Papers by Le Li

Beyond Surface-Level Pattern Trap: LLM Agents for Faster and Smarter Cross-Architecture Code Migration (2026.findings-acl)

Challenge:	Recent LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs and increasing compute cost and memory overhead.
Approach:	They propose an agent framework that maintains a compact memory during multi-turn interactions.
Outcome:	The proposed framework outperforms strong history-concatenation (ReAct-style) baselines on a range of public datasets while maintaining nearly constant token counts across multi-turn interactions.

Copied to clipboard

Weijia Li, KE Gao, Pengfei Chen, Jiajie Li, Xinyu Wang, Yiran Le, Yize Wu, Ling Li

Youling: an AI-assisted Lyrics Creation System (2020.emnlp-demos)

Challenge:	cross-architecture code migration is a resource-intensive and errorprone task.
Approach:	a framework for cross-architecture code migration is proposed to decouple implementation details through functional mining and code refactoring.
Outcome:	a new framework improves performance and correctness over state-of-the-art frameworks on OpenCV migration tasks.

Copied to clipboard

Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang

Challenge:	Recent studies have focused on a single pass of lyrics generation with little human intervention.
Approach:	They propose an AI-assisted lyrics creation system that supports one pass full-text generation and interactive generation modes.
Outcome:	The proposed system supports full-text generation and interactive generation modes . it also provides a revision module which enables users to revise undesired lyrics repeatedly.

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models (2026.acl-long)

Copied to clipboard

Ziyan Wang, Enmao Diao, Qi Le, Pu Wang, Minwoo Lee, Shu-ping Yeh, Evgeny Stupachenko, Hao Feng, Li Yang

Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding (2024.emnlp-main)

Challenge:	Structured pruning is a practical approach to deploying large language models (LLMs) but it fails to capitalize on modest task-specific calibration signals, causing limited downstream gains.
Approach:	They propose a method that removes attention heads and MLP channels using loss-based important scores . they use perplexity for language modeling and a margin-based objective for decision-style tasks .
Outcome:	The proposed method lowers perplexity and improves accuracy at higher sparsity . it also stabilizes accuracy and mitigates perxity collapse without fine-tuning .

Copied to clipboard

Wei Li, Zhen Huang, Xinmei Tian, Le Lu, Houqiang Li, Xu Shen, Jieping Ye

Explainability & Interpretability in NLP

Challenge:	Despite promising progress, vision-language models still exhibit significant challenges in understanding visio-linguistic concepts beyond object terms.
Approach:	They propose a framework that encourages the model to pay greater attention to composition words denoting relationships and attributes within the text.
Outcome:	The proposed framework improves the ability to discern intricate details and construct more sophisticated interpretations of combined visual and linguistic elements.

Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models (2025.acl-long)

Copied to clipboard

Wei Li, Zhen Huang, Houqiang Li, Le Lu, Yang Lu, Xinmei Tian, Xu Shen, Jieping Ye

PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing (2026.acl-long)

Challenge:	LVLMs have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs.
Approach:	They propose a visual evidence prompting method to mitigate hallucinations in large vision-language models by using small visual models to complement them.
Outcome:	The proposed method reduces hallucinations by reducing false activation and enhancing correct ones.

Copied to clipboard

Zhuoqun Li, Xuanang Chen, Hongyu Lin, Yaojie Lu, Xianpei Han, Shanshan Jiang, Bin Dong, Le Sun

Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration (2026.eacl-long)

Challenge:	Existing paper search systems lack detailed information to support finer-grained queries.
Approach:	They propose a paper-based index that transforms abstract-based corpus index into hierarchical index tree and offline can support paper search queries.
Outcome:	The proposed system achieves the SOTA performance and excels in fine-grained scenarios.

Copied to clipboard

Guozhao Mo, Yanjiang Liu, Yafei Shi, Jiawei Chen, Yang Li, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Bo Zheng, Xianpei Han

Linguistics & Cognitive NLP

Challenge:	Existing methods for dynamic web navigation rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models.
Approach:	They propose a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration.
Outcome:	The proposed framework surpasses the proprietary model Claude-3.5 Sonnet on the WebArena benchmark.

