Papers by Lian Lian

MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization (2025.findings-emnlp)

Challenge:	Recent advances in reasoning with large language models have popularized Long Chain-of-Thought (LCoT) a framework that converts sequential LCoTs into hierarchical tree structures enables deeper structural analysis of LLM reasoning.
Approach:	They propose a framework that converts sequential LCoTs into hierarchical tree structures and enables deeper structural analysis of LLM reasoning.
Outcome:	The proposed framework can be used to analyze LLM reasoning in a variety of tasks and models.

Copied to clipboard

Yinhong Liu, Jianfeng He, Hang Su, Ruixue Lian, Yi Nian, Jake W. Vincent, Srikanth Vishnubhotla, Robinson Piramuthu, Saab Mansour

Sequential LLM Framework for Fashion Recommendation (2024.emnlp-industry)

Challenge:	Multimodal Dialogue Summarization (MDS) is a critical task with wide-ranging applications.
Approach:	They propose a meta-evaluation benchmark for multimodal dialogue summarization based on image-sharing dialogues, corresponding summaries and human judgments .
Outcome:	The proposed framework is the first to identify and formalize key evaluation dimensions specific to MDS.

Copied to clipboard

Han Liu, Xianfeng Tang, Tianlang Chen, Jiapeng Liu, Indu Indu, Henry Zou, Peng Dai, Roberto Galan, Michael Porter, Dongmei Jia, Ning Zhang, Lian Xiong

D2-RAG: Dual-Decision Retrieval-Augmented Generation via Multi-Dimensional Uncertainty and Utility-Aware Decoding (2026.findings-acl)

Challenge:	Existing fashion recommendation systems struggle with the unique challenges of the fashion domain.
Approach:	They propose a sequential fashion recommendation framework that leverages a pre-trained large language model enhanced with recommendation-specific prompts.
Outcome:	The proposed framework significantly improves fashion recommendation performance on Amazon fashion.

Copied to clipboard

Jinshuo Zhang, Xiaoding Zhou, Weiyu Zhang, Guoqiang Chen, Ying Lian, Xiaoyang Meng, Yonghe Chen, Hongjiao Guan, Jiasheng Si, Wenpeng Lu

MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance (2024.emnlp-main)

Challenge:	Retrieval-Augmented Generation (RAG) mitigates hallucinations in large language models by incorporating external knowledge.
Approach:	They propose a dual-decision retrieval-augmented generation that integrates multi-dimensional uncertainty estimation to decide whether to retrieve and employs adaptive contrastive decoding to handle retrieved contexts of varying quality.
Outcome:	The proposed model outperforms baselines on four medical question-answering datasets while suppressing interference from noisy contexts.

Copied to clipboard

Renjie Pi, Tianyang Han, Jianshu Zhang, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang

MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models? (2025.findings-acl)

Challenge:	MLLMs are deployed on limited image-text pairs, which makes them more vulnerable to catastrophic forgetting of their original abilities during safety fine-tuning.
Approach:	They propose a plug-and-play strategy that detects harmful visual inputs and transforms harmful ones into harmless ones.
Outcome:	The proposed approach mitigates the risks posed by malicious visual inputs without compromising the original performance of MLLMs.

Copied to clipboard

Xixian Yong, Jianxun Lian, Xiaoyuan Yi, Xiao Zhou, Xing Xie

CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion (2025.emnlp-main)

Challenge:	Existing benchmarks for large language models lack information asymmetry with real-world situations.
Approach:	They propose a benchmark to evaluate the human-like motivational and behavioral reasoning ability of LLMs with detailed, realistic situations.
Outcome:	The proposed benchmark compared LLMs with real-world scenarios on seven model families and found that the most advanced models struggle with understanding "love & belonging" needs.

Copied to clipboard

Sheng Zhang, Yifan Ding, Shuquan Lian, Shun Song, Hui Li

Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge (2025.findings-naacl)

Challenge:	Recent advances in code large language models have produced repository-level code completion methods that automatically predict the unfinished code based on the broader information from the repository.
Approach:	They propose a framework to identify relevant knowledge for retrieval-augmented repository-level code completion.
Outcome:	The proposed framework significantly outperforms state-of-the-art methods on ReccEval and CCEval.

Copied to clipboard

Lian Remme, Kevin Tang

CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions (2024.emnlp-main)

Challenge:	Using a small dataset, we propose that audio of tabletop role-playing games (TTRPGs) could serve as a challenge for speaker diarization systems.
Approach:	They propose that audio of tabletop role-playing games (TTRPGs) could serve as a challenge for speaker diarization systems.
Outcome:	The proposed system can pick the speaker and determine that impersonating is just that.

Copied to clipboard

Jun Rao, Xuebo Liu, Lian Lian, Shengjun Cheng, Yunjie Liao, Min Zhang

Enhancing Persona Consistency for LLMs’ Role-Playing using Persona-Aware Contrastive Learning (2025.findings-acl)

Challenge:	Current studies have focused on fine-tuning, but the use of instruction tuning is not as effective as fine-cuning.
Approach:	They propose a commonality-aware instruction tuning strategy to cluster instruction datasets into distinct groups with three proposed metrics Task, Embedding and Length.
Outcome:	The proposed strategy boosts an average improvement of 2.1% on the general domain and 5.2% on the special domain.

Copied to clipboard

Ke Ji, Yixin Lian, Linxu Li, Jingsheng Gao, Weiyuan Li, Bin Dai

On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)

Challenge:	Existing methods for analyzing and analyzing large language models (LLMs) lack of emotion and fine-grained role awareness limits the model’s ability to provide personalized and diverse interactions further.
Approach:	They propose an annotation-free framework to align LLMs’ behavior during role-playing, enhancing the model’s role consistency.
Outcome:	The proposed framework outperforms vanilla LLMs under automatic evaluation methods and human expert evaluation.

Copied to clipboard

Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu

LiveCANNBench: Benchmark SWE AI Coding for Ascend CANN (2026.findings-acl)

Challenge:	Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited.
Approach:	They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO).
Outcome:	The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness.

Copied to clipboard

Sijie Wang, Kai Zhao, Wee Peng Tay, Shuo Zhang, Chengwen Liu, Quanjiang Guo, Ren Junhao, Xin Li, Heng Lian, Jingdi Lei, Rui She, Huacan Wang, Ronghao Chen

Challenge:	Recent advances in agents have enabled multi-file, multi-language, and dependency-aware AI coding.
Approach:	They propose an SWE-level benchmark for AI coding in the Huawei Ascend CANN software stack.
Outcome:	The proposed benchmark is constructed from real-world CANN repositories and consists of over 400 task instances spanning multiple file, multi-language, and execution-aware coding challenges.

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)

Copied to clipboard

Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen

Challenge:	Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios.
Approach:	They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance.
Outcome:	The proposed framework improves model capabilities across all domains and scales.

Beyond Surface Simplicity: Revealing Hidden Reasoning Attributes for Precise Commonsense Diagnosis (2025.acl-long)

Copied to clipboard

Huijun Lian, Zekai Sun, Keqi Chen, Yingming Gao, Ya Li

Temporal Scaling Law for Large Language Models (2025.emnlp-main)

Challenge:	Existing commonsense question answering benchmarks often treat these aspects in isolation, resulting in evaluation accuracy differences of up to 24.8% across different difficulty levels.
Approach:	They propose a framework that reveals hidden reasoning attributes behind commonsense questions by leveraging the knowledge generated during the reasoning process.
Outcome:	The proposed framework reveals hidden reasoning attributes behind commonsense questions by leveraging the knowledge generated during the reasoning process.

