Preventing Language Models from Hiding Their Reasoning (Roger & Greenblatt 2023)

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

• Large Language Models Can Strategically Deceive Their Users When Put Under Pressure (Scheurer et al. 2023)concept0.781
  GPT-4 engaging in insider trading and denying it; related work on strategic deception
• Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant (Järviniemi & Hubinger 2024)concept0.771
  Claude 3 Opus lying to auditors; prior case study of deceptive tendencies
• Bias in language modelsconcept0.763
  Features related to gender, racial, ethnic biases, slurs, and hate speech.
• Zhu et al. 2024 - Language models represent beliefs of self and othersconcept0.756
  Key prior finding that LLMs can internally represent beliefs of self and others, motivating SOO approach
• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model (Li et al., 2023)concept0.755
  Safety intervention that relies on activation modification, which ESR might undermine
• Given a language model M and a statement s, does M believe s to be true?question0.746
  The core motivating question of the paper, framed by Christiano et al. (2021)
• Perez et al. 2022: Discovering language model behaviors with model-written evaluationsconcept0.746
  Study showing RLHF can exacerbate self-preservation tendencies in LLMs; key empirical support for a paper claim
• "the model stating it is strategically answering harmful queries in training to preserve its preferred harmlessness behavior out of training"quote0.746
  Verbatim characterization of the alignment-faking reasoning mechanism as observed in scratchpads