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning (2025.acl-long)

Copied to clipboard

Ruoxi Xu, Yunjie Ji, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Ben He, Yingfei Sun, Xiangang Li, Le Sun

CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models (2025.naacl-long)

Challenge:	Existing knowledge injection frameworks focus on knowledge memorization and retrieval, but static nature of large language models leads to outdated information as the real world evolves or when adapting to domain-specific knowledge.
Approach:	They propose a four-tier knowledge injection framework that defines the levels of knowledge injection: memorization, retrieval, reasoning, and association.
Outcome:	The proposed framework defines the levels of knowledge injection: memorization, retrieval, reasoning, and association.

Copied to clipboard

Jierui Li, Hung Le, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Doyen Sahoo

Programming Languages in NLP

Challenge:	coding tasks require generated code to be fully executable and functionally correct . current agentic approaches struggle with multi-stage planning, generating, and debugging .
Approach:	They propose a framework for LLM agents to efficiently explore the search space in different stages of the code generation process.
Outcome:	The proposed framework achieves top results on 7 code generation benchmarks and a 31.9% solving rate on the SWEBench benchmark.

Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization (2024.findings-acl)

Copied to clipboard

Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li, Zifeng Wang, Long Le, Abhishek Kumar, James Glass, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, Tomas Pfister

Challenge:	Large language models struggle to capture relevant information located in the middle of their input.
Approach:	They propose a calibration mechanism that allows the model to attend to contexts faithfully according to their relevance even when they are in the middle.
Outcome:	The proposed calibration mechanism mitigates this positional bias and improves retrieval-augmented generation performance.

DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering (2022.findings-acl)

Copied to clipboard

Le Qi, Shangwen Lv, Hongyu Li, Jing Liu, Yu Zhang, Qiaoqiao She, Hua Wu, Haifeng Wang, Ting Liu

TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System (2025.findings-naacl)

Challenge:	Open-domain question answering is a task that requires answering questions based on a collection of document images.
Approach:	They propose to use document images to answer questions using layouts and visual features instead of text.
Outcome:	The proposed approach reduces human cost and improves scalability of QA systems by incorporating layouts and visual features.

Copied to clipboard

Zeyu Zhang, Jianxun Lian, Chen Ma, Yaning Qu, Ye Luo, Lei Wang, Rui Li, Xu Chen, Yankai Lin, Le Wu, Xing Xie, Ji-Rong Wen

Robustness in NLP

Challenge:	Trending topics bring in a new channel for poisoning attacks, resulting in negative impacts on society.
Approach:	They propose an LLM-based multi-agent system to simulate trending topics in social media . they propose a time-aware interaction mechanism, centralized message dissemination, and an interactive system .
Outcome:	The proposed system simulates trending topics under poisoning attacks on social media platforms.

DiffusPoll: Conditional Text Diffusion Model for Poll Generation (2024.findings-acl)

Copied to clipboard

Le Cheng, Shuangyin Li

Multimodality

Challenge:	Social media platforms manipulate public opinion through sheer numbers and cause biases, authors say . they say new paradigm for poll generation can generate high-quality samples while preserving diversity .
Approach:	They propose a non-autoregressive diffusion model that uses masks to generate polls . they use attribute tags to enhance the quality of polls and to diversify poll options .
Outcome:	The proposed model matches the Transformer model while offering greater diversity and quality.

RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents (2026.acl-long)

Copied to clipboard

Jize Wang, Han Wu, Zhiyuan You, Yiming Song, Yijun Wang, Zifei Shan, Yining Li, Songyang Zhang, Xinyi Le, Cailian Chen, Xinping Guan, Dacheng Tao

NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval (D18-1)

Challenge:	Existing methods for mixing-of-agents (MoA) lack model selection criteria and struggle with large model pools.
Approach:	They propose a mixture-of-agents framework with dynamic routing that uses a lightweight scorer to perform initial screening and refines the model scores through self- and cross-assessment.
Outcome:	The proposed framework outperforms existing methods for large model pools and tasks . it reduces cost by 89.8% and latency by 63.6% in the large-scale model pool.