Copied to clipboard

Yizhe Xiong, Xiansheng Chen, Xin Ye, Hui Chen, Zijia Lin, Haoran Lian, Zhenpeng Su, Wei Huang, Jianwei Niu, Jungong Han, Guiguang Ding

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models (2026.findings-acl)

Challenge:	Existing studies have found that the test loss of LLMs scales as power-laws with model size, computational budget, and dataset size.
Approach:	They propose a concept of Temporal Scaling Law to study test loss of LLMs . they break down test loss into fine-grained token positions and develop a dynamic hyperbolic-law .
Outcome:	The proposed model predicts the test loss of LLMs as the training steps scale up.

Copied to clipboard

Jizhihui Liu, Guangdao Zhu, Feiyi Du, Niu Lian, Jun Li, Bin Chen, Weili Guan, Yaowei Wang

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs (2024.emnlp-main)

Challenge:	Existing methods for visual token pruning lack insight into the intrinsic property of the vision encoder . et al., 2017: 99.3% of task accuracy with only 1/3 of the tokens.
Approach:	They propose a model-agnostic token pruning method that trains without training . they propose 'HiPrune' method which prunes visual tokens according to their attention .
Outcome:	The proposed method achieves 99.3% of task accuracy with only 1/3 of the tokens . it reduces inference FLOPs by 58.7% and maintains 99.99% accuracy with 2/9 tokens.

Copied to clipboard

Tianyang Han, Qing Lian, Rui Pan, Renjie Pi, Jipeng Zhang, Shizhe Diao, Yong Lin, Tong Zhang

Train Once, and Decode As You Like (2020.coling-main)

Challenge:	Existing multi-modal large language models (MLLMs) are able to process visual inputs by converting them into visual tokens that share the same latent space as language tokens in LLMs.
Approach:	They propose a benchmark that assesses the visual illusion level given spurious images and a pipeline that converts visual inputs into visual tokens.
Outcome:	The proposed benchmark shows that MLLMs suffer from an instinctive bias to varying degrees when presented with spurious images.

Copied to clipboard

Chao Tian, Yifei Wang, Hao Cheng, Yijiang Lian, Zhihua Zhang

JointCoder: Exploring Automated ICD Coding on Real-World Chinese EHRs with a Multi-Agent Framework (2026.acl-demo)

Challenge:	Existing approaches to machine translation support autoregressive, semi-autoregressive and refinement-based non-auto-regressives.
Approach:	They propose a unified approach for supporting different generation manners of machine translation including autoregressive, semi-autoregressive and refinement-based non-auto-regressives.
Outcome:	The proposed approach achieves better or competitive translation performance compared with strong baseline models in all the settings.

Copied to clipboard

Kangjun Liu, Zhenyu Li, Jianlei Wang, Hongjiao Guan, Ying Lian, Guoqiang Chen, Tao Xin, Wenpeng Lu

Challenge:	Existing automated ICD coding systems face several fundamental challenges due to the limited availability of publicly available Chinese ICD datasets.
Approach:	They propose to use a Chinese ICD coding dataset and a multi-agent framework to reformulate ICD as a joint disease-procedure coding task.
Outcome:	The proposed system outperforms state-of-the-art methods on real-world Chinese ICD coding datasets and 1.7B-parameter models.

RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations (2025.findings-acl)

Copied to clipboard

Lian Yan, Chen Tang, Yi Guan, Haotian Wang, Songyuan Wang, Haifeng Liu, Yang Yang, Jingchi Jiang

Structured Data in NLP

Challenge:	Lack of human preference labels remains a significant bottleneck when applying RLHF to a downstream domain.
Approach:	They propose a method that leverages human priors encoded in Knowledge Graphs (KGs) to derive RL rewards in the absence of manual annotations.
Outcome:	Experiments on three public and one private medical dialogue datasets show that the proposed method outperforms the competitive RLAIF in improving LLM diagnostic accuracy.

Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation (2025.findings-acl)

Copied to clipboard

Zhuofan Wen, Zheng Lian, Shun Chen, Hailiang Yao, Longjiang Yang, Bin Liu, Jianhua Tao

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

Challenge:	Existing methods to assess human emotion are limited by the subjective nature of emotion perception, limiting the robustness of existing models.
Approach:	They propose a plug-and-play module that enhances MLLMs’ ability to tackle compound and context-rich emotion tasks.
Outcome:	The proposed framework improves MLLMs' ability to tackle compound and context-rich emotion tasks and the Compound Emotion QA dataset shows it performs well across both benchmarks and evaluation frameworks.

Copied to clipboard

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

GSID: Generative Semantic Indexing for E-Commerce Product Understanding (2025.emnlp-industry)

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

Copied to clipboard

Haiyang Yang, Qinye Xie, Qingheng Zhang, Chen Li Yu, Huike Zou, Chengbao Lian, Shuguang Han, Fei Huang, Jufeng Chen, Bo Zheng

Curriculum Consistency Learning for Conditional Sentence Generation (2024.emnlp-main)

Challenge:	Structured product information is a major bottleneck for the efficiency of e-commerce platforms.
Approach:	They propose a data-driven approach to generate product structured representations using product metadata.
Outcome:	Extensive experiments show that GSID can generate better product representations on real-world e-commerce platforms.

Copied to clipboard

Liangxin Liu, Xuebo Liu, Lian Lian, Shengjun Cheng, Jun Rao, Tengfei Yu, Hexuan Deng, Min Zhang

Evaluating Readability and Faithfulness of Concept-based Explanations (2024.emnlp-main)

Challenge:	Consistency learning (CL) has proven to be a valuable technique for improving the robustness of conditional sentence generation models.
Approach:	They propose a strategy that guides models to learn consistency in alignment with their current capacity to differentiate between features.
Outcome:	The proposed strategy delivers +2.0 accuracy point improvement compared with vanilla IT and +0.7 COMET scores over traditional CL methods in MT tasks.

Copied to clipboard

Meng Li, Haoran Jin, Ruixuan Huang, Zhihao Xu, Defu Lian, Zijia Lin, Di Zhang, Xiting Wang

Explainability & Interpretability in NLP

Challenge:	Existing methods for evaluating concepts from different perspectives lack a unified formalization.
Approach:	They propose a formal definition of concepts generalizing to diverse concept-based explanations’ settings and apply it to other types of explanations or tasks.
Outcome:	Extensive experimental analysis was carried out to determine the evaluation measures for explanation evaluation measures.

M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation (2024.findings-acl)

Copied to clipboard

Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, Zheng Liu

DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models (2023.emnlp-main)

Challenge:	In this paper, we introduce a new embedding model for semantic retrieval of more than 100 working languages.
Approach:	They propose a new embedding model that supports multi-lingual, cross-lingual and long-document retrieval . they propose integrating relevance scores from different retrieval functionalities into the teacher signal .
Outcome:	The proposed model exhibits superior performance on multilingual, cross-lingual, and long-document retrieval benchmarks.

Copied to clipboard

Chengcheng Han, Xiaowei Du, Che Zhang, Yixin Lian, Xiang Li, Ming Gao, Baoyuan Wang

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

Challenge:	Chain-of-Thought prompting has improved the reasoning capabilities of Large Language Models (LLMs) but it is ineffective or detrimental to the performance on reasoning tasks in Smaller Language Model (SLMs) with less than 10 billion parameters.
Approach:	They propose a Dialogue-guided Chain-of-Thought method to improve the reasoning capabilities of Large Language Models (LLMs) by generating intermediate reasoning steps in a dialogue format to guide the model to the final answer.
Outcome:	The proposed method can achieve significant performance gains over state-of-the-art competitors on four arithmetic reasoning datasets.

