Popper_vonStengel_Cross_context_deduction-1.pdf
aiimpacts.org · 5,961 words · saved by 1 readers
N/A
Cross-context deduction: on the capability necessary for LLM-philosophers Rio Popper∗ Clem von Stengel† July 2024 Abstract In this paper, we define a capability we call ‘cross-context deduction’, and we argue that cross-context deduction is required for large language models (LLMs) to be able to do philos- ophy well. First, we parse out several related conceptions…
related reading
- As Rocks May Think | Eric Jangevjang.com
- LLM Daydreaming · Gwern.netgwern.net
- DeepSeek-R1arxiv.org
- Recursive Language Models | Alex L. Zhangalexzhang13.github.io
- Against LLM Reductionism — LessWronglesswrong.com
- Against LLM Reductionismerichgrunewald.com
- The Role of Deductive and Inductive Reasoning in Large Language Models - ACL Anthologyaclanthology.org
- LMCA_dataset.pdfandrew.cmu.edu
- Hot Take: LLM can 'jump'yongzx.github.io
- Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
- Do Large Language Models (LLMs) reason? | Shapedshaped.ai
- [2603.07267] How to Steal Reasoning Without Reasoning Tracesarxiv.org