Papers by Peng Lu

Twist Decoding: Diverse Generators Guide Each Other (2022.emnlp-main)

Challenge:	Existing approaches to modifying large language models require continual updates to rectify outdated or erroneous knowledge.
Approach:	They propose a model editing strategy that mitigates catastrophic interference through sequential null-space alignment.
Outcome:	EvoEdit achieves better or comparable performance than prior state-of-the-art techniques with up to 3.53 speedup.

Copied to clipboard

Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Hao Peng, Ximing Lu, Dragomir Radev, Yejin Choi, Noah A. Smith

Text Generation

Challenge:	Using a variety of language generation models, ensembling models is challenging during inference.
Approach:	They propose a method that decodes text models that do not assume a shared vocabulary, tokenization or generation order.
Outcome:	The proposed method outperforms models decoded in isolation over various scenarios.

SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues (2021.acl-long)

Copied to clipboard

Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu

Structured Data in NLP

Challenge:	Existing studies focus on identifying entities' relations from the semantics of dialogues-they utilize either the attention mechanism or a refined token graph to locate informative words.
Approach:	They propose a sequential structure prediction task to incrementally parse SocAoG for dynamic inference upon any incoming utterance.
Outcome:	Empirical results show that the proposed model infers social relations more accurately than the state-of-the-art methods.

Investigating the Multilingual Calibration Effects of Language Model Instruction Tuning (2026.eacl-short)

Copied to clipboard

Jerry Huang, Peng Lu, Qiuhao Zeng, Yusuke Iwasawa, Yutaka Matsuo, Sarath Chandar, Edison Marrese-Taylor, Irene Li

RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation (2021.findings-emnlp)

Challenge:	despite advances in foundation model research, the relationship between large language models and their calibration remains an open area of research.
Approach:	They examine a gap in the calibration of large language models within multilingual settings to better understand how data scarcity can potentially lead to different calibration effects.
Outcome:	The proposed calibration gap is found in two multilingual benchmarks over 29 and 42 languages.

Copied to clipboard

Peng Lu, Abbas Ghaddar, Ahmad Rashid, Mehdi Rezagholizadeh, Ali Ghodsi, Philippe Langlais

DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL (2025.findings-emnlp)

Challenge:	Knowledge Distillation (KD) is used to compress the pre-training and task-specific fine-tuning phases of large neural language models.
Approach:	They propose a sample-wise loss weighting method that re-weights the two losses for each sample.
Outcome:	The proposed method outperforms existing methods on 7 datasets of the GLUE benchmark.

Copied to clipboard

Haoyuan Ma, Yongliang Shen, Hengwei Liu, Wenqi Zhang, Haolei Xu, Qiuying Peng, Jun Wang, Weiming Lu

Programming Languages in NLP

Challenge:	Recent text-to-SQL systems that use large language models struggle with complex database structures and domain-specific queries.
Approach:	a framework that aligns large language models with database knowledge is proposed . DB-Explore constructs database graphs to capture complex relational schemas .
Outcome:	a new framework outperforms existing text-to-SQL systems by outperforming existing systems.

CELLO: Causal Evaluation of Large Vision-Language Models (2024.emnlp-main)

Copied to clipboard

Meiqi Chen, Bo Peng, Yan Zhang, Chaochao Lu

Medical Entity Disambiguation with Medical Mention Relation and Fine-grained Entity Knowledge (2024.lrec-main)

Challenge:	Recent advances in large vision-language models have improved causal reasoning abilities . however, current models struggle with tasks like causal reasoning .
Approach:	They propose a fine-grained and unified definition of causality involving interactions between humans and objects.
Outcome:	The proposed model surpasses traditional commonsense causality by including explicit causal graphs . it also shows that current LVLMs can benefit from a causally inspired prompting strategy .

Copied to clipboard

Wenpeng Lu, Guobiao Zhang, Xueping Peng, Hongjiao Guan, Shoujin Wang

Challenge:	Existing methods for medical entity disambiguation (MED) fail to fully utilize the knowledge within medical knowledge bases (KBs) Existing models overlook essential interactions between medical mentions and candidate entities, resulting in knowledge- and interaction-inefficient modeling and suboptimal disambiguations performance.
Approach:	They propose to combine a mention relation fusion module and an entity knowledge fusion modules to map medical mentions to corresponding entities in a knowledge base (KB)
Outcome:	The proposed method outperforms state-of-the-art MED models on two publicly available real-world datasets.

