Inference-Time Intervention: Eliciting Truthful Answers from a Language Model (Li et al., 2023)

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

• Inference-Time Intervention (ITI)method0.820
  Method by Li et al. 2023a that adds static vectors to model activations at inference time to steer behavior
• Ouyang et al. 2022: Training language models to follow instructions with human feedbackconcept0.790
  RLHF paper cited as a major fine-tuning technique used in commercial dialogue agents
• Do human participants demonstrate the same insight dynamics predicted by active inference in the rule-learning paradigm (currently under investigation with eye tracking and crowd-sourced reaction times)?question0.782
  Empirical gap explicitly acknowledged; experiments reportedly in progress at time of writing
• NLA explanations can contain claims about the target model's input context that are verifiably false, but are typically thematically faithful to the context.claim0.781
  Key limitation identified: NLAs hallucinate specific details while preserving thematic accuracy; informs practical usage.
• Chain-of-thought prompting elicits reasoning in large language models (Wei et al., 2022)concept0.780
  Foundational paper on CoT prompting cited as basis for reasoning LLM training
• Active inference LLMs extending prediction-focused language models with tighter perception-action feedback loops may naturally embody contemplative wisdom as they scalehypothesis0.779
  Predictive hypothesis about Contemplative Architecture approach based on Petersen et al. 2025 work
• Given a language model M and a statement s, does M believe s to be true?question0.778
  The core motivating question of the paper, framed by Christiano et al. (2021)
• Friston, FitzGerald et al. (2016) — Active inference and learningconcept0.778
  Prior active inference paper providing detailed neurophysiological implementation of belief updates