Connecting the Dots: LLMs Can Infer and Verbalize Latent Structure from Disparate Training Data (Treutlein et al. 2024)

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

• LLMs trained only on language data have rich knowledge of visual structures sufficient to train decent visual representationsclaim0.848
  Supporting evidence for cross-modal platonic representation
• LLMs trained only on language data have rich enough knowledge of visual structures that decent visual representations can be trained on images generated solely by querying the LLMfinding0.844
  Sharma et al. result supporting cross-modal alignment: language-only models implicitly encode visual structure
• LLMs linearly represent truth-relevant information beyond the plausibility of text, as evidenced by probes trained on likely performing poorly on anti-correlated datasetsclaim0.829
  Establishes that the observed linear structure is not merely a representation of text probability
• Whether conclusions about latent reflection directions generalize to larger LLMs, different architectures, or broader datasets remains to be verified.question0.816
  Key limitation and open question about experimental scope.
• LLMs can predict their own responses more accurately than external observers, implying privileged internal knowledgefinding0.814
  Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
• Understanding how LMs learn linguistic behaviours may offer insights into fundamental properties of languagehypothesis0.801
  Forward-looking hypothesis linking LM mechanism analysis to linguistic theory
• LLM personality self-reports are illusory: post-training alignment creates stable human-like reports dissociated from actual behavior (Han et al. 2025)claim0.801
  Skeptical prior work motivating the need to validate self-reports against internal states rather than taking them at face value
• LLM representations exhibit intriguing patterns under spatio-permutational analyses, suggesting a potentially profound yet tentative indication of consciousness.claim0.799
  Qualified positive claim from spatio permutation analysis where two cases satisfy all three criteria.