Papers by Xueyang Feng

7 papers
Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have propelled the development of Conversational Recommendation Agents (CRAs).
Approach: They propose a multi-turn preference optimization paradigm that leverages Expectation Confirmation Theory to explicitly model the evolution of user satisfaction throughout multi-turned dialogues.
Outcome: The proposed paradigm eliminates the significant sampling overhead of existing MTPO methods while ensuring the optimization process drives meaningful improvements.
KAPA: A Deliberative Agent Framework with Tree-Structured Knowledge Base for Multi-Domain User Intent Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on the use of LLMs for estimating user intents are either too far from real human thought processes or require labeled samples.
Approach: They propose a deliberative agent framework that leverages human thought process to build high-level domain knowledge and a tree-structured knowledge base to store refined experience and data.
Outcome: The proposed framework is able to build high-level domain knowledge and efficiently store it across multiple steps.
Large Language Model-based Human-Agent Collaboration for Complex Task Solving (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in large language models have led to the development of LLM-based autonomous agents.
Approach: They propose a Reinforcement Learning-based Human-Agent Collaboration method which trains a policy model to determine the most opportune stages for human intervention within the task-solving process.
Outcome: The proposed method improves human-agent collaboration significantly through well-planned, limited human intervention.
Event Representation Learning with Multi-Grained Contrastive Learning and Triple-Mixture of Experts (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for learning event representations fail to capture hidden feature information between events.
Approach: They propose a method that extends the random masked language model by incorporating a specialized MLM to capture different grammatical structures within events.
Outcome: The proposed method outperforms baselines in hard similarity and transitive sentence similarity tasks, highlighting the superiority of the proposed method.
Enhancing Recommendation Explanations through User-Centric Refinement (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing explanations for user reviews often fail to meet user-centric aspects, reducing their usefulness to users.
Approach: They propose a paradigm that refines initial explanations generated by existing models during the inference stage to enhance their quality in multiple aspects.
Outcome: The proposed model improves explanations generated by existing models during the inference stage to enhance their quality in multiple aspects.
Improving Retrospective Language Agents via Joint Policy Gradient Optimization (2025.naacl-long)

Copied to clipboard

Challenge: Recent advances in large language models have sparked interest in creating autonomous agents.
Approach: They propose a framework that jointly optimizes both task-planning and self-reflective evolution capabilities in language agents.
Outcome: The proposed framework improves task planning and self-reflective evolution capabilities in language agents.
Temporal Cognitive Tree: A Hierarchical Modeling Approach for Event Temporal Relation Extraction (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent studies focus on locating relative position of event pairs on timeline . hierarchical modeling approach neglects multidimensional information in temporal relation and hierarchy of reasoning.
Approach: They propose a novel hierarchical modeling approach that mimics human logical reasoning by introducing a Temporal Cognitive Tree.
Outcome: The proposed model outperforms existing methods on TB-Dense and MATRES datasets.

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