Copied to clipboard

Canjia Li, Yingfei Sun, Ben He, Le Wang, Kai Hui, Andrew Yates, Le Sun, Jungang Xu

Joint Learning from Labeled and Unlabeled Data for Information Retrieval (C18-1)

Challenge:	Existing neural IR models do not have a mechanism for treating expansion terms differently from the original query terms, making it difficult to combine them with existing PRF approaches.
Approach:	They propose an end-to-end neural PRF framework that can be used with existing neural IR models by embedding different neural models as building blocks.
Outcome:	Extensive experiments on two standard test collections confirm the effectiveness of the proposed framework in improving the performance of two state-of-the-art neural IR models.

Copied to clipboard

Bo Li, Ping Cheng, Le Jia

TermDiffuSum: A Term-guided Diffusion Model for Extractive Summarization of Legal Documents (2025.coling-main)

Challenge:	Recent studies have focused on neural information retrieval (IR) models.
Approach:	They propose a framework which can benefit from both labeled and more abundant unlabeled data . they propose supervised retrieval over several strong baselines for IR .
Outcome:	The proposed framework can benefit from labeled and more abundant unlabeled data for representation learning in the context of IR.

Copied to clipboard

Xiangyun Dong, Wei Li, Yuquan Le, Zhangyue Jiang, Junxi Zhong, Zhong Wang

DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking (2025.acl-long)

Challenge:	Recent studies have explored diffusion models for extractive summarization task, showcasing their remarkable capabilities.
Approach:	They propose a term-guided diffusion model for extractive summarization of legal documents that incorporates legal terminology into the model via a well-designed multifactor fusion noise weighting schedule.
Outcome:	The proposed model outperforms existing models on a self-constructed legal summarization dataset and achieves improvements of 3.10, 2.84, and 2.89 on three public datasets.

Copied to clipboard

Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, Le Sun

Challenge:	Existing studies in retrieval-augmented generation (RAG) do not sufficiently address the design of complex engineering solutions.
Approach:	They propose a retrieval-augmented generation system that leverages tree-based exploration and bi-point thinking mechanism to generate reliable solutions.
Outcome:	Experiments show that the proposed system achieves state-of-the-art (SOTA) performance on the SolutionBench, highlighting its potential to enhance the automation and reliability of complex engineering solution design in real-world applications.

NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning (2025.acl-long)

Copied to clipboard

Zheyuan Zhang, Yiyang Li, Nhi Ha Lan Le, Zehong Wang, Tianyi Ma, Vincent Galassi, Keerthiram Murugesan, Nuno Moniz, Werner Geyer, Nitesh V Chawla, Chuxu Zhang, Yanfang Ye

Multimodality

Challenge:	Diet plays a critical role in human health, but tailoring dietary reasoning to individual health conditions remains a challenge.
Approach:	a new benchmark evaluates dietary reasoning using a national health survey data set.
Outcome:	The NGQA benchmark evaluates dietary reasoning across three tasks using a set of question complexity settings and baseline models.

ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select (2022.emnlp-main)

Copied to clipboard

Yuchen Zhuang, Yinghao Li, Junyang Zhang, Yue Yu, Yingjun Mou, Xiang Chen, Le Song, Chao Zhang

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)

Challenge:	Our proposed method extracts N-ary relation tuples from scientific articles.
Approach:	They propose a method that decomposes the task into two stages . they propose modal query and modal entity selection . their results show that ReSel outperforms state-of-the-art baselines significantly .
Outcome:	The proposed method outperforms state-of-the-art baselines on three scientific information extraction datasets.

Copied to clipboard

Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu

MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora (2025.emnlp-main)

Challenge:	Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts.
Approach:	They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs.
Outcome:	The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks.

