← Search

Keyu Hu

2 accepted papers

2026

REFO: Reinforced Evolutionary Faithfulness Optimization for Large Language Models

AAAI 2026technical

Despite its success in enriching LLMs with external knowledge, RAG remains plagued by faithfulness hallucinations, where generated text contradicts the retrieved source information. Previous research on faithfulness hallucination in LLMs is frequently hindered by prohibitive manual annotation costs

Cited by 0SourcePDFScholar
2025

CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models

ACL 2025long

Faithfulness hallucinations are claims generated by a Large Language Model (LLM) not supported by contexts provided to the LLM. Lacking assessment standards, existing benchmarks focus on “factual statements” that rephrase source materials while overlooking “cognitive statements” that involve making…