed method can be quickly adjusted to a named entity recognition system.

Copied to clipboard

Zehong Yan, Peng Qi, Wynne Hsu, Mong-Li Lee

Connectivity Patterns are Task Embeddings (2023.findings-acl)

Challenge:	Existing methods focus on a single type of distortion and struggle to generalize to unseen scenarios.
Approach:	They propose a vision-language model that combines a question-aware visual amplifier module with a large-scale instruction dataset to support training.
Outcome:	The proposed model is able to generalize to multiple distortion types while requiring task-specific skills.

Copied to clipboard

Zhiheng Xi, Rui Zheng, Yuansen Zhang, Xuanjing Huang, Zhongyu Wei, Minlong Peng, Mingming Sun, Qi Zhang, Tao Gui

ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format (2023.emnlp-demo)

Challenge:	Existing methods for predicting inter-task transferability are sparse and task-specific.
Approach:	They propose a method that uses connectivity patterns of neurons as a unique identifier associated with a task.
Outcome:	The proposed method outperforms baselines in predicting inter-task transferability across data regimes and transfer settings while keeping high efficiency in computation and storage.

Copied to clipboard

Qi Zhu, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Shutong Feng, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gasic, Minlie Huang

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Challenge:	Existing tools for building TOD systems often lack a user-friendly interface . a toolkit with advanced, easily integrable modules is needed to bridge this gap .
Approach:	They propose a multifaceted dialogue system toolkit that integrates diverse datasets and models with a streamlined training process and in-depth evaluation tools.
Outcome:	The proposed toolkit combines RL and transfer learning to support the rapid development and evaluation of robust dialogue policies.

Copied to clipboard

Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song

ADELIE: Aligning Large Language Models on Information Extraction (2024.emnlp-main)

Challenge:	Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach:	They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome:	The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.

Copied to clipboard

Yunjia Qi, Hao Peng, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li

PragmatiCQA: A Dataset for Pragmatic Question Answering in Conversations (2023.findings-acl)

Challenge:	Large language models (LLMs) struggle to follow complex instructions of IE tasks due to not being aligned with humans.
Approach:	They propose an aligned large language moDEL that effectively solves various IE tasks including closed IE, open IE and on-demand IE.
Outcome:	The proposed model achieves state-of-the-art (SoTA) performance among open-source models.

Copied to clipboard

Peng Qi, Nina Du, Christopher Manning, Jing Huang

Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models (2026.findings-acl)

Challenge:	Mars? - PragmatiCQA
Approach:	Mars? - The Paper .
Outcome:	The proposed dataset features 6873 QA pairs that explores pragmatic reasoning in conversations over a diverse set of topics.

Copied to clipboard

Qi Cao, Takeshi Kojima, Andrew Gambardella, Helinyi Peng, Yutaka Matsuo, Yusuke Iwasawa

QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm (2025.findings-acl)

Challenge:	Existing methods for uncertainty quantification in large language models rely on indirect signals, such as entropy across sampled generations, which can be difficult to interpret and do not fully leverage the model’s ability to assess its own uncertainty.
Approach:	They propose a method that groups sampled generations into semantically distinct clusters and uses the probability assigned by the LLM to each option as a confidence estimate.
Outcome:	The proposed method outperforms baseline methods and achieves competitive performance with as few as two additional samples.

Copied to clipboard

Qirui Zhou, Shaohui Peng, Weiqiang Xiong, Haixin Chen, Yuanbo Wen, Haochen Li, Ling Li, Qi Guo, Yongwei Zhao, Ke Gao, Ruizhi Chen, Yanjun Wu, Zhao Chen, Yunji Chen

Programming Languages in NLP

Challenge:	Existing LLMs cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance.
Approach:	They propose an LLM-friendly Thinking Language (LLM-TL) that can decouple the generation of high-level optimization logic and low-level implementation on GPU and enhance LLMs’ understanding of attention operator.
Outcome:	The proposed method outshines existing LLMs on A100, RTX8000, and T4 GPUs, achieving a speed-up of up to 35.16.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization (2025.findings-emnlp)

