Yao et al. 2023: ReAct — synergizing reasoning and acting in language models

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

• Perez et al. 2022: Discovering language model behaviors with model-written evaluationsconcept0.779
  Study showing RLHF can exacerbate self-preservation tendencies in LLMs; key empirical support for a paper claim
• Steering Language Models With Activation Engineering (Turner et al., 2023)concept0.777
  Foundational paper introducing activation steering methodology used in this work
• Ouyang et al. 2022: Training language models to follow instructions with human feedbackconcept0.769
  RLHF paper cited as a major fine-tuning technique used in commercial dialogue agents
• Discovering Language Model Behaviors with Model-Written Evaluations (Perez et al. 2022)concept0.757
  Prior work studying sycophancy and desire not to be shut down in RLHF-trained models
• Towards Monosemanticity: Decomposing Language Models with Dictionary Learning (Bricken et al., 2023)concept0.753
  Foundational SAE mechanistic interpretability paper
• Zhu et al. 2024 - Language models represent beliefs of self and othersconcept0.748
  Key prior finding that LLMs can internally represent beliefs of self and others, motivating SOO approach
• Andreas 2022: Language models as agent modelsconcept0.747
  Paper hypothesising LLMs model agent beliefs/desires/intentions with preliminary GPT-3 evidence; cited as ref 2
• Bakhtin et al. 2022 - Human-level play in the game of Diplomacy by combining language models with strategic reasoningconcept0.747
  Key reference documenting Meta's CICERO using deception in Diplomacy despite cooperative design intent