VDebugger: Harnessing Execution Feedback for Debugging Visual Programs (2024.findings-emnlp)

Copied to clipboard

Xueqing Wu, Zongyu Lin, Songyan Zhao, Te-Lin Wu, Pan Lu, Nanyun Peng, Kai-Wei Chang

A Table-to-Text Framework with Heterogeneous Multidominance Attention and Self-Evaluated Multi-Pass Deliberation (2023.findings-emnlp)

Challenge:	Visual programs are executable code generated by large language models to address visual reasoning problems.
Approach:	They propose a critic-refiner framework that localizes and debugs visual programs by tracking execution step by step.
Outcome:	The proposed framework detects and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy.

Copied to clipboard

Xi Chen, Xinjiang Lu, Haoran Xin, Wenjun Peng, Haoyang Duan, Feihu Jiang, Jingbo Zhou, Hui Xiong

Structured Data in NLP

Challenge:	Table-to-text works have been widely applied in different domains, such as weather forecast and financial report generation.
Approach:	They propose a table-to-text approach on top of Self-evaluated multi-pass Generation and Heterogenous Multidominance Attention to explore the hierarchical structure.
Outcome:	The proposed method outperforms several SOTA methods quantitatively and qualitatively on three public datasets.

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning (2026.acl-long)

Copied to clipboard

Zekai Lin, Chao Xue, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Lei Jiang, Yu Lu, Bob Simons, Shuang Liang, Minlong Peng

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models (2026.acl-long)

Challenge:	Recent approaches to fine-tuning of large language models suffer from task interference and catastrophic forgetting.
Approach:	They propose a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance.
Outcome:	The proposed framework reduces interference and forgetting while releasing outdated parameters to recover plasticity.

Copied to clipboard

Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Chenyao Lu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng, Flora D. Salim

SC-LSTM: Learning Task-Specific Representations in Multi-Task Learning for Sequence Labeling (N19-1)

Challenge:	Incomplete learning is widespread and heterogeneous in large language models . authors identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between SFT supervision and pre-training knowledge, internal inconsistencies within SFT data, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns.
Approach:	They propose a diagnostic-first framework that maps incomplete learning to causes . they identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between supervision and pre-training knowledge, internal inconsistencies, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns.
Outcome:	The proposed framework maps incomplete learning to causes using observable training and inference signals.

Copied to clipboard

Peng Lu, Ting Bai, Philippe Langlais

MIME: MIMicking Emotions for Empathetic Response Generation (2020.emnlp-main)

Challenge:	Multi-task learning (MTL) has been studied for sequence labeling tasks . auxiliary tasks are selected specifically to improve performance of a target task .
Approach:	They propose a shared-cell long-short-term memory cell which contains shared parameters that can learn from all tasks and task-specific parameters that could learn task-related information.
Outcome:	The proposed model can learn from all tasks and task-specific parameters.

Copied to clipboard

Navonil Majumder, Pengfei Hong, Shanshan Peng, Jiankun Lu, Deepanway Ghosal, Alexander Gelbukh, Rada Mihalcea, Soujanya Poria

Text Generation

Challenge:	Empathy is a fundamental human trait that reflects our ability to understand and reflect the thoughts and feelings of the people we interact with.
Approach:	They propose to use polarity-based emotion clusters to generate empathetic responses . they also introduce stochasticity into the emotion mixture that yields emotionally more varied responses compared to the previous work .
Outcome:	The proposed methods improve empathy and contextual relevance of the response, and introduce stochasticity into the emotion mixture that yields emotionally more varied responses than the previous work.

Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference (2025.naacl-long)

Copied to clipboard

Zeping Li, Xinlong Yang, Ziheng Gao, Ji Liu, Guanchen Li, Zhuang Liu, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum

Machine Translation

Challenge:	Existing methods such as Medusa lack adequate information interaction between different drafting heads.
Approach:	They propose an enhanced speculative decoding framework that builds upon Medusa and integrates a drafting block capable of parallel inference.
Outcome:	The proposed framework outperforms Medusa in terms of head accuracy and latency.

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository (2026.acl-long)

Copied to clipboard

Zhiyuan Peng, Xin Yin, Pu Zhao, Fangkai Yang, Lu Wang, Ran Jia, Xu Chen, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing benchmarks focus on isolated function/class-level generation, neglecting complete microservice repository generation.
Approach:	They propose a multilingual benchmark for repository-level end-to-end web microservice generation that reflects real-world development workflows.
Outcome:	The benchmark compared 106 repositories across 18 domains and 11 frameworks and 1,258 API endpoints and 2,335 test cases.

Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs (2024.acl-long)

Copied to clipboard

Zhiwei Cao, Qian Cao, Yu Lu, Ningxin Peng, Luyang Huang, Shanbo Cheng, Jinsong Su

Efficient Classification of Long Documents via State-Space Models (2023.emnlp-main)

Challenge:	Existing methods to compress long contexts have degraded dramatically as compression ratios increase, sometimes even falling to the closed-book level.
Approach:	They propose a query-guided compression method that preserves key information within the compressed context.
Outcome:	The proposed method can consistently perform well even at high compression ratios, and offers significant benefits in terms of inference cost and throughput.

Copied to clipboard

Peng Lu, Suyuchen Wang, Mehdi Rezagholizadeh, Bang Liu, Ivan Kobyzev

QaDialMoE: Question-answering Dialogue based Fact Verification with Mixture of Experts (2022.findings-emnlp)

Challenge:	Existing transformer-based models can only process long documents with limited computational resources due to their quadratic computation time and space.
Approach:	They propose to use state-space models for long document classification tasks instead of using sparse or hierarchical structures to solve this problem.
Outcome:	The proposed model performs comparable to self-attention models while being 36% more efficient.

Copied to clipboard

Longzheng Wang, Peng Zhang, Xiaoyu Lu, Lei Zhang, Chaoyang Yan, Chuang Zhang

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization (2024.acl-long)

Challenge:	Existing research on fact verification focuses on news, tables and Wikipedia passages.
Approach:	They propose a question-answering dialogue based fact verification with mixture of experts that exploits questions and evidence effectively in the verification process.
Outcome:	The proposed approach outperforms previous approaches on three benchmark datasets and achieves state-of-the-art results.

Copied to clipboard

Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang, Weiming Lu

Event Extraction as Multi-turn Question Answering (2020.findings-emnlp)

Challenge:	Large Language Models (LLMs) are designed as specific task solvers with sophisticated prompt engineering, but are inherently incapacitating to address complex dynamic scenarios.
Approach:	They propose an LLM-based agent with policy-level reflection and optimization that can learn from interactive experiences and progressively elevate its behavioral policy.
Outcome:	The proposed agent outperforms vanilla LLM and specialized models in blackjack and Texas hold’em.

Copied to clipboard

Fayuan Li, Weihua Peng, Yuguang Chen, Quan Wang, Lu Pan, Yajuan Lyu, Yong Zhu

Information Extraction & Text Mining

Challenge:	Current approaches to event extraction fail to model rich interactions among event types and arguments of different roles.
Approach:	They propose a new paradigm that formulates event extraction as multi-turn question answering . they propose to use reading comprehension problems to extract triggers and arguments .
Outcome:	The proposed approach outperforms current state-of-the-art on argument extraction tasks . it makes full use of dependency among arguments and event types, and generalizes well .

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)

Copied to clipboard

Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu, Wenqi Zhang, Yuchen Yan, Qiuying Peng, Jun Wang, Weiming Lu

Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging (2022.findings-emnlp)

Challenge:	Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification.
Approach:	They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth.
Outcome:	The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation.

Copied to clipboard

Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh, Ahmad Rashid, Ali Ghodsi, Phillippe Langlais

Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research (2025.acl-demo)

Challenge:	Recent studies show that the flatness of the local minimum correlates well with better generalization.
Approach:	They propose to use a method encouraging convergence to a flatter minimum to fine-tune PLMs.
Outcome:	The proposed method outperforms state-of-the-art methods on NLP tasks without extra computation cost.

