Liu Leqi

Learning Composable Chains-of-Thought

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes

More of the Same: Persistent Representational Harms Under Increased Representation

ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning

EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations

A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement

Prompting Fairness: Integrating Causality to Debias Large Language Models

Personalized Language Modeling from Personalized Human Feedback

A Unified Causal Framework for Auditing Recommender Systems for Ethical Concerns