Papers by Yucong Luo

2 papers
Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for enhancing response accuracy and accuracy struggle with open-domain QA tasks because they perform independent retrieval operations without maintaining a summarizing memory or using adaptive retrieval strategies.
Approach: They propose a method that integrates non-parametric knowledge from external knowledge bases into models to enhance response accuracy while mitigating factual errors and hallucinations.
Outcome: The proposed method improves on open-domain QA datasets and reduces noise and hallucinations due to redundant information and insufficient information integration.
HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Challenge: Current approaches to addressing knowledge outdating in LLMs struggle with retrieval and generation aspects when handling outdated information.
Approach: They propose a benchmark to evaluate the impact of outdated information on RAG . they use token-level diff algorithms and LLM pipelines to create a large-scale QA dataset .
Outcome: The proposed benchmark analyzes the impact of outdated information on RAG performance.

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