Papers by Huiyuan Xie

4 papers
Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are used as automatic evaluators to provide accurate and reliable assessments.
Approach: They propose a framework that integrates LLM-based judgment models into a multi-agent system and simulates the interactive client-server polling mechanism.
Outcome: The proposed framework outperforms supervised models trained on annotated judgment data while requiring no human-labeled annotations.
TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing dialog models can generate on-topic utterances but struggle to proactively switch topics.
Approach: They propose a topic-shift aware dialog benchmark based on human topic shift annotations.
Outcome: The proposed benchmark enables chatbots to generate topic-shift responses while still struggling to decide when to change topic.
LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases (2026.acl-long)

Copied to clipboard

Challenge: Legal relations are an important analytical framework for dispute resolution in civil cases.
Approach: They propose a comprehensive schema for legal relations in civil cases with hierarchical taxonomy and definitions of arguments.
Outcome: The proposed schema shows that existing LLMs lack the ability to identify civil legal relations and performance improves on downstream tasks.
LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have enabled Multi-Agent Systems (MASs) where agents interact through natural language to solve complex tasks or simulate multi-party dialogues.
Approach: They propose a linguistically-grounded game-theoretic paradigm for multi-agent dialogue generation that uses a training-free equilibrium approximation algorithm to model dialogue over communicative intents and strategies.
Outcome: The proposed framework improves agents’ communication efficiency by helping them convey their intended meaning more effectively through language.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations