7 papers
AbstRAG: Learning to Abstract for Retrieval Problems
Lei Xu, Xin Quan, Daniel Pedronette +1
Retrieval-augmented generation often fails when the query, the document evidence, and the user's intent are expressed at different levels of abstraction. A query may ask about a cl…
Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization
Lei Xu, Xin Quan, André Freitas
Autoformalization (AF) requires both prover acceptance and fidelity to an informal source, but prover acceptance alone cannot establish fidelity, and expert-validated reference for…
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Sirui Chen, Lei Xu, Yuying Zhao +6
Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewar…
CauScientist: Teaching LLMs to Respect Data for Causal Discovery
Bo Peng, Sirui Chen, Lei Xu +1
Causal discovery is fundamental to scientific understanding and reliable decision-making. Existing approaches face critical limitations: purely data-driven methods suffer from stat…
DEPO: Dual-Efficiency Preference Optimization for LLM Agents
Sirui Chen, Mengshi Zhao, Lei Xu +5
Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes…
Synthesis by Design: Controlled Data Generation via Structural Guidance
Lei Xu, Sirui Chen, Yuxuan Huang +1
Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets throu…
Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability
Yujin Han, Lei Xu, Sirui Chen +2
Large language models (LLMs) have shown remarkable capability in natural language tasks, yet debate persists on whether they truly comprehend deep structure (i.e., core semantics)…