proxy-analyzer

Tag

Cards List
#proxy-analyzer

Hallucination Detection via Activations of Open-Weight Proxy Analyzers

arXiv cs.CL · 6d ago Cached

This paper introduces a proxy-analyzer framework that detects hallucinations in large language models by analyzing internal activations of small, open-weight models rather than the generator itself. The method achieves superior performance on benchmarks like RAGTruth compared to existing methods like ReDeEP, demonstrating that model size is less critical than the analysis approach.

0 favorites 0 likes
← Back to home

Submit Feedback