Papers by Xiaozhong Liu

LLMs as Lab Engineers: A Benchmark for Analytical Method Lifecycle Management (2026.findings-acl)

Challenge:	Recent years have witnessed a substantial increase in the demand for legal services, especially for individuals with modest means.
Approach:	They propose a diagnostic legal large language model which uses adaptive lawyer-like diagnostic questions to collect additional case information and then provides high-quality feedback.
Outcome:	The proposed model surpasses classical LLMs by providing outstanding performance and a remarkable user experience in the legal domain.

Copied to clipboard

Xiaoyi Chen, Mahsa Monshizadeh, Chaoqi Zhang, Jianjun Lang, Yang Wu, Genevieve Mortensen, Xiaozhong Liu, Haixu Tang

Reasoning

Challenge:	General-purpose commercial models outperform domain-specialized ones, while RAG and reasoning significantly improve performance.
Approach:	They propose a benchmark to evaluate LLMs' capabilities in analytical chemistry scenarios.
Outcome:	The proposed framework outperforms existing benchmarks focused on factual knowledge and provides practical guidance for analytical chemistry challenges.

Cross Copy Network for Dialogue Generation (2020.emnlp-main)

Copied to clipboard

Changzhen Ji, Xin Zhou, Yating Zhang, Xiaozhong Liu, Changlong Sun, Conghui Zhu, Tiejun Zhao

ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning (2025.findings-emnlp)

Challenge:	Despite the success of sequence-to-sequence models, dialogue logics are often ignored.
Approach:	They propose a network architecture to explore the current dialog context and similar dialogue instances’ logical structure simultaneously.
Outcome:	The proposed network architecture is superior to existing state-of-the-art models.

Copied to clipboard

Yang Wu, Huayi Zhang, Yizheng Jiao, Lin Ma, Xiaozhong Liu, Jinhong Yu, Dongyu Zhang, Dezhi Yu, Wei Xu

Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization (2023.findings-emnlp)

Challenge:	Prevailing methods for task-specific instruction tuning use similarity metrics to select training data . but instruction tuning loss often fails to exhibit a monotonic relationship with actual task performance .
Approach:	They propose a task-specific instruction tuning method that leverages pairwise preference loss as a reward signal.
Outcome:	The proposed method surpasses state-of-the-art methods for task-specific instruction tuning.

Copied to clipboard

Kaihang Pan, Juncheng Li, Hongye Song, Jun Lin, Xiaozhong Liu, Siliang Tang

Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document (2023.findings-emnlp)

Challenge:	Existing methods for prompt tuning can overfit to few-shot training samples, causing overfitting . authors propose a new framework for prompt learning with supervised meta-learning .
Approach:	They propose a self-supervised meta-prompt learning framework with MEta-gradient Regularization for few-shot generalization that leverages self-recognized meta-learning with a diverse set of meta-tasks to learn a universal prompt initialization using only unlabeled data.
Outcome:	The proposed framework learns a universal prompt initialization for efficient adaptation using only unlabeled data.

Copied to clipboard

Xiangnan Chen, Qian Xiao, Juncheng Li, Duo Dong, Jun Lin, Xiaozhong Liu, Siliang Tang

BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks (2025.emnlp-main)

Challenge:	Existing methods focus on manipulating entity features to find pairwise relations, yet neglect the more fundamental structural information that links disparate entity pairs together.
Approach:	They propose a Visual Relation Extraction framework that generates relation predictions on entity pairs extracted from scanned images and incorporates global structural knowledge into the representations of the entities.
Outcome:	The proposed framework outperforms existing methods in fine-tuning setting and yields stronger data-efficient performance in the low-resource setting.

Copied to clipboard

Tianyuan Huang, Zepeng Zhu, Hangdi Xing, Zirui Shao, Zhi Yu, Chaoxiong Yang, Jiaxian He, Xiaozhong Liu, Jiajun Bu

Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation (D19-1)

Challenge:	Existing Braille research focuses on isolated tasks while mixed-content Braille tasks face data scarcity and ambiguities.
Approach:	They propose a syntax tree-based augmentation method tailored for Braille data.
Outcome:	The proposed method improves Braille translation, formula-to-Braille conversion, and mixed-text translation.

Copied to clipboard

Zhuoren Jiang, Zhe Gao, Guoxiu He, Yangyang Kang, Changlong Sun, Qiong Zhang, Luo Si, Xiaozhong Liu

Semantic Text Processing

Challenge:	Currently, Chinese characters share glyph and phonetic variations to escape detection algorithms due to their complexity and complexity.
Approach:	They propose a Chinese variation-enhanced Graph Embedding algorithm that can learn Chinese character embeddings and latent variation families.
Outcome:	The proposed model outperforms state-of-the-art models on Chinese spam detection datasets and review datasets.

Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains (2025.findings-emnlp)

Copied to clipboard

Yang Wu, Raha Moraffah, Rujing Yao, Jinhong Yu, Zhimin Tao, Xiaozhong Liu

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have demonstrated an impressive level of general knowledge, but often struggle in highly specialized domains due to the lack of expert knowledge.
Approach:	They propose a framework to actively engage domain experts within a fixed budget to enhance domain-specific LLMs.
Outcome:	The proposed framework improves LLMs in highly specialized domains while adhering to budget constraints.

De-Biased Court’s View Generation with Causality (2020.emnlp-main)

Copied to clipboard

Yiquan Wu, Kun Kuang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Jun Xiao, Yueting Zhuang, Luo Si, Fei Wu

Semantic Text Processing

Challenge:	Existing approaches to court’s view generation can be used to address this problem, but neglecting the confounding bias in data can limit the model performance and pollute learning outcomes.
Approach:	They propose a novel Attentional and Counterfactual based Natural Language Generation method consisting of an attentional encoder and a pair of innovative counterfactual decoders to generate judgment-discriminative court's views.
Outcome:	The proposed method is able to generate judgment-discriminative court's views (both supportive and non-supportive views) under both quantitative and qualitative evaluation metrics.

From Model-centered to Human-Centered: Revision Distance as a Metric for Text Evaluation in LLMs-based Applications (2024.findings-acl)

Copied to clipboard

Yongqiang Ma, Lizhi Qing, Jiawei Liu, Yangyang Kang, Yue Zhang, Wei Lu, Xiaozhong Liu, Qikai Cheng

Predicting Clinical Trial Results by Implicit Evidence Integration (2020.emnlp-main)

Challenge:	Existing evaluation metrics for large language models yield numerical scores that ignore user experience.
Approach:	They propose a metric that suggests revision edits that mimic the human writing process . their results show that the metric offers more insightful feedback and distinguishes between texts .
Outcome:	The proposed metric can provide a self-explained text evaluation result in a human-understandable manner beyond the context-independent score.

Copied to clipboard

Qiao Jin, Chuanqi Tan, Mosha Chen, Xiaozhong Liu, Songfang Huang

Reasoning

Challenge:	Clinical trials are expensive and time-consuming, and inappropriately designed studies can be devastating in a pandemic.
Approach:	They propose a model that takes a PICO-formatted clinical trial proposal and predicts the outcome from it.
Outcome:	The proposed model outperforms baseline models on a benchmark dataset with 10.7% relative gain over BioBERT.

PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering (2026.acl-long)

Copied to clipboard

Yiqing Zhang, Xiaozhong Liu, Fabricio Murai

Reasoning

Challenge:	Existing approaches to QA provide inaccurate answers but lack mechanisms to iteratively refine poor queries.
Approach:	They propose a biomedical question answering agent that performs self-critic query refinement . they propose re-reflection methods that kick in only after full retrieval is completed .
Outcome:	a biomedical question answering agent achieves 78.32% accuracy on PubMedQA . the proposed approach provides practical assistance to clinicians and biomedically researchers .

Using Customer Service Dialogues for Satisfaction Analysis with Context-Assisted Multiple Instance Learning (D19-1)

Copied to clipboard

Kaisong Song, Lidong Bing, Wei Gao, Jun Lin, Lujun Zhao, Jiancheng Wang, Changlong Sun, Xiaozhong Liu, Qiong Zhang

Natural Language Interfaces

Challenge:	Existing studies fail to provide comprehensive service satisfaction analysis . Existing models fail to include satisfaction polarity classification and sentimental utterance identification .
Approach:	They propose a model that predicts customer sentiments and aggregates them into service satisfaction polarity.
Outcome:	The proposed model predicts customer sentiments and aggregates them into service satisfaction polarity and reasoning clues.

Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning (2020.acl-main)

Copied to clipboard

Zhuoren Jiang, Zhe Gao, Yu Duan, Yangyang Kang, Changlong Sun, Qiong Zhang, Xiaozhong Liu

LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination (2024.naacl-long)

Challenge:	Existing active learning models for text spam detection tasks are based on pool-based active learning, but the annotating process is laborious and time consuming for humans.
Approach:	They propose a semi-supervised active learning model to address spam imbalances . they propose masked attention learning approach and character variation graph-enhanced augmentation procedure .
Outcome:	The proposed model can improve the performance of existing models for Chinese spam detection task.