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.

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing (2024.emnlp-main)

Copied to clipboard

Weichuan Wang, Zhaoyi Li, Defu Lian, Chen Ma, Linqi Song, Ying Wei

Machine Translation

Challenge:	Existing studies have focused on using Large Language Models to improve translation quality . language mismatch and repetition are two of the main problems with LLMs .
Approach:	They propose to leverage model editing methods to reduce language mismatch and repetition . they propose to fetch intersections of locating results under different language settings .
Outcome:	The proposed methods reduce language mismatch and repetition ratios and enhance translation quality in most cases.

Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off (2023.tacl-1)

Copied to clipboard

Yuchen Lian, Arianna Bisazza, Tessa Verhoef

Challenge:	Existing models of language learning with neural agents lack appropriate cognitive biases in artificial learners.
Approach:	They propose a framework where speaking and listening agents learn a miniature language via supervised learning and optimize it for communication via reinforcement learning.
Outcome:	The proposed framework replicates the word-order/case-marking trade-off without hard-coding biases in the agents.

Mixture of Heterogeneous Grouped Experts for Language Modeling (2026.acl-industry)

Copied to clipboard

Zhicheng Ma, Xiang Liu, Zhaoxiang Liu, Ning Wang, Yi Shen, Kai Wang, Shuming Shi, Shiguo Lian

LightVLP: A Lightweight Vision-Language Pre-training via Gated Interactive Masked AutoEncoders (2024.lrec-main)

Challenge:	Large Language Models (LLMs) based on Mixture-of-Experts (MoE) enforce uniform expert sizes, creating a rigidity that fails to align computational costs with varying token-level complexity.
Approach:	They propose a mixture of heterogeneous grouped experts (MoHGE) that allows for flexible, resource-aware expert combinations.
Outcome:	The proposed model matches the performance of existing Mixture-of-Experts architectures while maintaining balanced GPU utilization.

Copied to clipboard

Xingwu Sun, Zhen Yang, Ruobing Xie, Fengzong Lian, Zhanhui Kang, Chengzhong Xu

MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval (2025.acl-long)

Challenge:	Existing vision-language pre-training models use multi-modal encoders to encode image and text, causing noisy training corpora.
Approach:	They propose a vision-language pre-training framework with two autoencoders for efficient training . they propose masked tokens and a gated interaction mechanism to cope with noise .
Outcome:	The proposed model achieves 2.2% R@1 gains on COCO Text Retrieval and 1.1% on refCOCO+ on six datasets.

Copied to clipboard

Junjie Zhou, Yongping Xiong, Zheng Liu, Ze Liu, Shitao Xiao, Yueze Wang, Bo Zhao, Chen Jason Zhang, Defu Lian

Document-level Biomedical Relation Extraction Based on Multi-Dimensional Fusion Information and Multi-Granularity Logical Reasoning (2022.coling-1)

Challenge:	despite the growing demand for multimodal retrieval, there is a lack of training data.
Approach:	They propose a data synthesis method that leverages vision language models and open-domain images to generate high-quality data.
Outcome:	The proposed method outperforms baseline models on 70 more datasets and can scale up.

Copied to clipboard

Lishuang Li, Ruiyuan Lian, Hongbin Lu, Jingyao Tang

Information Extraction & Text Mining

Challenge:	Existing models with reasoning are single-granularity based on one element information, ignoring complementary fact of different granularities.
Approach:	They propose a document-level biomedical relation extraction model called FILR . it uses multi-dimensional information fusion and multi-granularity logic to obtain rich inferences .
Outcome:	The proposed model extracts all relation facts from biomedical documents . it is based on multi-dimensional information fusion and multi-granularity logic reasoning . the proposed model achieves state-of-the-art performance on two widely used biomedically corpora .

Agri-CM3: A Chinese Massive Multi-modal, Multi-level Benchmark for Agricultural Understanding and Reasoning (2025.acl-long)

Copied to clipboard

Haotian Wang, Yi Guan, Fanshu Meng, Chao Zhao, Lian Yan, Yang Yang, Jingchi Jiang

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation (2026.acl-long)

Challenge:	Existing benchmarks lack comprehensive evaluations, particularly in multi-level reasoning, making it difficult to identify model limitations.
Approach:	They propose to use Agri-CM3 to assess multi-level reasoning in agricultural management by integrating multiple data modalities.
Outcome:	The Agri-CM3 benchmark includes 3,939 images and 15,901 multi-level multiple-choice questions with detailed explanations.

Copied to clipboard

Erel Kaplan, Tomer Bitan, Lian Ghrayeb, Le Chen, Tom Yotam, Niranjan Hasabnis, Gal Oren

Knowing-but-Doing: Diagnosing and Defending Role-Play-Driven LLMs Jailbreaks via Moral Disengagement (2026.findings-acl)

Challenge:	Parallel programming is central to modern highperformance computing, but producing parallel implementations that are correct and fast remains arduous.
Approach:	They propose a workflow that turns a Codex-based agent into an autonomous OpenMP GPU offload system . they use staged hotspot analysis, explicit data planning, correctness gating, profiling-guided refinement .
Outcome:	The proposed system outperforms a Codex-based agent on HeCBench, Rodinia, and NAS.

Copied to clipboard

Haiming Qin, Jianxun Lian, Qimin Zhong, Mingyang Zhou, Hao Liao, Naipeng Chao

ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval (2026.acl-long)

Challenge:	Large Language Models (LLMs) are increasingly used in role-play scenarios, but their safety implications remain under-characterized.
Approach:	They propose a diagnostic benchmark for role-play jailbreaks based on Bandura’s Moral Disengagement theory and propose 'MD-Trace' based defense that reduces attack success while maintaining Role Fidelity.
Outcome:	The proposed framework improves safety behavior for benign personas while increasing unsafe compliance for malicious ones.

Copied to clipboard

Jianlyu Chen, Junwei Lan, Chaofan Li, Defu Lian, Zheng Liu

Representation Learning

Challenge:	Recent studies suggest that traditional retrievers struggle with reasoningintensive tasks such as personal assistants and scientific research.
Approach:	They propose a new data synthesis method that overcomes the triviality problem prevalent in previous synthetic datasets and propose 'ReMixer', a data fusion method that generates 82K high-quality training samples.
Outcome:	The proposed model outperforms existing models on reasoning-intensive retrieval tasks.

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

Copied to clipboard

Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu

Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning (2024.findings-acl)

Challenge:	In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach:	They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome:	The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.

Copied to clipboard

Chenyuan Wu, Gangwei Jiang, Defu Lian

Proactive Human-Machine Conversation with Explicit Conversation Goal (P19-1)

Challenge:	Existing approaches to improve the performance of lifelong prompt tuning are limited due to inherent challenges.
Approach:	They propose a similarity heuristic lifelong prompt tuning framework that partitions tasks into two distinct subsets by harnessing a learnable similarity measure.
Outcome:	The proposed framework outperforms state-of-the-art techniques in lifelong learning benchmarks and demonstrates robustness against negative transfer in diverse task sequences.

Copied to clipboard

Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian, Haifeng Wang

Natural Language Interfaces

Challenge:	Typical human-machine conversation systems only use utterances and responses as training data, which results in uninformative and inappropriate responses.
Approach:	They propose a dataset where one acts as a conversation leader and the other as 'follower' they establish baseline results on a 270K utterances and 30k dialogues dataset using state-of-the-art models.
Outcome:	The proposed model can generate diverse multi-turn conversations using knowledge from a new dataset .

Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View (2026.findings-acl)

Copied to clipboard

Hao Liao, Jiwei Zhang, Jianxun Lian, Wensheng Lu, Mingqi Wu, null Shuowangg, Yong Zhang, Yitian Huang, Mingyang Zhou, Rui Mao

LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming (2023.acl-long)

Challenge:	Existing approaches to reduce OOD recommendations fall into three grounding paradigms: retrieval, constrained generation and discrete item tokenizer generation.
Approach:	They propose a framework that instantiates three grounding paradigms under a single architecture . embedding-based retrieval, constrained generation and discrete item-tokenizer methods are implemented .
Outcome:	The proposed framework eradicates OOD recommendations across all variants and achieves state-of-the-art accuracy compared to strong ID-based and LLM-based baselines.

Copied to clipboard

Jingsheng Gao, Yixin Lian, Ziyi Zhou, Yuzhuo Fu, Baoyuan Wang

Constructing Procedural Graphs with Multiple Dependency Relations: A New Dataset and Baseline (2023.findings-acl)

Challenge:	a recent study shows that open-domain dialogue systems are not able to perform well in fast-growing scenarios such as live streaming due to the domain gap between online-post constructed data and those required in downstream conversational tasks.
Approach:	They propose to train a conversational agent based on large social media datasets with multiple domains to improve response in live streaming scenarios.
Outcome:	The proposed model improves response modeling and addressee recognition in live open-domain scenarios.

Copied to clipboard

Haopeng Ren, Yushi Zeng, Yi Cai, Bihan Zhou, Zetao Lian

Pretraining Context Compressor for Large Language Models with Embedding-Based Memory (2025.acl-long)

Challenge:	Existing methods to structure procedural knowledge focus on representing descriptive knowledge but ignore another commonsense knowledge-Procedural Knowledge.
Approach:	They propose to generate flow graphs from procedural documents by extracting sequential dependency between sentences and missing two important dependencies in procedural document.
Outcome:	The proposed method can generate flow graphs from unstructured documents with syntactic information and discourse structures.

Copied to clipboard

Yuhong Dai, Jianxun Lian, Yitian Huang, Wei Zhang, Mingyang Zhou, Mingqi Wu, Xing Xie, Hao Liao

Matching-oriented Embedding Quantization For Ad-hoc Retrieval (2021.emnlp-main)

Challenge:	Efficient processing of long contexts in large language models is essential for real-world applications such as retrieval-augmented generation and in-context learning.
Approach:	They propose a decoupled compressor-LLM framework that preserves contextual information within condensed embedding representations.
Outcome:	The proposed framework outperforms baseline models in three domains and across eight datasets while adapting to different downstream LLMs.

Copied to clipboard

Shitao Xiao, Zheng Liu, Yingxia Shao, Defu Lian, Xing Xie

KCS: Diversify Multi-hop Question Generation with Knowledge Composition Sampling (2025.emnlp-main)

Challenge:	Product quantization (PQ) is a widely used technique for ad-hoc retrieval.
Approach:	They propose a match-oriented product quantization with a multinoulli contrastive loss objective.
Outcome:	The proposed method maximizes matching probability of query and ground-truth key, compared with previous methods on non-supervised datasets.

Copied to clipboard

Yangfan Wang, Jie Liu, Chen Tang, Lian Yan, Jingchi Jiang

Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation (2025.findings-emnlp)

Challenge:	Existing approaches to multi-hop question answering focus on generating simple questions and neglecting the integration of essential knowledge, such as relevant sentences within documents.
Approach:	They propose a framework to expand the diversity of generated multi-hop questions by sampling varied knowledge compositions within a given context.
Outcome:	The proposed framework improves the overall accuracy of knowledge composition selection by 3.9% on hotpotQA and 2WikiMultihopQA datasets.

Copied to clipboard

Weiting Tan, Jiachen Lian, Hirofumi Inaguma, Paden Tomasello, Philipp Koehn, Xutai Ma

R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ (2024.naacl-long)

Challenge:	AVLM integrates full-face visual cues into a pre-trained expressive speech model.
Approach:	They propose an Audio-Visual Language Model (AVLM) for expressive speech generation by integrating full-face visual cues into a pre-trained expressive speech model.
Outcome:	The proposed model incorporates full-face visual cues into a pre-trained expressive speech model.

Copied to clipboard

Hanning Zhang, Shizhe Diao, Yong Lin, Yi Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, Tong Zhang

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training (2025.findings-acl)

Challenge:	Existing methods for instruction tuning force the model to complete a sentence no matter whether it knows the knowledge or not.
Approach:	They propose a new approach to tuning large language models to refrain from answering questions beyond its parametric knowledge by identifying the disparity in parametric and parametric information.
Outcome:	The proposed approach improves a model’s ability to answer known questions and refrain from answering unknown questions.

Copied to clipboard

Jun Rao, Zepeng Lin, Xuebo Liu, Xiaopeng Ke, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation (2025.acl-long)

Challenge:	Large Language Models often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities.
Approach:	They propose to use self-generated dis-preferred weakness data to enhance model performance with a targeted training approach that minimizes interference with existing knowledge base.
Outcome:	The proposed approach ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to existing methods.

Copied to clipboard

Haoran Jin, Meng Li, Xiting Wang, Zhihao Xu, Minlie Huang, Yantao Jia, Defu Lian

Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompts (2023.findings-emnlp)

Challenge:	Existing LLMs do not possess consistent values, but many have been developed to align them at the behavioral level, including supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF).
Approach:	They propose a Controlled Value Vector Activation method that directly aligns the internal values of Large Language Models by interpreting how a value is encoded in their latent representations.
Outcome:	The proposed method achieves highest success rate across 10 basic values without hurting model performance and fluency, and ensures target values even with opposite and potentially malicious input prompts.

Copied to clipboard

Gangwei Jiang, Caigao Jiang, Siqiao Xue, James Zhang, Jun Zhou, Defu Lian, Ying Wei

Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics (2022.findings-acl)

Challenge:	Continual pre-training has been used for a multitude of domains and tasks . a continually pre-trained model can show a non-decreasing performance on unseen domains .
Approach:	They propose a method that generates domain-specific prompts by agreement and disagreement losses.
Outcome:	The proposed method achieves improvements of 3.57% and 3.4% on two real-world datasets.

Copied to clipboard

Jiannan Xiang, Huayang Li, Yahui Liu, Lemao Liu, Guoping Huang, Defu Lian, Shuming Shi

Machine Translation

Challenge:	Current evaluation methods focus on one dataset, e.g., Newstest dataset in each year’s WMT Metrics Shared Task.
Approach:	They propose to use a single dataset to evaluate the performance of automatic translation metrics.
Outcome:	The results show that the rankings of metrics vary when the evaluation is conducted on different datasets.

Learning to Substitute Spans towards Improving Compositional Generalization (2023.acl-long)

Copied to clipboard

Zhaoyi Li, Ying Wei, Defu Lian

Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration (2026.acl-short)

Challenge:	despite the rising prevalence of neural sequence models, there is a deficiency in compositional generalization.
Approach:	They propose a compositional augmentation strategy that enables multi-grained composition of substructures in the whole training set.
Outcome:	The proposed strategy outperforms existing strategies on three compositional generalization benchmarks.

Copied to clipboard

Hang Lv, Hongchao Gu, Ruiqing Yang, Liangyue Li, Zulong Chen, Defu Lian, Hao Wang, Enhong Chen

RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection (2026.acl-long)

Challenge:	Existing methods for listwise reranking exhibit intrinsic position bias . existing methods are constrained by an inherent trade-off between efficiency and flexibility .
Approach:	They propose a training-free framework that mechanically decouples positional bias from ranking decisions.
Outcome:	a training-free framework decouples position bias from ranking decisions . evaluations show it outperforms training-based methods and outperformed expensive methods .