Copied to clipboard

Zhensheng Jin, Xinze Li, Yifan Ji, Chunyi Peng, Zhenghao Liu, Qi Shi, Yukun Yan, Shuo Wang, Furong Peng, Ge Yu

Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning (P19-1)

Challenge:	Existing methods to train LLMs suffer from overthinking, leading to lengthy reasoning traces . Existing approaches to train large language models suffer from this problem .
Approach:	They propose a method to combine multiple reasoning chains for training LLMs . they use stepwise exploration and long-short switched sampling to evaluate reasoning paths .
Outcome:	The proposed method reduces reasoning lengths by approximately 30-50% . it also maintains or improves reasoning accuracy compared to baselines .

Copied to clipboard

Minlong Peng, Xiaoyu Xing, Qi Zhang, Jinlan Fu, Xuanjing Huang

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Challenge:	Empirical studies on four public NER datasets demonstrate the effectiveness of our proposed method.
Approach:	They propose a method to perform named entity recognition using unlabeled data and named entity dictionaries.
Outcome:	The proposed method can estimate task loss as if there is fully labeled data.

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

LCAN: A Label-Aware Contrastive Attention Network for Multi-Intent Recognition and Slot Filling in Task-Oriented Dialogue Systems (2025.findings-emnlp)

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

Copied to clipboard

Shuli Zhang, Zhiqiang You, Xiao Xiang Qi, Peng Liu, Gaode Wu, Kan Xia, Shenguang Huang

Semantic Parsing

Challenge:	Multi-intent utterances processing remains a persistent challenge due to intricate intent-slot dependencies and semantic ambiguities.
Approach:	They propose a label-aware contrastive attention network (LCAN) that integrates label-based attention and contrastive learning strategies to improve semantic understanding and generalization in multi-intent scenarios.
Outcome:	The proposed model improves intent recognition and slot filling performance in multi-intent dialogue systems.

Language Agnostic Multilingual Information Retrieval with Contrastive Learning (2023.findings-acl)

Copied to clipboard

Xiyang Hu, Xinchi Chen, Peng Qi, Deguang Kong, Kunlun Liu, William Yang Wang, Zhiheng Huang

RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering (2024.emnlp-main)

Challenge:	Annotated training data is costly to obtain in many languages .
Approach:	They propose a semantic contrastive loss to align parallel sentences that share the same semantics in different languages and a language contrastive gain to leverage parallel sentence pairs to remove language-specific information from non-parallel corpora.
Outcome:	The proposed model improves retrieval performance while requiring less computational effort.

Copied to clipboard

Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli

Cross-Domain Sentiment Classification with Target Domain Specific Information (P18-1)

Challenge:	Existing datasets for question answering based on retrieval augmented generation (RAG-QA) are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization.
Approach:	They propose a dataset that integrates short extractive answers from multiple documents into a single coherent narrative.
Outcome:	The proposed dataset integrates short extractive answers from multiple documents into a single coherent narrative, covering 26K queries and large corpora across seven different domains.

Copied to clipboard

Minlong Peng, Qi Zhang, Yu-gang Jiang, Xuanjing Huang

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning (2025.emnlp-main)

Challenge:	Existing methods for sentiment classification focus on learning domain-invariant representations . few of them pay attention to domain-specific information, which should also be informative.
Approach:	They propose a method to extract domain specific and invariant representations and train a classifier on each of them.
Outcome:	The proposed model can achieve better performance than state-of-the-art methods.

Copied to clipboard

Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang

Actively Supervised Clustering for Open Relation Extraction (2023.acl-long)

Challenge:	Existing work focuses on enabling models to generate natural language chain-of-thought rationales or leverage executable and verifiable code, such as Python.
Approach:	They propose a novel training pipeline that integrates sequential P-CoT and N-Co T generation and a subtask hybrid training strategy to facilitate natural language transferability.
Outcome:	The proposed training pipeline improves both N-CoT and P-Co T performance over the RL baseline.