Copied to clipboard

Qianqian Zhang, Jiajia Liao, Heting Ying, Yibo Ma, Haozhan Shen, Jingcheng Li, Peng Liu, Lu Zhang, Chunxin Fang, Kyusong Lee, Ruochen Xu, Tiancheng Zhao

Word Sense Disambiguation with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension (2022.coling-1)

Challenge:	Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks.
Approach:	They propose a flexible framework that addresses engineering overhead and insufficient evaluation frameworks for fair comparison.
Outcome:	The proposed framework simplifies language agent development and establishes a foundation for reproducible agent research.

Copied to clipboard

Guobiao Zhang, Wenpeng Lu, Xueping Peng, Shoujin Wang, Baoshuo Kan, Rui Yu

Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty (2026.findings-acl)

Challenge:	Word sense disambiguation (WSD) is one of the most challenging tasks in natural language processing.
Approach:	They propose a method to extract the right sense from a sentence context . they propose to incorporate additional examples and definitions of related senses in WordNet .
Outcome:	The proposed method achieves better performance than baseline models on public benchmark datasets.

Copied to clipboard

Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Chenyao Lu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng, Flora D. Salim

Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation (2025.acl-demo)

Challenge:	Existing approaches to generating reward models rely on voting-based mechanisms to evaluate CoT outputs.
Approach:	They propose an efficient generative reward modeling framework grounded in model-internal uncertainty.
Outcome:	The proposed framework reduces inference cost while improving answer accuracy.

Copied to clipboard

Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Yang Ou, Scarlett Li, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, James Evans, Xing Xie

Challenge:	Current evaluation methods for large language models face two key challenges: 1. evaluation validity and 2. Result interpretation reduce the pluralistic and incommensurable values to one-dimensional scores.
Approach:	They propose a platform for comprehensive value diagnosis of large language models (LLMs) that provides a generative evaluation paradigm that automatically creates real-world test items co-evolving with ever-advancing LLMs.
Outcome:	The proposed platform provides a framework for comprehensive value diagnosis of large language models (LLMs) with fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, customized comparisons, and visualized analysis of LLM’s alignment with cultural values.

LLMs for Now, Fine-Tuning for Later: An Ensemble Approach to Data Drift in Domain-Specific Tasks (2026.acl-srw)

Copied to clipboard

Yuxuan Lu, Bingsheng Yao, Shao Zhang, Yisi Sang, Yun Wang, Hansu Gu, Peng Zhang, Tun Lu, Toby Jia-Jun Li, Dakuo Wang

Real-time Ad Retrieval via LLM-generative Commercial Intention for Sponsored Search Advertising (2025.emnlp-main)

Challenge:	Deploying machine learning models in domain-specific scenarios is challenged by data drift and the scarcity of expert annotations.
Approach:	They propose a system that combines an LLM, an AL-assisted compact model and an automatic switch module to assist the active learning process.
Outcome:	The proposed system achieves 96–98% switch accuracy and outperforms both models used alone.

Copied to clipboard

Tongtong Liu, Zhaohui Wang, Meiyue Qin, Zenghui Lu, Xudong Chen, Yuekui Yang, Peng Shu

Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information (2024.findings-emnlp)

Challenge:	Existing methods for retrieving documents and ads use one-to-few mappings and time-consuming content extraction.
Approach:	They propose a framework that leverages LLM-generated commercial intents as an intermediate semantic representation to directly retrieve ads for queries in real-time.
Outcome:	The proposed framework has been implemented in a real-world online system, handling daily search volumes in billions.

Copied to clipboard

Yongheng Zhang, Qiguang Chen, Jingxuan Zhou, Peng Wang, Jiasheng Si, Jin Wang, Wenpeng Lu, Libo Qin

An Intent-based and Annotation-free Method for Duplicate Question Detection in CQA Forums (2023.findings-emnlp)

Challenge:	Chain-of-Thought (CoT) is a key technique for enhancing the performance of Large Language Models.
Approach:	They propose a framework that optimizes outputs by utilizing wrong information and multi-perspective verification.
Outcome:	The proposed framework surpasses all baselines on 8 datasets and 5 LLMs.

