Papers by Yongmei Zhou

2 papers
PrefRAG: Correcting Semantic Errors in Auto-Formalization for Logical Reasoning with Program Preference RAG (2026.findings-acl)

Copied to clipboard

Challenge: Existing auto-formalization methods for logical reasoning are prone to syntactic and semantic errors.
Approach: They propose a neuro-symbolic paradigm for logical reasoning based on auto-formalization . they propose 'programme preference retrieval-augmented generation' to detect and repair syntactic and semantic errors.
Outcome: The proposed approach outperforms baselines on in-distribution and out-of-difference datasets.
Jailbreaking? One Step Is Enough! (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs.
Approach: They propose a Reverse Embedded Defense Attack mechanism that disguises the attack intention as the "defense" intention against harmful content.
Outcome: The proposed method outperforms existing methods on open-source and closed-source models and enables successful jailbreak in one iteration.

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