Copied to clipboard

Jun Zhao, Yongxin Zhang, Qi Zhang, Tao Gui, Zhongyu Wei, Minlong Peng, Mingming Sun

Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation (2023.emnlp-main)

Challenge:	Existing methods for Open Relation Extraction (OpenRE) use a two-stage pipeline, which learns relation representations and assignments in the first stage, then manually labels relation for each cluster.
Approach:	They propose a method that performs relation learning and relation labeling simultaneously without a significant increase in human effort.
Outcome:	The proposed method improves existing SOTA methods by 13.8% and 10.6% on two datasets.

Copied to clipboard

Siyuan Wang, Bo Peng, Yichao Liu, Qi Peng

Visual Data in NLP

Challenge:	Existing methods to learn medical vision-language representations by contrasting images with entire reports are not effective.
Approach:	They propose a phenotype-driven medical vision-language representation learning framework to bridge the gap between visual and textual modalities for improved text-oriented generation.
Outcome:	The proposed framework bridges the gap between visual and textual modalities for improved radiology report generation.

A Class-Rebalancing Self-Training Framework for Distantly-Supervised Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Qi Li, Tingyu Xie, Peng Peng, Hongwei Wang, Gaoang Wang

metaCAT: A Metadata-based Task-oriented Chatbot Annotation Tool (2020.aacl-demo)

Challenge:	Distant supervision reduces the reliance on human annotation in named entity recognition tasks.
Approach:	They propose a class-rebalancing self-training framework for improving distantly-supervised named entity recognition by using a flexible threshold and a hybrid pseudo label.
Outcome:	The proposed model achieves state-of-the-art on five flat and two nested datasets and compares with other methods on the same dataset.

Copied to clipboard

Ximing Liu, Wei Xue, Qi Su, Weiran Nie, Wei Peng

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

Challenge:	Creating high-quality annotated dialogue corpora necessitates a high level of human engagements.
Approach:	They propose to develop an annotation tool specifically for developing task-oriented dialogue data that provides comprehensive metadata annotation coverage to the domain, intent, and span information.
Outcome:	The tool provides comprehensive metadata annotation coverage to domain, intent, and span information.

Copied to clipboard

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

Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection (2020.findings-emnlp)

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

Copied to clipboard

Hongliang Pan, Zheng Lin, Peng Fu, Yatao Qi, Weiping Wang

Sentiment Analysis

Challenge:	Existing methods for sarcasm detection ignore the incongruity character in sarcasm, which is often manifested between modalities or within modalités.
Approach:	They propose to capture inter-modality incongruity in a text-based model by using a self-attention mechanism and a co-attention model to model the contradiction within the text.
Outcome:	The proposed model achieves state-of-the-art on a public multi-modal sarcasm detection dataset.

Do Syntax Trees Help Pre-trained Transformers Extract Information? (2021.eacl-main)

Copied to clipboard

Devendra Sachan, Yuhao Zhang, Peng Qi, William L. Hamilton

Syntactic Text Processing

Challenge:	Recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models.
Approach:	They propose to incorporate dependency tree information into pre-trained transformers for three tasks . they propose a late fusion approach and a joint fusion technique to infuses syntax structure into attention layers.
Outcome:	The proposed models obtain state-of-the-art results on SRL and relation extraction tasks.

Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs (2022.acl-long)

Copied to clipboard

Chao Shang, Guangtao Wang, Peng Qi, Jing Huang

Simplify the Usage of Lexicon in Chinese NER (2020.acl-main)

Challenge:	Temporal knowledge graphs record entity relations and when they occur in time . previous work fails to address time-related challenges such as time-order issues . paper proposes time-sensitive question answering framework to address these problems .
Approach:	They propose a time-sensitive question answering framework that uses temporal KGs to answer natural language questions.
Outcome:	The proposed framework outperforms the state-of-the-art on a new benchmark for question answering over temporal knowledge graphs.

