Papers by Guan Yuan

7 papers
ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch (2025.emnlp-main)

Copied to clipboard

Challenge: Existing instruction data synthesis methods focus on single-turn instructions and neglect cross-turn coherence, resulting in context drift and reduced task completion rates.
Approach: They propose a framework that constrains multi-turn instruction synthesis by explicitly modeling human conversational intent.
Outcome: The proposed framework outperforms existing models trained on single-turn and multi-turn instruction datasets.
Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown great potential to enhance Natural Language Processing (NLP) models in areas such as predictive accuracy, fairness, robustness, and explainability.
Approach: They evaluate or improve generative Large Language Models from a causal perspective in areas such as reasoning capacity, fairness and safety issues, explainability, and handling multimodality.
Outcome: The proposed models can be used to perform causal relationship discovery and causal effect estimation tasks.
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to safety alignment of large language models rely on costly manual annotations or human review.
Approach: They propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative collaboration among three roles with near-zero manual annotation.
Outcome: The proposed framework achieves 20%–50% improvement in adversarial effectiveness while preserving high output diversity while achieving 10%–30% gains in safety performance without degrading general reasoning capability.
Improving Role-Oriented Dialogue Summarization with Interaction-Aware Contrastive Learning (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for encoding dialogues do not capture interaction information between roles, thus ignore interaction-related key information.
Approach: They propose a contrastive learning based interaction-aware model for the role-oriented dialogue summarization namely CIAM and use it to train the decoder to learn role-level interaction.
Outcome: The proposed model captures interaction information between different roles and produces informative summaries on two public datasets.
Common Law Annotations: Investigating the Stability of Dialog System Output Annotations (2023.findings-acl)

Copied to clipboard

Challenge: High agreement is often used to show reliability of annotation procedures, but it is insufficient to ensure or reproducibility.
Approach: They propose a protocol that increases Inter-Annotator Agreement among annotators and a standardized and codified protocol that strictly enforces transparency in the annotation process.
Outcome: The proposed protocol ensures transparency in the annotation process, which ensures reproducibility of annotation guidelines.
CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks (2026.acl-long)

Copied to clipboard

Challenge: Existing large language models for software engineering rely on coarse-grained pass rates obscuring specific cognitive bottlenecks.
Approach: They propose a repository-level benchmark that dissects coding capabilities through atomized tasks.
Outcome: The proposed framework achieves a 78.55% validity yield, surpassing the 31.7% retention rate of SWE-bench-Verified.
Minimal Free Resolution Guided Adaptive Tree Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to building dynamic reasoning trees rely on manual decomposition patterns and subproblems.
Approach: They propose a hierarchical reasoning framework based on MFR theory that supports adaptive reasoning trees and reliable error correction within a single LLM.
Outcome: The proposed framework significantly reduces logical errors and improves reasoning accuracy compared to the Chain-of-Thought, Decompose–Analyze–Rethink and Tree-of–Though.

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