Bias in language models

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

• Language Modelsconcept0.827
  Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
• Language Modelconcept0.825
  Primary test domain for manifold steering, including reasoning and ICL tasks
• Zhu et al. 2024 - Language models represent beliefs of self and othersconcept0.793
  Key prior finding that LLMs can internally represent beliefs of self and others, motivating SOO approach
• Anisotropy in Language Modelsconcept0.792
  Property of smaller saturated models making hidden states harder to access via alignment maps
• Perez et al. 2022: Discovering language model behaviors with model-written evaluationsconcept0.788
  Study showing RLHF can exacerbate self-preservation tendencies in LLMs; key empirical support for a paper claim
• Language models implement algorithms humans have tried and failed to write by hand for decadesclaim0.785
  Opening interpretive claim about the remarkable nature of language models.
• Autoregressive Language Modelingconcept0.781
  Training objective interpretable as optimizing a diverse set of tasks; thus subject to multitask scaling convergence pressures
• Language models are few-shot learners (Brown et al., 2020)concept0.780
  Demonstrated transformers on mathematical understanding and logic; cited to motivate transformer versatility.