Do language models possess knowledge (soundness)? - HackMD

# Do language models possess knowledge (soundness)?  ### Author

Do language models possess knowledge (soundness)? - HackMD # Do language models possess knowledge (soundness)?  ### Authors: [Tarun Chitra](twitter.com/tarunchitra) and [Henry Prior](twitter.com/priorupdates) ([Gauntlet](gauntlet.network)) In this post we explore how interactive proofs, a concept of interest in theoretical computer science and cryptography, can be useful for testing capabilities of language models. We consider how a setup comprised of multiple language models could be used in place of prompt tuning for this purpose. Our goal is to try to und

saved by

• Ratan Kaliani

related reading

• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
• The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
• Modifying LLM Beliefs with Synthetic Document Finetuningalignment.anthropic.com
• Large Language Model: world models or surface statistics?thegradient.pub
• 2310.10631arxiv.org
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Against LLM Reductionism — LessWronglesswrong.com
• Do large language models understand us? | by Blaise Aguera y Arcas | Mediummedium.com
• Believe It or Not: How Deeply do LLMs Believe Implanted Facts?alignment.anthropic.com
• Physics of Language Modelsphysics.allen-zhu.com
• Taking LLMs Seriously (As Language Models) — LessWronglesswrong.com