question
active
question:given-a-language-model-m-and-a-statement-s-does-m-believe-s-to-be-trueGiven a language model M and a statement s, does M believe s to be true?
The core motivating question of the paper, framed by Christiano et al. (2021)
Source paper
extracted_from(2023) · Samuel Marks · Max Tegmark
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Establishes that the observed linear structure is not merely a representation of text probability
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Core open question the paper addresses through a behaviourist operationalisation.
- Key prior finding that LLMs can internally represent beliefs of self and others, motivating SOO approach
- Core open question the paper addresses regarding AI intentionality.
- Opening motivating question.
- Suggestive evidence for language-independent truth representation in LLMs
- Antonym example.
- Motivating hypothesis for Section 5's investigation of prompt template effects.
- If a model doesn't represent a concept at all, no amount of steering will change its beliefhypothesis0.788Explanation for phi-4 null effect.