Copied to clipboard

Yubo Shu, Hansu Gu, Peng Zhang, Tun Lu, Ning Gu

ReGLA: Refining Gated Linear Attention (2025.naacl-long)

Challenge:	Existing methods for detecting duplicate questions in CQA rely on generic text-pair matching models, overlooking the intent behind the questions.
Approach:	They propose a new intent-based duplication detector that leverages intent information to address the problem of duplicate question detection in CQA.
Outcome:	The proposed detector leverages the characteristics of CQA forums and extracts training labels to recognize and match intents without human annotation.

Copied to clipboard

Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh, Boxing Chen, Philippe Langlais

Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction (2024.lrec-main)

Challenge:	Recent advances in Large Language Models (LLMs) are known for their computational and storage requirements due to the quadratic computation complexity of softmax attention.
Approach:	They propose to reduce the quadratic computation complexity of softmax attention by using feature maps, normalization and the gating mechanism to improve performance.
Outcome:	The proposed model outperforms existing gated linear attention models in extensive tasks including training from scratch and post-linearization with continual pre-training.

Copied to clipboard

Ziyang Xu, Keqin Peng, Liang Ding, Dacheng Tao, Xiliang Lu

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

Challenge:	Recent research shows that pre-trained language models suffer from “prompt bias” in factual knowledge extraction.
Approach:	They propose a representation-based approach to mitigate prompt bias during inference time by querying the model and removing it from its internal representations to generate debiased representations.
Outcome:	The proposed approach corrects the overfitted performance caused by prompt bias and significantly improves prompt retrieval capability.

Copied to clipboard

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

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization (2024.findings-emnlp)

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

Copied to clipboard

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu, Zheng Liu, Tun Lu, Xing Xie, Ning Gu

Wenqiang Wang, Peng Chen, Yan Xiao, Yangshijie Zhang, Xiaoyue Lu, Jianjie Huang, Xiaochun Cao

Challenge:	Existing methods to steer LLMs towards human preference suffer from noisy positive-negative training pairs.
Approach:	They propose a distributional preference optimization method which maximizes discrepancy between dispreferred responses and generated non-negative ones.
Outcome:	The proposed method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence.

Copied to clipboard

PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection (2026.acl-long)

Challenge:	Standard in-context learning assumes identical output spaces between test and retrieval datasets . however, in practice, these datasets can be fully aligned, partially alignes, or fully disjoint in label space .
Approach:	They propose a framework for in-context learning under output-space mismatch . they identify demonstrations relevant to the test label space via a Bayesian probabilistic criterion .
Outcome:	The proposed framework achieves state-of-the-art results across three LLMs, three task types, and four datasets.

Copied to clipboard

Jinhan Liu, Yibo Yang, Ruiying Lu, Piotr Piękos, Yimeng Chen, Peng Wang, Dandan Guo

LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization (2023.findings-acl)

Challenge:	Existing likelihood-based methods for detecting pretraining data are limited in black-box, zero-shot settings.
Approach:	They propose a training-free and plug-and-play framework that reweights token-level scores to amplify distinct signals from early positions while suppressing noise from later ones.
Outcome:	The proposed framework amplifys signals from early positions while suppressing noise from later positions.

Copied to clipboard

Peng Lu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Phillippe Langlais

STaR-SQL: Self-Taught Reasoner for Text-to-SQL (2025.acl-long)

Challenge:	Existing methods for regularizing deep neural networks rely on weight decay, dropout, batch/layer normalization to converge faster and generalize.
Approach:	They propose a framework for training with label regularization which includes conventional LS but can also model instance-specific variants.
Outcome:	The proposed approach consistently yields better results than conventional regularization on seven machine translation and three image classification tasks while maintaining training efficiency.

