Papers by Mengqiao Liu

3 papers
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Incomplete learning is widespread and heterogeneous in large language models . authors identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between SFT supervision and pre-training knowledge, internal inconsistencies within SFT data, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns.
Approach: They propose a diagnostic-first framework that maps incomplete learning to causes . they identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between supervision and pre-training knowledge, internal inconsistencies, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns.
Outcome: The proposed framework maps incomplete learning to causes using observable training and inference signals.
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to generating reward models rely on voting-based mechanisms to evaluate CoT outputs.
Approach: They propose an efficient generative reward modeling framework grounded in model-internal uncertainty.
Outcome: The proposed framework reduces inference cost while improving answer accuracy.
Understand User Opinions of Large Language Models via LLM-Powered In-the-Moment User Experience Interviews (2025.findings-acl)

Copied to clipboard

Challenge: Existing large language models (LLMs) are difficult to evaluate and often lack the ability to capture user opinions.
Approach: They propose an LLM-powered interviewer that conducts in-the-moment user experience interviews right after users interact with LLMs and automatically gathers insights about user opinions from massive interview logs.
Outcome: The proposed interviewer captures interesting user opinions, e.g., bipolar views on the displayed reasoning process of DeepSeek-R1 and demands for information freshness and multi-modality.

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