Truth Direction in LLM Latent Space

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Where inside the LLM should we look for an accurate truth direction that will generalize the most across tasks?question0.832
  One of the three guiding research questions of the paper.
• Linear truth directions in LLMs are reliable primarily in factual recall cases and break down when truth assessment depends on computing and storing intermediate results.claim0.805
  Central empirical conclusion of the paper about the fundamental limits of truth directions.
• A linear reflection direction exists in reasoning LLMs' latent representation space that governs self-reflection behaviorclaim0.795
  Core claim of ReflCtrl that a single direction captures and controls reflection
• Truth Directionconcept0.781
  A hypothesized direction in LLM activation space that encodes the truth or falsehood of factual statements
• Whether conclusions about latent reflection directions generalize to larger LLMs, different architectures, or broader datasets remains to be verified.question0.779
  Key limitation and open question about experimental scope.
• Truthful behavior in LLMs is not confined to a single linear axis; multiple orthogonal directions can independently mediate itclaim0.779
  Central interpretive claim of the paper
• Do LLMs have a unified representation of truth that spans structurally and topically diverse data?question0.758
  Central research question driving dataset design and experimental approach
• Latent Direction of Reflectionconcept0.757
  The paper's central construct: a vector in LLM activation space encoding the transition between reflection levels.