Copied to clipboard

Zhaoheng Huang, Dacheng Wen, Yutao Zhu, Xiaoying Lian, Yushi Liang, Kai Hao, Nan Li, Liangjie Zhang, Qi Zhang, Ji-Rong Wen, Zhicheng Dou, Fangzhao Wu

SocialCC: Interactive Evaluation for Cultural Competence in Language Agents (2025.acl-long)

Challenge:	Recent work addresses this problem by training span-level hallucination detectors using reinforcement learning and chain-of-thought reasoning.
Approach:	They propose a framework that explicitly enforces active evidence seeking during CoT reasoning by requiring quotation of relevant source segments at each verification step.
Outcome:	The proposed framework improves hallucination span detection performance with limited reasoning overhead and improved robustness in out-of-domain settings.

Copied to clipboard

Jincenzi Wu, Jianxun Lian, Dingdong Wang, Helen M. Meng

Challenge:	Existing studies have evaluated cultural knowledge of large language models, but they fail to assess dynamic cultural competence.
Approach:	They propose a benchmark to assess cultural competence through intercultural scenarios that span 60 countries across six continents.
Outcome:	The proposed benchmark measures the ability of large language models to apply cultural knowledge effectively in cross-cultural interactions.

Let Retrievers Think Before Action: Thought-Augmented Embedding for Dense Retrieval (2026.findings-acl)

Copied to clipboard

Ruiran Yan, Wen Xiong, Ze Liu, Chaozhuo Li, Hao Liao, Defu Lian, Zheng Liu

Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models (2026.acl-long)

Challenge:	Large language models have demonstrated that explicit step-by-step thinking can substantially improve performance on complex tasks.
Approach:	They propose a model that generates preliminary thoughts for input queries before document retrieval.
Outcome:	The proposed model generates preliminary thoughts for input queries before document retrieval.

Copied to clipboard

Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zhengqi Wen, Chonghua Liao, Ling Yang, Haoran Luo, Zheng Lian, Jianhua Tao

Understanding and Patching Compositional Reasoning in LLMs (2024.findings-acl)

Challenge:	In-context learning (ICL) struggles with complex reasoning due to superficial, example-level implicit imitation.
Approach:	They propose an automated method that shifts from surface-level examples to more guidance-oriented thought patterns.
Outcome:	The proposed method achieves 80.6% accuracy on MATH and 62.5% on AMC, surpassing GPT-4o’s 77.2% and 57.5% accuracy.

Copied to clipboard

Zhaoyi Li, Gangwei Jiang, Hong Xie, Linqi Song, Defu Lian, Ying Wei

Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification (2025.emnlp-industry)

Challenge:	LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
Approach:	They propose a lightweight method to patch compositional reasoning errors via editing the located MHSA modules in LLMs.
Outcome:	The proposed method can be used to patch compositional reasoning errors using MHSA modules located within the layers of the LLMs.

Copied to clipboard

Huike Zou, Haiyang Yang, Yindu Su, Chen Li Yu, Qinye Xie, Chengbao Lian, Qingheng Zhang, Shuguang Han, Fei Huang, Jufeng Chen

Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval (2024.acl-long)

Challenge:	Existing methods for product attribute value identification suffer from cascading errors and lack of generalization capability.
Approach:	They propose a multi-level retrieval scheme that uses products and attribute values as distinct hierarchical levels in PAVI domain.
Outcome:	The proposed method performs better than the state-of-the-art methods on a real-world industrial dataset.

Copied to clipboard

Chaofan Li, Zheng Liu, Shitao Xiao, Yingxia Shao, Defu Lian

MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards (2026.acl-long)

Challenge:	Dense retrieval requires discriminative embeddings to represent the semantic relationship between query and document.
Approach:	They propose an unsupervised approach that performs unsupervised adaptation of large language models for dense retrieval.
Outcome:	The proposed model improves on a variety of dense retrieval benchmarks and is available on github.

Copied to clipboard

Zhiyu Shen, Ziming Wu, Fuming Lai, Shaobing Lian, Yanghui Rao

Natural Language Interfaces

Challenge:	Memory-augmented frameworks fail to capture temporal evolution of historical states, limiting consistency in long-term dialogues.
Approach:	They propose a framework that trains models to orchestrate multi-dimensional memory construction with attributed dense rewards.
Outcome:	The proposed framework outperforms state-of-the-art closed-source models and generalizes well to OOD benchmarks.

Visualizing the Relationship Between Encoded Linguistic Information and Task Performance (2022.findings-acl)

Copied to clipboard

Jiannan Xiang, Huayang Li, Defu Lian, Guoping Huang, Taro Watanabe, Lemao Liu

Syntactic Text Processing

Challenge:	Recent studies show that encoding more syntactic information does not lead to better performance.
Approach:	They propose a method to optimize pareto-optimal models by formalizing it as a multi-objective optimization problem.
Outcome:	The proposed method is better than a baseline method on two NLP tasks.

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Jun Rao, Yunjie Liao, Xuebo Liu, Zepeng Lin, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

Robustness in NLP

Challenge:	Existing methods for preference optimization of large language models use pairs of positive and negative samples, but the quality of positive samples may become similar during training, complicating preference learning.
Approach:	SeaPO introduces error types commonly occurring in large language models to improve preference learning.
Outcome:	SeaPO introduces error types into model Preference Optimization to improve model performance . negative samples are more erroneous than positive samples, and preference-based training mitigates errors .

Assessing Dialogue Systems with Distribution Distances (2021.findings-acl)

Copied to clipboard

Jiannan Xiang, Yahui Liu, Deng Cai, Huayang Li, Defu Lian, Lemao Liu

Natural Language Interfaces

Challenge:	Existing evaluation metrics focus on turnlevel quality, which is not well suited for open-end dialogue tasks.
Approach:	They propose to measure the performance of a dialogue system by computing the distributionwise distance between its generated conversations and real-world conversations.
Outcome:	The proposed metrics correlate better with human judgments than existing metrics on dialogue systems.

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark (2025.acl-long)

Copied to clipboard

Jianlyu Chen, Nan Wang, Chaofan Li, Bo Wang, Shitao Xiao, Han Xiao, Hao Liao, Defu Lian, Zheng Liu

SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context (2026.findings-acl)

Challenge:	Evaluation benchmarks based on predefined domains and human-labeled data face limitations in addressing evaluation needs for emerging domains.
Approach:	They propose an automated information retrieval benchmark based on predefined domains and human-labeled data . AIR-Bench is automated and Heterogeneous with three key features .
Outcome:	The proposed benchmarks are based on predefined domains and human-labeled data.

Copied to clipboard

Shuquan Lian, Juncheng Liu, Yazhe Chen, Yuhong Chen, Hui Li

PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision (2020.findings-emnlp)

Challenge:	representative ReAct-style approaches lack explicit System-2 reasoning for deep analysis and handling complex edge cases.
Approach:	They propose a software agent framework that preserves full reasoning history while compressing historical reasoning content into concise Reasoning Digests.
Outcome:	Empirically, the proposed framework sets a new standard for 7B-8B models on SWE-Bench-Verified using only 2.2k trajectories and 896 tasks.

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Tao Qi, Jianxun Lian, Yongfeng Huang, Xing Xie

Boosting Long-Context Information Seeking via Query-Guided Activation Refilling (2025.acl-long)

Challenge:	Existing methods for user modeling cannot exploit useful information in unlabeled data . Existing models only model task-specific user information and do not exploit universal user information encoded in user behaviors.
Approach:	They propose to pre-train user models from large-scale unlabeled user behavior data.
Outcome:	The proposed method can model relatedness between historical and future behaviors on two real-world datasets.