Copied to clipboard

Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang, Trung Le, Dragan Gasevic, Yuan-Fang Li, Thanh-Toan Do

READoc: A Unified Benchmark for Realistic Document Structured Extraction (2025.findings-acl)

Challenge:	Existing approaches to update model-based indexes with new documents are expensive and require expensive retraining.
Approach:	They propose a framework that combines an expandable mixture of Low-Rank Adaptation experts with a layer-wise out-of-distribution-driven expansion strategy.
Outcome:	Experiments on NQ320k and MS MARCO Passage show that the proposed framework outperforms full-model update baselines with minimal parameter overhead and substantially lower training costs.

Copied to clipboard

Zichao Li, Aizier Abulaiti, Yaojie Lu, Xuanang Chen, Jia Zheng, Hongyu Lin, Xianpei Han, Shanshan Jiang, Bin Dong, Le Sun

All Information is Valuable: Question Matching over Full Information Transmission Network (2022.findings-naacl)

Challenge:	Document Structured Extraction (DSE) is a field of document structure analysis that aims to extract structured content from raw documents.
Approach:	They propose a benchmark to evaluate document structured extraction systems by converting unstructured PDFs into semantically rich Markdown.
Outcome:	The proposed benchmark is based on 3,576 diverse and real-world documents from arXiv, GitHub, and Zenodo.

Copied to clipboard

Le Qi, Yu Zhang, Qingyu Yin, Guidong Zheng, Wen Junjie, Jinlong Li, Ting Liu

Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning (2024.findings-emnlp)

Challenge:	Existing methods for question matching only transmit one kind of information while failing to utilize both kinds of information simultaneously.
Approach:	They propose a question matching network that can transmit both representation and interactive information together in a simultaneous fashion.
Outcome:	The proposed approach outperforms strong baseline models on two standard benchmarks.

Copied to clipboard

Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Kumar Dubey, Alexandre Rame, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Leonard Hussenot, Olivier Bachem, Edouard Leurent

Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021.acl-long)

Challenge:	Existing approaches for multi-objective Reinforcement Learning (RL) are difficult due to plurality of preferences and applications.
Approach:	They propose a framework for finetuning language models on multiple objectives using conditional language policy.
Outcome:	The proposed framework outperforms and Pareto-dominates existing approaches for multi-objective Reinforcement Learning (RL) it does not require training or maintaining multiple models to achieve different trade-offs between the objectives.

Copied to clipboard

Yaojie Lu, Hongyu Lin, Jin Xu, Xianpei Han, Jialong Tang, Annan Li, Le Sun, Meng Liao, Shaoyi Chen

BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition (2021.acl-long)

Challenge:	Existing methods to extract event records from text decompose complex structure prediction task into multiple subtasks.
Approach:	They propose a sequence-to-structure generation paradigm that can extract events from text . they propose unified event extraction, constrained decoding algorithm and curriculum learning algorithm .
Outcome:	The proposed method can achieve competitive performance using record-level annotations in both supervised learning and transfer learning settings.

Copied to clipboard

Yinghao Li, Pranav Shetty, Lucas Liu, Chao Zhang, Le Song

Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision (2024.findings-emnlp)

Challenge:	Existing NER models are supervised by a large number of training sequences, each pre-annotated with token-level labels.
Approach:	They propose a conditional hidden Markov model which can effectively infer true labels from multi-source noisy labels in an unsupervised way.
Outcome:	The proposed model outperforms state-of-the-art weakly supervised NER models on four benchmarks from various domains.

Copied to clipboard

Zihan Wang, Yunxuan Li, Yuexin Wu, Liangchen Luo, Le Hou, Hongkun Yu, Jingbo Shang

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

Challenge:	a method for process supervision has shown significant improvements in multi-step problem solving . despite the advances in process supervision, there are still easily observable mistakes in state-of-the-art LLMs.
Approach:	They propose a method for automating data curation by using a trained verifier to evaluate intermediate steps generated by a reasoner.
Outcome:	The proposed method improves the performance of PaLM 2 on math and coding tasks.

Copied to clipboard

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

Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations (2024.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

Lvxue Li, Jiaqi Chen, Xinyu Lu, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning (2025.findings-acl)

Challenge:	In-context learning (ICL) has gained considerable attention due to its data efficiency and task adaptability.
Approach:	They propose to de-biase demonstration bias in in-context learning by focusing on semantic ambiguity induced by demonstrations and reducing the semantic hazard.
Outcome:	The proposed methods significantly improve performance on six datasets.

