LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations · HackerPapers discussions

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations — mentioned by dofm

Fri, 31 Jul 2026 21:23:08 GMT

You certainly can't ask an LLM for its confidence level because it will generate that answer as it sees fit. My understanding was that models can be post-trained to assess their own confidence on short prompts within a level of accuracy (there was an article about this a few weeks ago that I can't find), but can't use it to reason, and that research has shown that internally they effectively have a measurable sense of truth but can't surface it: https://arxiv.org/abs/2410.02707 I mangled what I was trying to say but the point I guess is, it is effectively in there, and researchers can see it…

Paper and discussion history. A mention is not an endorsement.

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations — mentioned by mike_hearn

Thu, 05 Dec 2024 09:55:23 GMT

He does get it and models do know their own confidence levels with a remarkably high degree of accuracy. The article states this clearly: > Encoded truth: Recent work suggests that LLMs encode more truthfulness than previously understood, with certain tokens concentrating this information, which improves error detection. However, this encoding is complex and dataset-specific, hence limiting generalization. Notably, models may be encoding the correct answers internally despite generating errors, highlighting areas for targeted mitigation strategies. Linking to this paper…

Paper and discussion history. A mention is not an endorsement.

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations — HN submission

Wed, 30 Oct 2024 14:22:18 GMT

LLMs know more than they show: On the intrinsic representation of hallucinations

137 points; 140 discussion replies on HN. Paper and source history. A submission is not an endorsement.

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations — HN submission

Tue, 08 Oct 2024 08:27:54 GMT

LLMs Know More Than They Show

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.