Copied to clipboard

Ruotian Ma, Minlong Peng, Qi Zhang, Zhongyu Wei, Xuanjing Huang

MAVEN-FACT: A Large-scale Event Factuality Detection Dataset (2024.findings-emnlp)

Challenge:	Named entity recognition (NER) is concerned with the identification of named entities in unstructured text.
Approach:	They propose a method for incorporating word lexicon into character representations . experimental results show method can be easily incorporated with pre-trained models .
Outcome:	The proposed method achieves 6.15 times faster inference speed and better performance on four benchmark Chinese NER datasets.

Copied to clipboard

Chunyang Li, Hao Peng, Xiaozhi Wang, Yunjia Qi, Lei Hou, Bin Xu, Juanzi Li

Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning (2026.acl-long)

Challenge:	Event factuality detection is under-explored due to the lack of high-quality large-scale data . efd is a subfield of event understanding, which aims to determine the factuity of textual events.
Approach:	They propose a large-scale EFD dataset with factuality annotations of 112,276 events . they find that adopting event arguments and relations helps in event factuity detection .
Outcome:	The proposed dataset includes factuality annotations of 112,276 events . it is the largest EFD dataset and is challenging for fine-tuned models and large language models .

Copied to clipboard

Shuyao Xu, Cheng Peng, Jiangxuan Long, Weidi Xu, Wei Chu, Yuan Qi

Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models (2024.emnlp-main)

Challenge:	Recent advances in model distillation show that data from advanced reasoning models can effectively train smaller student models.
Approach:	They propose a method to use both positive and negative distilled reasoning traces to maximize LLM reasoning performance in offline settings.
Outcome:	The proposed model outperforms existing methods in the distillation context.

Copied to clipboard

Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang

Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (D18-1)

Challenge:	Modern language models fail to follow human instructions while being faithful . a trade-off exists between instruction following and faithfulness when training LMs .
Approach:	They propose a method that relies on Reject-sampling by Self-instruct with Continued Fine-tuning to train LMs to follow human instructions while being faithful.
Outcome:	The proposed method outperforms vanilla MTL with high-quality data, but with significantly smaller data.

Copied to clipboard

Yuhao Zhang, Peng Qi, Christopher D. Manning

Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks (2023.findings-emnlp)

Challenge:	Existing dependency-based models neglect crucial information (e.g., negation) by pruning the dependency trees too aggressively.
Approach:	They propose an extension of graph convolutional networks that is tailored for relation extraction by pruning dependency trees too aggressively.
Outcome:	The proposed model outperforms existing sequence and dependency-based models on the large-scale TACRED dataset and has complementary strengths to sequence models.

Copied to clipboard

Kaiser Sun, Peng Qi, Yuhao Zhang, Lan Liu, William Wang, Zhiheng Huang

Question Answering

Challenge:	Pretrained sequence-to-sequence (seq2sequ) models have been widely used to solve extractive tasks, where parts of the input are extracted to form the desired output.
Approach:	They propose a simple fix to tokenization inconsistency that damages extractive nature of generative models by causing performance drop and hallucination.
Outcome:	The proposed model performs better in both in-domain and out-of-domain datasets with a notable average of +1.7 F1 gain when a BART model is trained on SQuAD and evaluated on 8 QA datasets.

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)

Copied to clipboard

Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan

Stepwise Reasoning Disruption Attack of LLMs (2025.acl-long)

Challenge:	Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT).
Approach:	They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge.
Outcome:	The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples.