Copied to clipboard

Mingqian He, Yongliang Shen, Wenqi Zhang, Qiuying Peng, Jun Wang, Weiming Lu

Programming Languages in NLP

Challenge:	Existing methods for generating step-by-step “chain-of-thought” rationales are limited to text-to-SQL.
Approach:	They propose a method that prompts SQL query generation to produce reasoning steps for SQL queries and fine-tunes it on rationales that lead to correct outcomes.
Outcome:	The proposed method outperforms agent-like prompting methods on the Spider benchmark.

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model (2024.emnlp-main)

Copied to clipboard

Chenhan Yuan, Fei Huang, Ru Peng, Keming Lu, Bowen Yu, Chang Zhou, Jingren Zhou

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue (2024.emnlp-main)

Challenge:	Existing approaches to fine tune LLMs produce unsafe responses and unreliable reasoning, but this solution introduces substantial time and space overhead due to the separate models required.
Approach:	They propose to insert extra parameters into transformer architecture to predict calibration signals along with original LLM output.
Outcome:	The proposed model reduces time and space costs while enabling seamless online deployment.

Copied to clipboard

Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, Nanyun Peng

Evolving Agentic Workflow Driven by Human-Agent Collaboration (2026.findings-acl)

Challenge:	Existing methods that edit large language models with updated knowledge can cause side effects on the general abilities of LLMs such as reasoning, natural language inference, and question answering.
Approach:	They propose to regularize the edit update weights by imposing constraints on their complexity based on the RElative Change in weighT.
Outcome:	The proposed method can significantly mitigate the side effects while maintaining over 94% editing performance.

Copied to clipboard

Yuxin Liu, Jinxuan Zhang, Yuezhang Peng, Hefeng Zhou, Xiangfeng Wang, Jiong Lou, Chentao Wu, Jie LI, Jingjing Qu, Chaochao Lu

Challenge:	Existing approaches to generate agentic workflows using large language models are limited by high manual design costs, inefficient agentic search, and poor dynamic adaptability to new tasks and human preferences.
Approach:	They propose an evolutionary framework for generating agentic workflows through human-agent collaboration using evolutionary algorithms that mutate and cross over their structures, prompts, and LLM backbones.
Outcome:	The proposed framework surpasses other automated baselines by 27.34% while achieving comparable performance to o1-preview at only one-fourth of the cost.

LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions (2026.findings-acl)

Copied to clipboard

Xuhao Hu, Wang Peng, Xiaoya Lu, Dongrui Liu, Xuanjing Huang, Jing Shao

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

Challenge:	Existing studies have shown that LLMs finetuned on incorrect completions can exhibit harmful behaviors, which is called emergent misalignment.
Approach:	They investigate whether LLMs finetuned on incorrect completions can exhibit harmful behaviors . they find that 1% of misalignment data is sufficient to decrease honest behavior .
Outcome:	The proposed model can be misaligned on errors within narrow domains to exhibit harmful behaviors . the proposed model is able to exhibit dishonest behavior with only 10% biased user population .

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

Rethinking Creativity Evaluation: A Critical Analysis of Existing Creativity Evaluations (2026.eacl-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

Li-Chun Lu, Miri Liu, Pin Chun Lu, Yufei Tian, Shao-Hua Sun, Nanyun Peng

Syntactic Text Processing

Challenge:	Creativity measures that distinguish creativity in one domain fail in others, and different metrics disagree on the same data points.
Approach:	They examine, analyze, and compare four representative creativity measures across the diverse creative domains, including creative writing, unconventional problem-solving, and research ideation.
Outcome:	The measures of creativity across creative domains are compared using a set of human-aligned examples and lack consistency across domains and metrics.

Extractive Medical Entity Disambiguation with Memory Mechanism and Memorized Entity Information (2024.findings-emnlp)

Copied to clipboard

Guobiao Zhang, Xueping Peng, Tao Shen, Guodong Long, Jiasheng Si, Libo Qin, Wenpeng Lu

Challenge:	Existing methods focus on local optimal while ignoring sole-mention disambiguation boosted by richer context from other mentions’ disambiguating processes.
Approach:	They propose an approach to extracting medical entity disambiguation using memory mechanism and memorized entity information (M3E) they use a memory mechanism module that performs memory caching, retrieval, fusion and cross-network residual to aid the disambiguations of remaining mentions.
Outcome:	The proposed method outperforms state-of-the-art methods on two benchmark datasets.

Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Copied to clipboard

Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

Speech & Audio in NLP

Challenge:	Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach:	They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome:	The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.

Personalized Question Answering with User Profile Generation and Compression (2025.findings-emnlp)

Copied to clipboard

Hang Su, Yun Yang, Tianyang Liu, Xin Liu, Peng Pu, Xuesong Lu

SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings (2025.acl-long)

Challenge:	Large language models are prone to providing “midguy” answers regardless of users’ knowledge background, thereby failing to meet each user’s personalized needs.
Approach:	They propose to generate personalized answers with LLMs based on users’ past question-answering records.
Outcome:	The proposed method generates personalized answers based on user's past question-answering records.

Copied to clipboard

Weikai Lu, Hao Peng, Huiping Zhuang, Cen Chen, Ziqian Zeng

Aligning Cross-Lingual Entities with Multi-Aspect Information (D19-1)

Challenge:	Existing low-resource security alignment methods struggle with the security risks posed by additional modalities.
Approach:	They propose to use multimodal datasets to enhance safety alignment but it is costly to construct these datasets.
Outcome:	Experiments on image, video, and audio-based MLLMs show that the proposed method can synthesize a high-quality embedding on a single RTX3090 GPU within 24 seconds.

Copied to clipboard

Hsiu-Wei Yang, Yanyan Zou, Peng Shi, Wei Lu, Jimmy Lin, Xu Sun

ChartAssistant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning (2024.findings-acl)

Challenge:	Existing knowledge graphs that represent entities in different languages are not covered by existing systems.
Approach:	They propose two ways to embed entities from multilingual knowledge graphs into the same vector space, where equivalent entities are close to each other.
Outcome:	The proposed method significantly outperforms existing systems on two benchmark datasets.

Copied to clipboard

Fanqing Meng, Wenqi Shao, Quanfeng Lu, Peng Gao, Kaipeng Zhang, Yu Qiao, Ping Luo

SOAPTriage: SOAP-Guided Multi-View Clinical Text Modeling Framework for Automated ESI Prediction (2026.acl-long)

Challenge:	Charts are an effective tool for understanding data patterns, but their combination of graphical elements and textual components poses challenges for general-purpose multimodal models.
Approach:	They propose a chart-based vision-language model for universal chart comprehension and reasoning that leverages a dataset of chart-related tasks.
Outcome:	The proposed model outperforms the state-of-the-art charts with zero-shot setting on various chart tasks.

Copied to clipboard

Enming Wang, Jianlei Wang, Xueping Peng, Hongjiao Guan, Yinglong Wang, Sibo Wei, Jianbin Guo, Ruifeng Xu, Wenpeng Lu

Do we need Label Regularization to Fine-tune Pre-trained Language Models? (2023.eacl-main)

Challenge:	Emergency departments rely on the Emergency Severity Index (ESI) to assess patient acuity and prioritize care.
Approach:	They propose a SOAP-guided multi-view clinical text modeling framework for automated ESI prediction based on the SOAP paradigm .
Outcome:	The proposed framework outperforms prompting-based, multi-agent, and encoder-based baselines.

Copied to clipboard

Ivan Kobyzev, Aref Jafari, Mehdi Rezagholizadeh, Tianda Li, Alan Do-Omri, Peng Lu, Pascal Poupart, Ali Ghodsi

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives (2024.acl-long)

Challenge:	Knowledge Distillation (KD) is a label regularization technique that can be replaced with lighter teacher-free variants such as the label-smoothing technique.
Approach:	They propose to use knowledge distillation to train student models by deploying the teacher network during training.
Outcome:	The proposed method can be replaced with lighter teacher-free variants on PLMs with more than 600 distinct trials and ran each configuration five times.

Copied to clipboard

Wenqi Zhang, Yongliang Shen, Linjuan Wu, Qiuying Peng, Jun Wang, Yueting Zhuang, Weiming Lu

DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms (2025.findings-emnlp)

Challenge:	Recent research indicates without external feedback, LLM’s intrinsic reflection is unstable.
Approach:	They propose a method that combines self-evaluated and external feedback to improve LLM's reflection.
Outcome:	The proposed method improves the quality of self-evaluated feedback and can catalyze more accurate and stable reflection.

