factuality-detection

Tag

Cards List
#factuality-detection

Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness

arXiv cs.CL · 2026-04-20 Cached

This paper challenges the assumption that LLMs can reliably distinguish between hallucinated and factual outputs through internal signals, arguing that internal states primarily reflect knowledge recall rather than truthfulness. The authors propose a taxonomy of hallucinations (associated vs. unassociated) and show that associated hallucinations exhibit hidden-state geometries overlapping with factual outputs, making standard detection methods ineffective.

0 favorites 0 likes
← Back to home

Submit Feedback