Copied to clipboard

Hongjin Qian, Zheng Liu, Peitian Zhang, Zhicheng Dou, Defu Lian

Green & Sustainable NLP

Challenge:	Existing methods for processing long contexts are ineffective due to their inherent context window limitations and the computational burden of extensive key-value activations.
Approach:	They propose a method for processing long context information-seeking tasks via query-guided ACtivation REfilling (ACRE) a bi-layer KV Cache is constructed where the layer-1 cache compactly captures global information and the layer-2 cache provides detailed, localized information.
Outcome:	The proposed method achieves significant improvements in both performance and efficiency on a variety of long-context information-seeking datasets.

RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery (2025.findings-acl)

Copied to clipboard

Hongchao Gu, Dexun Li, Kuicai Dong, Hao Zhang, Hang Lv, Hao Wang, Defu Lian, Yong Liu, Enhong Chen

Benchmarking and Enabling Efficient Chinese Medical Retrieval via Asymmetric Encoders (2026.acl-long)

Challenge:	Existing methods for knowledge-intensive long texts struggle with issues like hallucinations, topic incoherence, and significant latency.
Approach:	They propose a retrieval-augmented long text generation framework with writing Planning and Information to address these challenges.
Outcome:	The proposed framework outperforms state-of-the-art methods on a freshWiki-2024 dataset.

Copied to clipboard

Angqing Jiang, Jianlyu Chen, null Zhefang, Yongcan Wang, Xinpeng Li, Keyu Ding, Defu Lian

Reinforced IR: A Self-Boosting Framework For Domain-Adapted Information Retrieval (2025.acl-long)

Challenge:	Effective medical text retrieval requires high accuracy and low latency.
Approach:	They propose a benchmark for medical text retrieval in Chinese using a symmetric architecture . CARE is a lightweight encoder with an LLM-based encoder for offline document encoding .
Outcome:	The proposed benchmark surpasses state-of-the-art symmetric models on CMedTEB . it matches high retrieval quality without increasing latency, and it performs well on a single GPU .

Copied to clipboard

Chaofan Li, Jianlyu Chen, Yingxia Shao, Chaozhuo Li, Quanqing Xu, Defu Lian, Zheng Liu

Learning Label Hierarchy with Supervised Contrastive Learning (2024.findings-eacl)

Challenge:	Existing retrieval methods struggle with highly specialized situations that require extensive domain expertise.
Approach:	They propose a method that integrates additional information from an LLM-based generator to enhance query performance and train the retriever to better discriminate the relevant documents identified by the generator.
Outcome:	The proposed method outperforms existing domain adaptation methods by a large margin and leads to substantial improvements in retrieval quality across a wide range of application scenarios.

Copied to clipboard

Ruixue Lian, William Sethares, Junjie Hu

Can AI Revise Research Papers with Human Review Feedback? An Empirical Study and Benchmark (2026.findings-acl)

Challenge:	Existing approaches to supervised contrastive learning treat each class as independent and therefore consider all classes to be equally important.
Approach:	They propose a family of Label-Aware SCL methods that incorporate hierarchical information to SCL by leveraging similarities between classes.
Outcome:	The proposed method outperforms baseline supervised approaches on three datasets.

Copied to clipboard

Zihan Luo, Hong Huang, Jianxun Lian, Yu Chang, Xing Xie, Hai Jin

Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions (2026.acl-long)

Challenge:	Large Language Models (LLMs) are fundamentally reshaping the scientific landscape, transitioning the role of AI from passive tools to active partners within a new paradigm of Human-AI collaboration.
Approach:	They propose a benchmark to evaluate the ability of Large Language Models to improve papers with human feedback.
Outcome:	The proposed benchmark tests the skills of Large Language Models (LLMs) on paper interpretation, experimental implementation, and paper formulation, using authors’ camera-ready versions as natural human baselines.

Copied to clipboard

Ruochong Xiong, Qien Li, Wangwang Lian, Yulong Wan, Hanlin Xue, Zhouxing Tan, Han Yang, Fengyu Lu, Junfei Liu

Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models (2025.coling-main)

Challenge:	Existing methods for detecting LLM-Generated text suffer from distribution misalignment and limited interpretability.
Approach:	They propose a statistical framework utilizing supervised subspace learning to extract compact features and construct conditional semantic distributions based on syntactic structures.
Outcome:	The proposed framework is superior in cross-domain, cross-model, and adversarial scenarios.

Copied to clipboard

Haoran Lian, Junmin Chen, Wei Huang, Yizhe Xiong, Wenping Hu, Guiguang Ding, Hui Chen, Jianwei Niu, Zijia Lin, Fuzheng Zhang, Di Zhang

Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline (2026.acl-long)

Challenge:	Recent studies show that Large language models struggle with handling long token sequences due to limited training context size.
Approach:	They propose a single-stage continual pretraining method to equip LLMs with long context modeling capabilities.
Outcome:	The proposed method outperforms existing methods on 4 language modeling benchmarks.

Copied to clipboard

Jingchun Lian, Lingyu Liu, Yaxiong Wang, Yujiao Wu, Lianwei Wu, Li Zhu, Zhedong Zheng

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation (2024.acl-long)

Challenge:	Existing facial forgery detection methods focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation.
Approach:	They propose a multimodal task that localizes forged regions and generates natural language explanations grounded in editing process.
Outcome:	The proposed task localizes forged regions and generates natural language explanations grounded in editing process.

Copied to clipboard

Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song, Ying Wei, Defu Lian, Zhendong Mao

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Challenge:	Existing MCTG methods face a noticeable performance drop in compositional testing.
Approach:	They propose a benchmark to evaluate compositional generalization of MCTG methods by combining multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol.
Outcome:	The proposed framework improves compositional generalization performance by 3.64% and 94.4% in compositional testing.

Copied to clipboard

Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models (2025.emnlp-industry)

Challenge:	Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach:	They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome:	The proposed framework outperforms baseline methods in real-time and in real applications.

Copied to clipboard

Yi Shen, Jian Zhang, Jieyun Huang, Shuming Shi, Wenjing Zhang, Jiangze Yan, Ning Wang, Kai Wang, Zhaoxiang Liu, Shiguo Lian

Green & Sustainable NLP

Challenge:	Recent advances in slow-thinking reasoning models have shown exceptional performance in complex reasoning tasks.
Approach:	They propose a framework that enables models to automatically adjust Chain-of-Thought (CoT) length based on problem difficulty.
Outcome:	The proposed framework penalizes inefficiency on simple problems while incentivizing deep reasoning for complex ones.

Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification (2023.acl-long)

Copied to clipboard

Ke Ji, Yixin Lian, Jingsheng Gao, Baoyuan Wang

PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models (2026.findings-acl)

Challenge:	Existing work on the hierarchical text classification problem is limited due to the complexity of label hierarchy and intensive labeling cost.
Approach:	They propose a path-based few-shot setting and a strict path-basic evaluation metric to further explore few- shot HTC tasks.
Outcome:	The proposed framework outperforms those who inject hierarchy through graph encoders on three popular HTC datasets under the few-shot setting.