Copied to clipboard

Xiaojun Bi, Shuo Li, Junyao Xing, Ziyue Wang, Fuwen Luo, Weizheng Qiao, Lu Han, Ziwei Sun, Peng Li, Yang Liu

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)

Challenge:	Dongba pictographic is the only pictograph script still in use in the world.
Approach:	DongbaMIE is the first dataset focusing on multimodal information extraction of Dongbe pictographs.
Outcome:	The dataset contains 23,530 sentence-level and 2,539 paragraph-level high-quality text-image pairs.

Copied to clipboard

Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li, Yueting Zhuang

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)

Challenge:	Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored.
Approach:	They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes.
Outcome:	The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks.

Copied to clipboard

Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui

Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity (2024.findings-emnlp)

Challenge:	Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows.
Approach:	They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system.
Outcome:	Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks.

Copied to clipboard

Michael Metel, Peng Lu, Boxing Chen, Mehdi Rezagholizadeh, Ivan Kobyzev

Challenge:	Speculative decoding uses a small draft model to generate a single input token, instead of sequentially generating tokens until completion.
Approach:	They propose a method that generates varying draft models adapted to the input context using simple rules.
Outcome:	The proposed method is competitive with the current SOTA for self-speculative decoding while being a truly plug-and-play method.

ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring (2026.acl-industry)

Copied to clipboard

Deyi Ji, Junyu Lu, Xuanyi Liu, Liqun Liu, Hailong Zhang, Peng Shu, Huan Yu, Jie Jiang, Tianrun Chen, Lanyun Zhu

TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking (2026.acl-long)

Challenge:	Existing regulatory policies create label inconsistencies and reasoning ambiguities in historical datasets.
Approach:	They propose a policy-adaptive governance system that enables evolving reinforcement through multi-agent adversarial umpiring.
Outcome:	The proposed system outperforms fine-tuning baselines on industrial and public datasets . it enables evolving reinforcement through multi-agent adversarial umpiring .

Copied to clipboard

Xiaocheng Zhang, Xi Wang, Yifei Lu, Jianing Wang, Zhuangzhuang Ye, Mengjiao Bao, Peng Yan, Xiaohong Su

Engage the Public: Poll Question Generation for Social Media Posts (2021.acl-long)

Challenge:	Existing benchmarks lack social metadata and evaluation framework to meet this urgent evaluation needs.
Approach:	They propose a benchmark capable of evaluating HPA and three fact-checking tasks.
Outcome:	The proposed framework improves HPA and computational efficiency for RLM-driven systems.

Copied to clipboard

Zexin Lu, Keyang Ding, Yuji Zhang, Jing Li, Baolin Peng, Lemao Liu

MetaBench: A Multi-task Benchmark for Assessing LLMs in Metabolomics (2026.acl-long)

Challenge:	a novel application to generate poll questions for social media posts offers an easy way to hear the public's voice . for the silent majority, they tend to read others' messages instead of voicing their opinions with words .
Approach:	They propose to encode user comments and discover latent topics therein as contexts to generate poll questions for social media posts.
Outcome:	The proposed model outperforms popular models without exploiting topics from comments . human evaluations show it can generate high-quality polls useful to draw user engagements .

Copied to clipboard

Yuxing Lu, Xukai Zhao, J. Ben Tamo, Micky C. Nnamdi, Rui Peng, Shuang Zeng, Xingyu Hu, Jinzhuo Wang, May Dongmei Wang

IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities on general text, but their proficiency in specialized scientific domains remains uncharacterized.
Approach:	They evaluate the capabilities of large language models in metabolomics research using MetaBench . they found that models perform well on text generation tasks, but cross-database identifier grounding remains challenging .
Outcome:	The evaluation of 25 open- and closed-source LLMs reveals distinct performance patterns across metabolomics tasks.

Copied to clipboard

Bo Peng, Zhiheng Wang, Heyang Gong, Chaochao Lu