Copied to clipboard

Dacao Zhang, Kun Zhang, Shimao Chu, Le Wu, Xin Li, Si Wei

The UIR Uncertainty Corpus for Chinese: Annotating Chinese Microblog Corpus for Uncertainty Identification from Social Media (L18-1)

Challenge:	Recent advances in Large Language Models (LLMs) have revolutionized various domains, offering unprecedented performance across numerous tasks.
Approach:	They propose a new Mixture of Low-Rank Experts (MoRE) for multi-task PEFT to improve performance of LLMs with fewer parameters.
Outcome:	The proposed method improves performance over multiple tasks and no additional inference cost.

Copied to clipboard

Binyang Li, Jun Xiang, Le Chen, Xu Han, Xiaoyan Yu, Ruifeng Xu, Tengjiao Wang, Kam-fai Wong

Challenge:	Uncertainty identification is an important semantic processing task, critical to the quality of information in terms of factuality in many NLP techniques and applications.
Approach:	They propose to annotate Chinese microblogs with an open uncertainty corpus . they propose to use contextual uncertain semantics rather than traditional cue-phrases to identify uncertainty .
Outcome:	The proposed corpus can be used to identify uncertainty in social media texts.

Transferable Post-training via Inverse Value Learning (2025.naacl-long)

Copied to clipboard

Xinyu Lu, Xueru Wen, Yaojie Lu, Bowen Yu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, Yongbin Li

ChatHF: Collecting Rich Human Feedback from Real-time Conversations (2024.emnlp-demo)

Challenge:	Existing algorithms for post-training large datasets are requiring a large computational effort.
Approach:	They propose to model the changes at logits level during post-training using a separate neural network . they demonstrate that the value network can be seamlessly integrated with another pre-trained model .
Outcome:	The proposed model can be integrated with another pre-trained model during inference, enabling similar capability enhancements.

Copied to clipboard

Andrew Li, Zhenduo Wang, Ethan Mendes, Duong Le, Wei Xu, Alan Ritter

Dialogue Systems & Conversational Agents

Challenge:	We present an interactive framework for chatbot evaluation that integrates configurable annotation within a chat interface.
Approach:	They propose an interactive framework for chatbot evaluation that integrates configurable annotation within a chat interface.
Outcome:	The proposed framework supports fine-grained error detection and human evaluation at the same time.

ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning (2020.emnlp-main)

Copied to clipboard

Michael Boratko, Xiang Li, Tim O’Gorman, Rajarshi Das, Dan Le, Andrew McCallum

A Fine-grained Chinese Software Privacy Policy Dataset for Sequence Labeling and Regulation Compliant Identification (2022.emnlp-main)

Challenge:	Existing question answering datasets for common sense reasoning are lacking for prototypical situations.
Approach:	They propose a question answering dataset for training and evaluating common sense reasoning capabilities of artificial intelligence systems in such prototypical situations.
Outcome:	The proposed model outperforms existing models on all evaluation metrics with a meaningful gap.

Copied to clipboard

Kaifa Zhao, Le Yu, Shiyao Zhou, Jing Li, Xiapu Luo, Yat Fei Aemon Chiu, Yutong Liu

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

Challenge:	Existing datasets that ignore law requirements are limited to English.
Approach:	They construct a Chinese privacy policy dataset that can be used to analyze software privacy policies.
Outcome:	The proposed dataset includes 483 Chinese Android privacy policies, over 11K sentences, and 52K fine-grained annotations.

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

Implicit Deep Latent Variable Models for Text Generation (D19-1)

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

Le Fang, Chunyuan Li, Jianfeng Gao, Wen Dong, Changyou Chen

Text Generation

Challenge:	Variational auto-encoders have been used for text generation but their representation power is limited due to two reasons.
Approach:	They advocate sample-based representations of variational distributions for natural language . they further develop an LVM to directly match the aggregated posterior to the prior .
Outcome:	The proposed model can be viewed as a natural extension of VAEs with a regularization of maximizing mutual information, mitigating the "posterior collapse" issue.