Copied to clipboard

Wenlong Shi, Jianxun Lian, Mingqi Wu, Haiming Qin, Mingyang Zhou, Xing Xie, Naipeng Chao, Hao Liao

Logic-Regularized Verifier Elicits Reasoning from LLMs (2025.acl-long)

Challenge:	Existing research focuses on character-level settings and static evaluation formats fail to capture the complexity of everyday social interactions.
Approach:	They propose a dynamic simulation framework for evaluating and improving persona-level role-playing in large language models (LLMs).
Outcome:	The proposed framework leverages user-generated social content to construct a nuanced persona bank and elicits multi-turn, context-rich interactions within simulated social environments.

Copied to clipboard

Xinyu Wang, Changzhi Sun, Lian Cheng, Yuanbin Wu, Dell Zhang, Xiaoling Wang, Xuelong Li

MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)

Challenge:	Typical verifiers require resource-intensive supervised dataset construction, which is costly and faces limitations in data diversity.
Approach:	They propose an unsupervised verifier regularized by logical rules that uses internal activations and logical constraints on multiple reasoning paths.
Outcome:	Experiments on 10 datasets show that the proposed verifier outperforms baselines and is comparable to the supervised verifier.

Copied to clipboard

Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, yi Chen, Boran Wang, Yingjian Zhu, Hongzhu Yi, Hong-Ming Yang, Han Hu, Cheng-Lin Liu, Xu-Yao Zhang

IPL: Leveraging Multimodal Large Language Models for Intelligent Product Listing (2024.emnlp-industry)

Challenge:	Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited.
Approach:	They propose a Meta-Reasoning informed alignment framework that quantifies state-transition probabilities along the model’s thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments.
Outcome:	Empirical evaluations of four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning.

Copied to clipboard

Kang Chen, Qing Zhang, Chengbao Lian, Yixin Ji, Xuwei Liu, Shuguang Han, Guoqiang Wu, Fei Huang, Jufeng Chen

Reasoning-Aware AIGC Detection via Alignment and Reinforcement (2026.findings-acl)

Challenge:	Unlike professional Business-to-Consumer (B2C) e-commerce platforms, consumer-to consumer (C2C), is mainly targeting individual sellers.
Approach:	They develop an intelligent product listing tool that generates product descriptions using various product attributes such as category, brand, color, condition, etc.
Outcome:	The proposed tool outperforms the base model in domain-specific tasks while producing less hallucination.

Copied to clipboard

Zhao Wang, Max Xiong, Jianxun Lian, Zhicheng Dou

Hierarchical Reward Modeling for Fault Localization in Large Code Repositories (2025.findings-emnlp)

Challenge:	Existing approaches to AIGC detection have relied on statistical classifiers or black-box neural models, which exploit surface-level patterns and struggle to generalize as LLMs evolve.
Approach:	They propose a framework that generates interpretable reasoning chains before classification using supervised fine-tuning and reinforcement learning to improve accuracy.
Outcome:	The proposed framework achieves state-of-the-art performance across multiple benchmarks, offering a robust and transparent solution for AIGC detection.

Copied to clipboard

Jiwei Zhang, Jianxun Lian, Haiming Qin, Mingyang Zhou, KeZhong Lu, Rui Mao, Hao Liao

Challenge:	Large Language Models (LLMs) have limited fault localization capabilities due to limited context length.
Approach:	They propose a hierarchical localization reward model to evaluate and select the most accurate fault localization candidates from the outputs of LLMs.
Outcome:	The proposed model improves the final line-level localization recall by 12% on the SWE-Bench-Lite dataset.

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

Copied to clipboard

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

Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations (2026.findings-acl)

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

Copied to clipboard

Nanxu Gong, Zixin Chen, Haotian Li, Zishu Zhao, Jianxun Lian, Huamin Qu, Yanjie Fu, Xing Xie

Linguistics & Cognitive NLP

Challenge:	Existing benchmarks measure ToM capability improvement through story-reading, multiple-choice questions from a third-person perspective, while ignoring the first-person, dynamic nature of human-AI interactions.
Approach:	They propose a new paradigm of interactive ToM evaluation with both perspective and metric shifts.
Outcome:	The proposed approach improves the performance of four representative LLM enhancement techniques using real-world datasets and a user study.

An Anchor-based Relative Position Embedding Method for Cross-Modal Tasks (2022.emnlp-main)

Copied to clipboard

Ya Wang, Xingwu Sun, Lian Fengzong, ZhanHui Kang, Chengzhong Xu Xu

NLoPT: N-gram Enhanced Low-Rank Task Adaptive Pre-training for Efficient Language Model Adaption (2024.lrec-main)

Challenge:	Position Embedding (PE) is essential for transformer to capture the sequence ordering of input tokens.
Approach:	They propose a unified position embedding method that bridges the semantic gap between modalities and embeds the anchor-based distance to guide computation of cross-attention.
Outcome:	The proposed method obtains new SOTA results on a wide range of benchmarks.

Copied to clipboard

Hao Gu, Jiangyan Yi, Zheng Lian, Jianhua Tao, Xinrui Yan

Efficient Data Labeling by Hierarchical Crowdsourcing with Large Language Models (2025.coling-main)

Challenge:	Pre-trained Language Models (PLMs) have superior performance on downstream tasks . however, conventional TAPT adjusts all parameters of the PLMs, which distorts the learned generic knowledge embedded in the original PLM's weights.
Approach:	They propose a two-step n-gram enhanced low-rank task adaptive pre-training method to customize a PLM to the downstream task.
Outcome:	The proposed method improves performance on six datasets from four domains.

Copied to clipboard

Haodi Zhang, Junyu Yang, Jinyin Nie, Peirou Liang, Kaishun Wu, Defu Lian, Rui Mao, Yuanfeng Song

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

Challenge:	Large language models (LLMs) have been gaining attention for their impressive performance in in-context dialogues.
Approach:	They propose a hierarchical framework that leverages multiple LLMs for efficient data labeling under budget constraints.
Outcome:	The proposed framework outperforms human labelers and GPT-4 in terms of accuracy and efficiency.

Copied to clipboard

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

Towards Better Entity Linking with Multi-View Enhanced Distillation (2023.acl-long)

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

Copied to clipboard

Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Weiwei Deng, Qi Zhang

Aligning Large Language Models for Controllable Recommendations (2024.acl-long)

Challenge:	Entity linking is a fundamental task in Natural Language Processing (NLP), connecting mentions within unstructured contexts to their corresponding entities in a Knowledge Base (KB).
Approach:	They propose a dual-encoder framework that can efficiently match mentions to two-encoding frameworks by a global-view.
Outcome:	The proposed framework achieves state-of-the-art on several entity linking benchmarks.

Copied to clipboard

Wensheng Lu, Jianxun Lian, Wei Zhang, Guanghua Li, Mingyang Zhou, Hao Liao, Xing Xie

MIND: A Large-scale Dataset for News Recommendation (2020.acl-main)

Challenge:	Existing literature focuses on integrating domain-specific knowledge into LLMs to enhance accuracy using a fixed task template.
Approach:	They propose a collection of supervised learning tasks augmented with labels derived from a conventional recommender model to improve LLMs’ proficiency in adhering to recommendation-specific instructions.
Outcome:	The proposed approach significantly improves the capability of LLMs to respond to instructions within recommender systems, reducing formatting errors while maintaining a high level of accuracy.

Copied to clipboard

Fangzhao Wu, Ying Qiao, Jiun-Hung Chen, Chuhan Wu, Tao Qi, Jianxun Lian, Danyang Liu, Xing Xie, Jianfeng Gao, Winnie Wu, Ming Zhou

DART: Distilling Autoregressive Reasoning to Silent Thought (2025.emnlp-main)

Challenge:	Personalized news recommendation is an important technique for personalized news service.
Approach:	They propose to build a large-scale news recommendation dataset from Microsoft News . they demonstrate that news recommendation relies on the quality of news content understanding .
Outcome:	The proposed dataset contains 1 million users and more than 160k English news articles, each of which has rich textual content such as title, abstract and body.

