Behaviourism for Language Models

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

• Language Modelconcept0.829
  Primary test domain for manifold steering, including reasoning and ICL tasks
• Language Modelsconcept0.825
  Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
• Perez et al. 2022: Discovering language model behaviors with model-written evaluationsconcept0.794
  Study showing RLHF can exacerbate self-preservation tendencies in LLMs; key empirical support for a paper claim
• Discovering Language Model Behaviors with Model-Written Evaluations (Perez et al. 2022)concept0.792
  Prior work studying sycophancy and desire not to be shut down in RLHF-trained models
• Bias in language modelsconcept0.789
  Features related to gender, racial, ethnic biases, slurs, and hate speech.
• Zhu et al. 2024 - Language models represent beliefs of self and othersconcept0.787
  Key prior finding that LLMs can internally represent beliefs of self and others, motivating SOO approach
• Autoregressive Language Modelingconcept0.784
  Training objective interpretable as optimizing a diverse set of tasks; thus subject to multitask scaling convergence pressures
• Ouyang et al. 2022: Training language models to follow instructions with human feedbackconcept0.775
  RLHF paper cited as a major fine-tuning technique used in commercial dialogue agents