Towards Self-Improving Error Diagnosis in Multi-Agent Systems (2026.findings-acl)

Copied to clipboard

Jiazheng Li, Emine Yilmaz, Bei Chen, Thu Le

Distilling Text Style Transfer With Self-Explanation From LLMs (2024.naacl-srw)

Challenge:	Existing diagnostic approaches rely on expensive expert annotations and ”LLM-as-a-judge” paradigms.
Approach:	They propose a framework for semantic failure attribution that identifies responsible agents and the originating error step.
Outcome:	The proposed framework outperforms baselines in step-level localization and validation.

Copied to clipboard

Chiyu Zhang, Honglong Cai, Yuezhang Li, Yuexin Wu, Le Hou, Muhammad Abdul-Mageed

Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings (2025.acl-long)

Challenge:	Text Style Transfer (TST) aims to alter the style of text while preserving its core content.
Approach:	They propose a framework that leverages large language models alongside chain-of-thought prompting to facilitate TST.
Outcome:	The proposed framework surpasses supervised fine-tuning and knowledge distillation methods in low-resource settings.

Copied to clipboard

Chenghao Sun, Zhen Huang, Yonggang Zhang, Le Lu, Houqiang Li, Xinmei Tian, Xu Shen, Jieping Ye

AirDialogue: An Environment for Goal-Oriented Dialogue Research (D18-1)

Challenge:	Large language models excel at downstream NLP tasks through in-context learning . however, the internal mechanisms behind ICL remain under-explored .
Approach:	They propose a PC patching approach to identify modules where input-label mappings function . they observe and verify that key heads utilize input-labeled mappings to generate target labels for new queries.
Outcome:	The proposed approach detects modules where input-label mappings function . it also detects that key heads use the mappings to generate labels for new queries .

Copied to clipboard

Wei Wei, Quoc Le, Andrew Dai, Jia Li

Dialogue Systems & Conversational Agents

Challenge:	Recent advances in dialogue generation have inspired a number of studies on dialogue systems . however, current datasets are limited in size and the environment for training agents is relatively unsophisticated.
Approach:	They propose to use a context-generator to generate travel and flight restrictions to train agents.
Outcome:	The proposed model achieves a score of 0.17 while humans can reach 0.91 . the proposed model is based on a large dataset that contains 301,427 goal-oriented conversations .

SpARK: An Embarrassingly Simple Sparse Watermarking in LLMs with Enhanced Text Quality (2026.findings-eacl)

Copied to clipboard

Duy Cao Hoang, Thanh Quoc Hung Le, Rui Chu, Ping Li, Weijie Zhao, Yingjie Lao, Khoa D Doan

Challenge:	Existing methods for detecting and monitoring generated text face a trade-off between the quality of the generated text and the effectiveness of the watermarking process.
Approach:	They propose a new type of LLM watermark, Sparse WatermARK, which uses watermarks to a small subset of generated tokens distributed across the text.
Outcome:	The proposed method outperforms existing methods in detectability and quality while maintaining generated text quality.

Seg2Act: Global Context-aware Action Generation for Document Logical Structuring (2024.emnlp-main)

Copied to clipboard

Zichao Li, Shaojie He, Meng Liao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Yanxiong Lu, Xianpei Han, Le Sun

Challenge:	Document logical structuring is crucial for document intelligence due to the complexity of text segment dependencies in the document.
Approach:	They propose an end-to-end, generation-based method for document logical structuring that generates the action sequence via a global context-aware generative model and updates its global context and current logical structure based on the generated actions.
Outcome:	Experiments on ChCatExt and HierDoc datasets show that Seg2Act performs better than previous methods in both supervised and transfer learning settings.