Copied to clipboard

Kai Zhang, Yangyang Kang, Fubang Zhao, Xiaozhong Liu

Challenge:	Existing studies have focused on learning and enhancing large language models to understand and generate natural language.
Approach:	They propose a computational bionic memory mechanism equipped with a parameter-efficient fine-tuning schema to personalize medical assistants.
Outcome:	The proposed method can enhance the response with aware of previous mistakes for new queries during a dialogue session, but the training costs are prohibitive.

Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning (2025.naacl-long)

Copied to clipboard

Rujing Yao, Yang Wu, Chenghao Wang, Jingwei Xiong, Fang Wang, Xiaozhong Liu

Information Retrieval

Challenge:	Existing approaches to large language models focus on semantic similarity, neglecting the intricate logical structures and reasoning essential for addressing complex legal issues.
Approach:	They propose a Logical-Semantic Integration Model (LSIM) that bridges semantic and logical coherence and a supervised framework that integrates semantic features with in-context learning.
Outcome:	The proposed framework significantly improves accuracy and reliability on a real-world legal QA dataset.

Copied to clipboard

Yongzhen Wang, Xiaozhong Liu, Zheng Gao

RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy (2021.acl-long)

Challenge:	Existing approaches to automatic related work summarization rely on human-engineered features.
Approach:	They propose a neural data-driven attention mechanism to measure contextual relevance within full texts and a heterogeneous bibliography graph simultaneously.
Outcome:	The proposed approach achieves significant improvement over a typical seq2seq summarization baseline and five classical summarizing baselines.

Copied to clipboard

Xiyan Fu, Yating Zhang, Tianyi Wang, Xiaozhong Liu, Changlong Sun, Zhenglu Yang

From Individual Excellence to Collective Sustainability: Seeking Strategic Equilibrium in Proactive Multi-Agent Teams (2026.findings-acl)

Challenge:	Existing methods to learn vital information from dialogue context with limited data are limited due to limited words in utterances and huge gap between dialogue and its summary.
Approach:	They propose an unsupervised strategy to learn vital information from dialogue context . the proposed model uses a hypothetical foundation that a superior summary approximates a replacement of the original dialogue .
Outcome:	The proposed model outperforms existing models on a number of datasets.

Copied to clipboard

Tong Zhang, Yang Wu, Yufei Shi, Rujing Yao, Zhuoren Jiang, Xiaozhong Liu

Uncover Sexual Harassment Patterns from Personal Stories by Joint Key Element Extraction and Categorization (D19-1)

Challenge:	a team of proactive agents suffer from a greedy optimization for immediate task accuracy . a new approach to improve team collaboration is based on the opportunity cost .
Approach:	They propose a game-theoretic proactive multi-agent reinforcement learning framework to solve this imbalance . they use a Positive-Unlabeled scorer to anchor intervention quality under sparse supervision .
Outcome:	The proposed framework maintains high performance while preventing experts from over-developing.

Copied to clipboard

Yingchi Liu, Quanzhi Li, Marika Cifor, Xiaozhong Liu, Qiong Zhang, Luo Si

Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration (2023.emnlp-main)

Challenge:	Sexual harassment is a pervasive, worldwide problem with a long history . statistics show that girls and women are put at high risk of experiencing harassment.
Approach:	They manually annotated sexual harassment stories with labels in dimensions of location, time, and harassers’ characteristics and applied natural language processing techniques to extract key elements at the same time.
Outcome:	The proposed algorithms will help people who have been harassed, authorities, researchers and other related parties in various ways, such as automatically filling reports, and enabling faster action to be taken.

Copied to clipboard

Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, Kun Kuang

Green & Sustainable NLP

Challenge:	Recent advances in deep learning have enabled a variety of techniques to be used to solve the LJP task.
Approach:	They propose a framework that leverages the strength of both LLMs and domain-specific models in the context of precedents.
Outcome:	The proposed framework leverages the strength of both LLM and domain models in the context of precedents.

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration (2024.findings-emnlp)

Copied to clipboard

Weikang Yuan, Junjie Cao, Zhuoren Jiang, Yangyang Kang, Jun Lin, Kaisong Song, Tianqianjin Lin, Pengwei Yan, Changlong Sun, Xiaozhong Liu

Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition (2026.findings-acl)

Challenge:	Existing studies have found that when LLMs are given criminal facts and legal rules, then asked whether cases constitute a certain charge, they struggle to understand legal theories and perform basic legal reasoning tasks.
Approach:	They propose a task to assess LLMs' understanding of legal theories and reasoning capabilities by using a novel framework: Multi-Agent framework for improving complex legal reasoning capability.
Outcome:	The proposed framework improves LLMs' understanding of legal theories and reasoning abilities in real-world scenarios.

