Papers by June Park

1 papers
Conflict-Aware Soft Prompting for Retrieval-Augmented Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies show that REtrieval-augmented generation (RAG) fails to resolve the conflict between incorrect external context and correct parametric knowledge.
Approach: They propose a conflict-aware REtrieval-augmented generation system that encodes external context into compact memory embeddings and captures a guidance signal that directs reasoning toward the more reliable knowledge source.
Outcome: Extensive experiments show that CARE effectively mitigates context-memory conflicts, leading to an average performance gain of 5.0% on QA and fact-checking benchmarks.

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