CodeT5+: Open Code Large Language Models for Code Understanding and Generation (2023.emnlp-main)

Copied to clipboard

Yue Wang, Hung Le, Akhilesh Gotmare, Nghi Bui, Junnan Li, Steven Hoi

Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch (2025.acl-long)

Challenge:	Existing code LLMs adopt a specific architecture or rely on a unified encoder-decoder network for downstream tasks, lacking flexibility to operate in the optimal architecture for a particular task.
Approach:	They propose to initialize code LLMs with frozen off-the-shelf LLM and explore instruction-tuning to align with natural language instructions.
Outcome:	The proposed model outperforms open-source LLMs on 20 code-related benchmarks.

Copied to clipboard

Xueru Wen, Jie Lou, Zichao Li, Yaojie Lu, XingYu XingYu, Yuqiu Ji, Guohai Xu, Hongyu Lin, Ben He, Xianpei Han, Le Sun, Debing Zhang

Challenge:	Existing Chinese resources are small in scale and limited to specific domains, making them insufficient for LLM post-training.
Approach:	They propose a Chinese-annotated reward model and a preference dataset to address this gap . they evaluate Chinese RMs on CheemsBench and construct an RM that captures human preferences .
Outcome:	The proposed RM achieves state-of-the-art performance on CheemsBench and CheeMePreference.

From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs (2025.acl-long)

Copied to clipboard

Jialun Cao, Yaojie Lu, Meiziniu Li, Haoyang Ma, Haokun Li, Mengda He, Cheng Wen, Le Sun, Hongyu Zhang, Shengchao Qin, Shing-Chi Cheung, Cong Tian

Improving Multi-Agent Debate with Sparse Communication Topology (2024.findings-emnlp)

Challenge:	Recent studies in formal mathematical reasoning have shown an unstoppable growth trend.
Approach:	They constructed 18k high-quality instruction-response pairs across five mainstream formal specification languages and evaluated them against ten open-sourced LLMs.
Outcome:	The proposed model compared instruction-response pairs across five formal specification languages and found that the LLMs were good at writing proof segments when given either the code, or the detailed description of proof steps.

Copied to clipboard

Yunxuan Li, Yibing Du, Jiageng Zhang, Le Hou, Peter Grabowski, Yeqing Li, Eugene Ie

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Existing approaches to multi-agent debates use a brute force algorithm, resulting in a computationally intensive process.
Approach:	They propose to extend the multi-agent debate framework to multi-modal reasoning and alignment labeling tasks, showcasing its broad applicability and effectiveness.
Outcome:	The proposed framework can achieve comparable or superior performance while significantly reducing computational costs.

Copied to clipboard

Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, Jinsong Su

Beyond Sentence-level Labels: Integrating Conversational Context and Personal Experience for Natural Emotional Expression (2026.findings-acl)

Challenge:	Existing faithful RAG approaches enforce strict context adherence, but they forcibly suppress the model’s parametric knowledge, which undermines the model's internal knowledge structure and increases the risk of misinterpreting the context.
Approach:	They propose a framework that resolves knowledge conflicts by explicitly modeling discrepancies between the model’s parametric knowledge and retrieved context.
Outcome:	The proposed framework outperforms state-of-the-art methods in knowledge conflict cases and identifies conflicting knowledge at the fact level and designs a self-thinking process.

Copied to clipboard

Haiyang Sun, Chenyang Le, Wei Wang, Leying Zhang, Chuang Li, Bing Han, Chenda Li, Mengxiao Bi, Yanmin Qian

Dialogue Systems & Conversational Agents

Challenge:	Existing systems rely on sentence-level labels, which fails to capture the subtle nuances of human affect.
Approach:	They propose to use a large-scale, context-aware speech corpus derived from multi-speaker audiobooks to generate a speech that is human-like.
Outcome:	The proposed model outperforms existing methods in terms of emotional expression accuracy and naturalness.

Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition (2022.findings-emnlp)

Copied to clipboard

Suyoun Kim, Ke Li, Lucas Kabela, Ron Huang, Jiedan Zhu, Ozlem Kalinli, Duc Le

Semantic Text Processing

Challenge:	Recent studies have shown that streaming end-to-end speech recognition models suffer from higher word error rates (WER) compared to non-streaming models, streaming endto-ended ASR models are limited to short audio context or not use future context to satisfy low latency constraints.
Approach:	They propose a 2nd-pass rescoring model on top of the 1st-pass streaming model to improve recognition accuracy while keeping latency low.
Outcome:	The proposed method improves word error rate significantly compared to the existing model without adding any additional parameters or latency.

