Bakhtin et al. 2022 - Human-level play in the game of Diplomacy by combining language models with strategic reasoning

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

• Today's Large Language Models have become so good at playing Turing's game that it often takes experts to demonstrate the present limits of their ability to simulate human-like intelligence.claim0.780
  Paper's assessment of current LLM capabilities relative to Turing Test
• Ouyang et al. 2022: Training language models to follow instructions with human feedbackconcept0.774
  RLHF paper cited as a major fine-tuning technique used in commercial dialogue agents
• The most effective strategy is not to cling to a single metaphor but to shift freely between multiple metaphors for LLM-based dialogue agentsclaim0.764
  Meta-level methodological claim about conceptual frameworks for LLMs
• Language models are few-shot learners (Brown et al., 2020)concept0.762
  Demonstrated transformers on mathematical understanding and logic; cited to motivate transformer versatility.
• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model (Li et al., 2023)concept0.760
  Safety intervention that relies on activation modification, which ESR might undermine
• Multi-turn strategic play depends on capabilities (state tracking, adaptive resource allocation, structured-output reliability) that static benchmarks do not measure but conversational evaluations partially captureclaim0.757
  explains divergence from static benchmarks
• Towards Monosemanticity: Decomposing Language Models with Dictionary Learning (Bricken et al., 2023)concept0.756
  Foundational SAE mechanistic interpretability paper
• Models might produce first-person experiential language by drawing on human-authored self-descriptions in pretraining data without internally encoding these acts as roleplayhypothesis0.756
  Alternative hypothesis for how experience reports arise without explicit performance