Perez et al. 2022: Discovering language model behaviors with model-written evaluations

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

• Ouyang et al. 2022: Training language models to follow instructions with human feedbackconcept0.812
  RLHF paper cited as a major fine-tuning technique used in commercial dialogue agents
• Bias in language modelsconcept0.788
  Features related to gender, racial, ethnic biases, slurs, and hate speech.
• Language Modelconcept0.785
  Primary test domain for manifold steering, including reasoning and ICL tasks
• Zhu et al. 2024 - Language models represent beliefs of self and othersconcept0.782
  Key prior finding that LLMs can internally represent beliefs of self and others, motivating SOO approach
• Steering Language Models With Activation Engineering (Turner et al., 2023)concept0.781
  Foundational paper introducing activation steering methodology used in this work
• Yao et al. 2023: ReAct — synergizing reasoning and acting in language modelsconcept0.779
  Paper on reasoning and acting in LLMs; cited as example of extended dialogue agent capabilities
• Models might produce first-person experiential language by drawing on human-authored self-descriptions in pretraining data without internally encoding these acts as roleplayhypothesis0.777
  Alternative hypothesis for how experience reports arise without explicit performance
• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model (Li et al., 2023)concept0.776
  Safety intervention that relies on activation modification, which ESR might undermine