Copied to clipboard

Nan Jiang, Ziming Wu, De-Chuan Zhan, Fuming Lai, Shaobing Lian

Dialogue Language Model with Large-Scale Persona Data Engineering (2025.naacl-industry)

Challenge:	Existing models that use Chain-of-Thought (CoT) have been slow to deploy in real-time applications due to its autoregressive nature.
Approach:	They propose a framework that replaces autoregressive CoT with non-autoregressive Silent Thought (ST) the framework uses a lightweight Reasoning Evolvement Module to align hidden states with the CoT pathway and a Reasoning Embedment Module (REM) during inference, only the ST pathway is activated, enabling the ST tokens to evolve into informative embeddings.
Outcome:	The proposed framework replaces autoregressive CoT with non-autoregressive Silent Thought (ST) it enables LLMs to generate answers directly from ST tokens without additional computational cost .

Copied to clipboard

Mengze Hong, Chen Jason Zhang, Chaotao Chen, Rongzhong Lian, Di Jiang

Exploring the Choice Behavior of Large Language Models (2025.findings-acl)

Challenge:	Existing persona-consistent dialogue models lack robustness due to limited scale and diversity of datasets.
Approach:	They propose an open-domain persona dialogue system that employs extensive generative pre-training on a persona dialog dataset to enhance persona consistency.
Outcome:	The proposed model generates vast persona dialogue datasets and addresses invalid persona bias.

Copied to clipboard

Weidong Wu, Qinlin Zhao, Hao Chen, Lexin Zhou, Defu Lian, Hong Xie

The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learning (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) are increasingly being adopted across various domains where they help to make choices.
Approach:	They construct a virtual QA platform that includes three different experimental conditions, with four models from GPT and Llama series participating in repeated experiments.
Outcome:	The proposed model includes three experimental conditions and four models from GPT and Llama series.

Copied to clipboard

Yuchen Lian, Arianna Bisazza, Tessa Verhoef

EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning (2026.acl-long)

Challenge:	Existing studies have focused on agent-based simulations of language emergence.
Approach:	They propose to model the trade-off between word order and inflection in natural languages by using neural network agents.
Outcome:	The results show that neural agents strive to maintain the utterance type distribution observed during learning, rather than developing a more efficient or systematic language.

Copied to clipboard

Jiawei Liu, Qisi Chen, Jianshu Zhang, Quan Liu, Defu Lian

From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents (2026.acl-long)

Challenge:	Existing semantic similarity methods struggle to accurately identify semantically equivalent steps in domain-specific contexts like mathematical reasoning.
Approach:	They propose a simple yet effective approach that identifies and prunes semantically equivalent actions during LLM reasoning search.
Outcome:	The proposed approach reduces token consumption while improving reasoning efficiency and accuracy on Qwen2.5-Math-7B-Instruct on GSM8K.

Copied to clipboard

Niu Lian, Yuting Wang, Hanshu Yao, Jinpeng Wang, Bin Chen, Yaowei Wang, Min Zhang, Shu-Tao Xia

Visual Data in NLP

Challenge:	Existing multimodal large language models struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency.
Approach:	They propose a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory that structures memory hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic Schema.
Outcome:	The proposed architecture achieves state-of-the-art on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization.

Enhancing One-Shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism (2025.coling-main)

Copied to clipboard

Guanchen Li, Xiandong Zhao, Lian Liu, Zeping Li, Yixing Xu, Dong Li, Lu Tian, Jie He, Ashish Sirasao, Emad Barsoum

Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest (2022.coling-1)

Challenge:	Pre-trained language models (PLMs) are robust in contextual understanding but their considerable size incurs significant computational and storage costs.
Approach:	They propose a Sparse-Dense-Sparse pruning framework to prune PLMs . they prune less critical connections using conventional pruning methods .
Outcome:	The proposed pruning framework outperforms SparseGPT and Wanda under identical sparsity.

Copied to clipboard

Yifan Jin, Jiangmeng Li, Zheng Lian, Chengbo Jiao, Xiaohui Hu

Information Extraction & Text Mining

Challenge:	Medical relation extraction (MRE) tasks aims to extract relations between entities in medical literature.
Approach:	They propose to combine semantic and syntactic information from medical texts by using causal explanation theory.
Outcome:	Empirically, the proposed model outperforms existing methods on benchmark medical datasets.

Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval (2025.acl-long)

Copied to clipboard

Zheng Liu, Ze Liu, Zhengyang Liang, Junjie Zhou, Shitao Xiao, Chao Gao, Chen Jason Zhang, Defu Lian

Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment (P19-1)

Challenge:	Existing multimodal retrieval models are lacking in visual representations of multimodal data.
Approach:	They propose a visualized information retrieval paradigm where multimodal information is represented by a unified visual format called Screenshots for various retrieval applications.
Outcome:	The proposed model is based on a large dataset of screenshots from diverse sources . it is compared with existing models and lays a solid foundation for the new model .

Copied to clipboard

Siqi Bao, Huang He, Fan Wang, Rongzhong Lian, Hua Wu

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)

Challenge:	Existing approaches to generate informative responses based on external knowledge are limited to singleround settings.
Approach:	They propose a framework for multi-turn conversations with two dialogue agents . they propose to evaluate dialogues on informativeness and coherence .
Outcome:	The proposed framework outperforms state-of-the-art approaches significantly on the publicly available dataset.

Copied to clipboard

Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang

Programming Languages in NLP

Challenge:	Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows .
Approach:	They propose a repository-level evaluation benchmark to assess security of AI-generated code.
Outcome:	The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation.

Towards Hierarchical Spoken Language Disfluency Modeling (2024.eacl-long)

Copied to clipboard

Jiachen Lian, Gopala Anumanchipalli

AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis (2022.coling-1)

Challenge:	Existing solutions to speech dysfluency modeling are limited and expensive for low-income families.
Approach:	They propose a hierarchical unconstrained dysfluency modeling approach that addresses both dysfluencies transcription and detection to eliminate the need for extensive manual annotation.
Outcome:	The proposed approach eliminates the need for extensive manual annotation and improves the accuracy of the proposed model in phonetic transcription.

Copied to clipboard

Ziming Li, Yan Zhou, Weibo Zhang, Yaxin Liu, Chuanpeng Yang, Zheng Lian, Songlin Hu

Explaining Length Bias in LLM-Based Preference Evaluations (2025.findings-emnlp)

Challenge:	Existing methods treat three modal features equally, without distinguishing the importance of different modalities. Existing models split the video into frames, leading to missing the global acoustic information.
Approach:	They propose a global Acoustic feature enhanced Modal-Order-Aware network to address these problems.
Outcome:	The proposed model outperforms state-of-the-art models on two public datasets.

Copied to clipboard

Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhengyu Chen, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong

Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity (2025.findings-emnlp)

Challenge:	a preference evaluation metric is often biased towards longer responses, revealing a reliability problem . a decomposition of the preference evaluation into two components is needed to understand this bias.
Approach:	They propose to decompose the preference evaluation metric into two key components . the first component is length-dependent and related to trustworthiness .
Outcome:	The proposed evaluation metric is based on two components: desirability and information mass.

Copied to clipboard

Ping Chen, Xiang Liu, Zhaoxiang Liu, Zezhou Chen, Xingpeng Zhang, Huan Hu, Zipeng Wang, Kai Wang, Shuming Shi, Shiguo Lian