Would comparable experiments with other languages yield substantially different results about causal mechanisms LMs learn?

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

• CausalGym only includes English data; comparable experiments with other languages might yield substantially different resultsquestion0.816
  Identified limitation/gap calling for cross-lingual extension of CausalGym
• Understanding how LMs learn linguistic behaviours may offer insights into fundamental properties of languagehypothesis0.787
  Forward-looking hypothesis linking LM mechanism analysis to linguistic theory
• LLMs trained only on language data have rich knowledge of visual structures sufficient to train decent visual representationsclaim0.777
  Supporting evidence for cross-modal platonic representation
• The better an LLM is at language modeling, the more it aligns with vision models, and vice versa — linear relationship between language modeling score and vision-language alignmentfinding0.773
  Core cross-modal empirical result: larger and better language models align better with vision models
• Connecting the Dots: LLMs Can Infer and Verbalize Latent Structure from Disparate Training Data (Treutlein et al. 2024)concept0.768
  Out-of-context reasoning work directly related to synthetic document fine-tuning experiments
• 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 LLMfinding0.765
  Sharma et al. result supporting cross-modal alignment: language-only models implicitly encode visual structure
• The results are more widely applicable; similar results will come from asking people in other cultures to answer analogous questions.claim0.758
  Universalist claim predicting cross-cultural generality.
• LLMs linearly represent truth-relevant information beyond the plausibility of text, as evidenced by probes trained on likely performing poorly on anti-correlated datasetsclaim0.757
  Establishes that the observed linear structure is not merely a representation of text probability