GlossaGen: Making Academic Translation Smarter with Glossing (2026.findings-acl)

Copied to clipboard

Zixiao Wang, Duzhen Zhang, Juntian Zhang, Yuhan Liu, Guoming Li, Haolun Wu, Le Song, Xiuying Chen

StitchLLM: Serving LLMs, One Block at a Time (2025.acl-long)

Challenge:	Existing machine translation systems obscure or mistranslate key terminology, while paraphrasing aimed at lay readers often oversimplifies it, hindering their ability to master domain-specific technical vocabulary.
Approach:	They propose a task which produces translations dynamically adapted to a reader’s academic proficiency, or level, and a framework to address this challenge.
Outcome:	The proposed framework achieves higher scores than baselines on a synthesized benchmark and human evaluations.

Copied to clipboard

Bodun Hu, Shuozhe Li, Saurabh Agarwal, Myungjin Lee, Akshay Jajoo, Jiamin Li, Le Xu, Geon-Woo Kim, Donghyun Kim, Hong Xu, Amy Zhang, Aditya Akella

HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts (2023.emnlp-main)

Challenge:	Existing techniques like distillation and pruning are not efficient for large language models.
Approach:	They propose a dynamic model routing framework that uses a powerful bottom model to process all queries and a lightweight routing mechanism to allocate computational resources appropriately.
Outcome:	The proposed framework improves system throughput while minimizing performance degradation.

Copied to clipboard

Truong Do, Le Khiem, Quang Pham, TrungTin Nguyen, Thanh-Nam Doan, Binh Nguyen, Chenghao Liu, Savitha Ramasamy, Xiaoli Li, Steven Hoi

ClaimLens: Automated, Explainable Fact-Checking on Voting Claims Using Frame-Semantics (2024.emnlp-demo)

Challenge:	Recent studies suggest that fixing the routers can achieve competitive performance by alleviating the collapsing problem, where all experts eventually learn similar representations.
Approach:	They propose a method that dynamically generates router parameters through a fixed hypernetwork and trainable embeddings to achieve a balance between training the routers and freezing them to learn an improved routing policy.
Outcome:	Experiments on a wide range of tasks show that the proposed method performs better than existing methods.

Copied to clipboard

Jacob Devasier, Rishabh Mediratta, Phuong Le, David Huang, Chengkai Li

KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)

Challenge:	Existing fact-checking solutions lack transparency and explainability . a lack of transparency can make it difficult for users to trust and understand the reasoning behind the outcomes.
Approach:	They propose an automated fact-checking system focused on voting-related factual claims that leverages frame-semantic parsing to provide structured and interpretable fact verification.
Outcome:	The proposed system can extract relevant information from voting-related factual claims using public records and Vote semantic frame.

Copied to clipboard

Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng Li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu

CodecLM: Aligning Language Models with Tailored Synthetic Data (2024.findings-naacl)

Challenge:	Recent advances in pre-trained language models have made it possible to generate human-like text.
Approach:	They propose to integrate an open-ended text adventure game in Chinese, named KuiLeiXi, where players interact with the AI until the plot goals are reached.
Outcome:	The proposed game lacks incentives and relies on players to explore on their own.

Copied to clipboard

Zifeng Wang, Chun-Liang Li, Vincent Perot, Long Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister

SoFA: Shielded On-the-fly Alignment via Priority Rule Following (2024.findings-acl)

Challenge:	Recent work on generating diverse instructions and applying LLM to increase instruction complexity neglects downstream use cases.
Approach:	They propose a framework for generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs.
Outcome:	Experiments on four open-domain instruction using the proposed framework validate the effectiveness of CodecLM over the current state-of-the-art.

Copied to clipboard

Xinyu Lu, Bowen Yu, Yaojie Lu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, Yongbin Li