Whether conclusions about latent reflection directions generalize to larger LLMs, different architectures, or broader datasets remains to be verified.

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

• Accuracy does not vary linearly with latent reflection directions; instead it follows a more non-linear mapping that requires deeper theoretical treatment.claim0.846
  Theoretical limitation identified by the authors distinguishing reflection from stylistic tasks.
• A linear reflection direction exists in reasoning LLMs' latent representation space that governs self-reflection behaviorclaim0.832
  Core claim of ReflCtrl that a single direction captures and controls reflection
• Connecting the Dots: LLMs Can Infer and Verbalize Latent Structure from Disparate Training Data (Treutlein et al. 2024)concept0.816
  Out-of-context reasoning work directly related to synthetic document fine-tuning experiments
• 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.claim0.811
  Central empirical conclusion of the paper about the fundamental limits of truth directions.
• The two-dimensional subspace reported by Burger et al. (2024) seems to reflect a stage of transition in the model's processing, rather than a universal property of truth directions.quote0.801
  Load-bearing interpretive claim about the layer-specificity of Burger et al.'s finding.
• As LLMs scale, they develop increasingly general abstractions, with large models linearly representing abstract concepts like truth that capture shared properties of diverse inputsclaim0.801
  Interpretive claim connecting scale to abstraction level in LLM representations
• Reflection-inducing directions emerge more clearly in higher layers (ℓ>5) for both models and datasetsfinding0.799
  Empirical observation about which network layers encode reflection-relevant information.
• Where inside the LLM should we look for an accurate truth direction that will generalize the most across tasks?question0.796
  One of the three guiding research questions of the paper.