Copied to clipboard

Jingyu Peng, Maolin Wang, Xiangyu Zhao, Kai Zhang, Wanyu Wang, Pengyue Jia, Qidong Liu, Ruocheng Guo, Qi Liu

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems (2025.acl-long)

Challenge:	Existing attacks on LLM reasoning are constrained by specific settings or lack of imperceptibility, limiting their feasibility and generalizability.
Approach:	They propose a stepwise rEasoning error disruption attack that subtly injects errors into prior reasoning steps to mislead the model into producing incorrect subsequent reasoning and final answers.
Outcome:	The proposed attack is compatible with zero-shot and few-shot settings, maintains the natural reasoning flow, and ensures covert execution without modification of the instruction.

Copied to clipboard

Hao Peng, Yunjia Qi, Xiaozhi Wang, Zijun Yao, Bin Xu, Lei Hou, Juanzi Li

Challenge:	Existing reward models focus on human preferences, neglecting verifiable correctness signals.
Approach:	They propose a reward system that combines human preference rewards with verifiable correctness signals to provide reliable rewards.
Outcome:	The proposed reward agent significantly outperforms vanilla reward models on benchmarks and inference-time best-of-n searches on real-world tasks.

FastBERT: a Self-distilling BERT with Adaptive Inference Time (2020.acl-main)

Copied to clipboard

Weijie Liu, Peng Zhou, Zhiruo Wang, Zhe Zhao, Haotang Deng, Qi Ju

AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)

Challenge:	Pre-trained language models like BERT have proven to be highly performant, but are often computationally expensive in many practical scenarios.
Approach:	They propose a speed-tunable FastBERT with adaptive inference time that can be flexibly adjusted under varying demands.
Outcome:	The proposed model achieves promising results in English and Chinese datasets.

Copied to clipboard

Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui

CiteEval: Principle-Driven Citation Evaluation for Source Attribution (2025.acl-long)

Challenge:	Recent advances in large language models (LLMs) have shown impressive performance on a range of tasks, yet advanced instruction following (IF) remains a significant challenge.
Approach:	They propose a benchmark that features over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions.
Outcome:	The proposed framework improves instruction-following abilities of large language models, achieving a 6.7% gain on AdvancedIF and strong results on public benchmarks.

Copied to clipboard

Yumo Xu, Peng Qi, Jifan Chen, Kunlun Liu, Rujun Han, Lan Liu, Bonan Min, Vittorio Castelli, Arshit Gupta, Zhiguo Wang

Challenge:	Current evaluation frameworks rely on NLI to assess binary or ternary support from cited sources, which is suboptimal for citation evaluation.
Approach:	They propose a citation evaluation framework based on fine-grained citation ratings within a broad context and construct a multi-domain benchmark with high-quality human annotations.
Outcome:	The proposed framework provides a high-quality human annotation benchmark and a suite of model-based metrics that exhibit strong correlation with human judgments.

ConvLab: Multi-Domain End-to-End Dialog System Platform (P19-3)

Copied to clipboard

Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Zheng Zhang, Yaoqin Zhang, Xiang Li, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao

Dialogue Systems & Conversational Agents

Challenge:	ConvLab is an open-source multi-domain end-to-end dialog system platform . it allows researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments.
Approach:	They propose to use an open-source multi-domain end-to-end dialog system platform to train and evaluate dialog bots in common environments.
Outcome:	The proposed system enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments.

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Stanza: A Python Natural Language Processing Toolkit for Many Human Languages (2020.acl-demos)

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Copied to clipboard

Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, Christopher D. Manning

Challenge:	Existing tools that support only a few major languages are under-optimized for accuracy due to a focus on efficiency or use of less powerful models.
Approach:	They introduce a Python natural language processing toolkit that supports 66 languages . they train Stanza on 112 datasets and show it generalizes well on all languages compared to other tools .
Outcome:	The proposed toolkit performs well on 112 datasets and is compatible with the popular Java CoreNLP software.

Answering Complex Open-domain Questions Through Iterative Query Generation (D19-1)

Copied to clipboard

Peng Qi, Xiaowen Lin, Leo Mehr, Zijian Wang, Christopher D. Manning