Copied to clipboard

Rujing Yao, Yufei Shi, Yang Wu, Ang Li, Zhuoren Jiang, XiaoFeng Wang, Haixu Tang, Xiaozhong Liu

GEM: Gestalt Enhanced Markup Language Model for Web Understanding via Render Tree (2023.emnlp-main)

Challenge:	Cloud-hosted Large Language Models (LLMs) offer unmatched reasoning capabilities and dynamic knowledge, yet submitting raw queries to these services can expose sensitive user intent.
Approach:	They propose a framework that formulates the trade-off between knowledge utility and privacy as a strategic game.
Outcome:	The proposed framework reduces intent leakage while maintaining high-fidelity answer quality.

Copied to clipboard

Zirui Shao, Feiyu Gao, Zhongda Qi, Hangdi Xing, Jiajun Bu, Zhi Yu, Qi Zheng, Xiaozhong Liu

Multi-Turn Dialogue Generation in E-Commerce Platform with the Context of Historical Dialogue (2020.findings-emnlp)

Challenge:	Existing models that use plain HTMLs do not include crucial visual information in the rendered web.
Approach:	They propose a Gestalt Enhanced Markup Language Model for hosting visual information without visual input.
Outcome:	The proposed model can handle multiple downstream tasks without visual input.

Copied to clipboard

WeiSheng Zhang, Kaisong Song, Yangyang Kang, Zhongqing Wang, Changlong Sun, Xiaozhong Liu, Shoushan Li, Min Zhang, Luo Si

One vs. Many QA Matching with both Word-level and Sentence-level Attention Network (C18-1)

Challenge:	Existing research on customer service dialogue generation generates generic responses from sellers . however, such cost prohibits small businesses, and multiturn dialogue generation is becoming more popular.
Approach:	They propose a novel and extensible dialogue generation method by leveraging sellers’ historical dialogue information to generate generic seller responses.
Outcome:	The proposed model can generate high-quality responses that cater to specific sellers’ characteristics and exhibit consistent superiority over baselines on a real-world multi-turn customer service dialogue dataset.

Copied to clipboard

Lu Wang, Shoushan Li, Changlong Sun, Luo Si, Xiaozhong Liu, Min Zhang, Guodong Zhou

Question Answering

Challenge:	Existing studies on question answer matching focus on formal text . however, there exists many scenarios where the QA text is informal .
Approach:	They propose a novel QA matching approach using informal text from a product review site.
Outcome:	The proposed approach improves word-level and sentence-level attentions for solving the noisy problem in the informal text.

Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network (P19-1)

Copied to clipboard

Jingjing Wang, Changlong Sun, Shoushan Li, Xiaozhong Liu, Luo Si, Min Zhang, Guodong Zhou

Sentiment Analysis

Challenge:	Existing studies on aspect sentiment classification focus on non-interactive reviews . a new task aims to predict sentiment polarities for specific aspects from interactive reviews based on annotated corpus .
Approach:	They propose a task to predict aspects from interactive QA style reviews using an annotated corpus.
Outcome:	The proposed approach is compared with state-of-the-art methods against a high-quality corpus of data.

STINMatch: Semi-Supervised Semantic-Topological Iteration Network for Financial Risk Detection via News Label Diffusion (2023.emnlp-main)

Copied to clipboard

Xurui Li, Yue Qin, Rui Zhu, Tianqianjin Lin, Yongming Fan, Yangyang Kang, Kaisong Song, Fubang Zhao, Changlong Sun, Haixu Tang, Xiaozhong Liu

Multimodality

Challenge:	Commercial news provides rich semantics and timely information for automated financial risk detection.
Approach:	They propose a semi-supervised Semantic-Topological Iteration Network, STINMatch, along with a news-enterprise knowledge graph to endorse the risk detection enhancement.
Outcome:	The proposed model outperforms existing models in terms of generalization and semantics and annotation.

PDAMeta: Meta-Learning Framework with Progressive Data Augmentation for Few-Shot Text Classification (2024.lrec-main)

Copied to clipboard

Xurui Li, Kaisong Song, Tianqianjing Lin, Yangyang Kang, Fubang Zhao, Changlong Sun, Xiaozhong Liu

Low-Resource NLP

Challenge:	Existing text data augmentation methods can not ensure the diversity and quality of the generated data, which leads to sub-optimal performance.
Approach:	They propose a meta-learning framework with progressive data augmentation for few-shot text classification using prompt-based data augmented by attention-based methods.
Outcome:	The proposed framework outperforms state-of-the-art models and shows better robustness on four public few-shot text classification datasets.

LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation (2026.acl-long)

Copied to clipboard

Weikang Yuan, Kaisong Song, Zhuoren Jiang, Junjie Cao, Yujie Zhang, Jun Lin, Kun Kuang, Ji Zhang, Xiaozhong Liu

"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations (2026.acl-long)

Challenge:	Current systems for legal consultation are insufficient to handle the knowledge-intensive nature of real-world consultations.
Approach:	They propose a multi-turn benchmark dataset to evaluate LLMs in legal consultation settings.
Outcome:	The proposed framework assesses LLMs’ consultation capabilities in terms of (1) clarification capability and (2) professional advice quality.

Copied to clipboard

Yang Wu, Jinhong Yu, Jingwei Xiong, Zhimin Tao, Xiaozhong Liu

A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis (2021.emnlp-main)

Challenge:	Existing large language models (LLMs) are reactive and respond only when prompted, limiting their effectiveness in collaborative settings.
Approach:	They introduce a proactive LLM assistant designed to enhance biomedical collaboration between AI systems and human experts through timely, context-aware interventions.
Outcome:	The proposed model outperforms baselines in intervention precision and collaborative task utility, highlighting the potential of proactive LLMs as intelligent scientific assistants.

Copied to clipboard

Jiawei Liu, Kaisong Song, Yangyang Kang, Guoxiu He, Zhuoren Jiang, Changlong Sun, Wei Lu, Xiaozhong Liu

Sentiment Classification towards Question-Answering with Hierarchical Matching Network (D18-1)

Challenge:	Recent efforts to predict chatbot failure hatches vital apprehensions due to complexity of human conversation.
Approach:	They propose a model that integrates dialogue satisfaction estimation and handoff prediction in one multi-task learning framework.
Outcome:	The proposed model integrates dialogue satisfaction estimation and handoff prediction in one multi-task learning framework.

Copied to clipboard

Chenlin Shen, Changlong Sun, Jingjing Wang, Yangyang Kang, Shoushan Li, Xiaozhong Liu, Luo Si, Min Zhang, Guodong Zhou

Information Retrieval

Challenge:	Existing methods to classify QA text contain rich sentiment information.
Approach:	They propose a task/method to address QA sentiment analysis by annotating QA text pair with annotation guidelines.
Outcome:	The proposed method can learn the matching vectors of each Q-sentence, A-sentent unit.

Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning (2021.findings-acl)

Copied to clipboard

Fubang Zhao, Zhuoren Jiang, Yangyang Kang, Changlong Sun, Xiaozhong Liu

Low-Resource NLP

Challenge:	Existing models for relational fact extraction do not analyze the output data structure from the perspective of graph representation flexibility and heterogeneity.
Approach:	They propose a relational fact extraction model based on graph-oriented analytical perspective that outperforms other models.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets and shows that it is flexible and space-efficient.

"I Don’t Know What to Say": A Fact-Filling Questionnaire Method to Help Non-Experts Talk to LegalAI Assistant (2026.findings-acl)

Copied to clipboard

Yuting Huang, Yiquan Wu, Meitong Guo, Ang Li, Xiaozhong Liu, Keting Yin, Fei Wu, Kun Kuang

Natural Language Interfaces

Challenge:	Recent advances in large language models (LLMs) have greatly expanded the scope of legal AI.
Approach:	They propose a method that generates questionnaires to help users refine queries . they leverage an iterative training process that collects valuable questionnaires .
Outcome:	The proposed method improves the completeness of queries and ensures the performance of domain-specific models in downstream legal tasks.

Content- and Topology-Aware Representation Learning for Scientific Multi-Literature (2023.emnlp-main)

Copied to clipboard

Kai Zhang, Kaisong Song, Yangyang Kang, Xiaozhong Liu

Representation Learning

Challenge:	Existing approaches focus on learning textual information at sentence- or document-level, but ignore inter-document connections.
Approach:	They propose a model that extends representation learning to the multi-document level . it integrates latent semantic and rich relatedness information from topological networks .
Outcome:	The proposed model learns latent semantic information from content and rich relatedness information from topological networks.

Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning (D19-1)

Copied to clipboard

Jingjing Wang, Changlong Sun, Shoushan Li, Jiancheng Wang, Luo Si, Min Zhang, Xiaozhong Liu, Guodong Zhou