Papers by Yibin Xu

5 papers
PairCoder: Pair Programming-Inspired Two-Agent Collaboration for Code Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing multi agent frameworks for large language models are brittle on code generation tasks.
Approach: They propose a framework that brings pair programming to autonomous LLM collaboration.
Outcome: Using PairCoder, large language models achieve better results on code generation tasks and reduce token usage by 40% to 70% on eight representative backbones.
LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly important for their intelligence evaluation.
Approach: They propose a game theory-based evaluation platform that measures LLMs’ decision-making strategies and social behaviors in classic game-theoretic settings.
Outcome: The proposed system cross-evaluates 15 leading LLMs using leaderboard rankings and scoring mechanisms.
Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness (2026.findings-acl)

Copied to clipboard

Challenge: Existing abstention fine-tuning methods cause models to suffer from label noise near the decision boundaries.
Approach: They propose a latent space representation perspective for abstention fine-tuning . they propose 'geometric denoising' framework that constructs a truth hyperplane .
Outcome: The proposed framework significantly enhances model truthfulness and demonstrates strong generalization in out-of-distribution scenarios.
Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to document-level relation extraction are difficult to establish direct connections between distant entity pairs.
Approach: They propose a global context-enhanced Graph Convolutional Network model which captures rich global context information of entities in a document.
Outcome: The proposed model captures rich global context information of entities in a document.
RankAdaptor: Hierarchical Rank Allocation for Efficient Fine-Tuning Pruned LLMs via Performance Model (2025.findings-naacl)

Copied to clipboard

Challenge: Current compression techniques entail structural pruning and a recovery phase that leverages the Low-Rank Adaptation algorithm.
Approach: They propose a hierarchical rank allocation method that enables efficient fine-tuning of pruned LLMs according to layerwise specific recovery requirements.
Outcome: The proposed algorithm outperforms state-of-the-art methods across pruning settings and LLM architectures with improvements ranging from 0.7% to 5.5%.

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