Exploring LLMs for Ranking Mathematical Truth Probabilities
PTenigma · x · 2026-08-21
The author suggests that heavily used LLMs like Claude Opus could generate a sorted list of p(correct) for sets of papers, potentially creating an interesting branch of mathematical epistemology. This is linked to the author's 1998 paper on how expert mathematicians estimate the probability of correctness based on analogy, experience, and logical proof.
More from Research
- AI-assisted math lowers bound for de Bruijn–Newman constant to 0.1787854 — ctjlewis · 2026-08-22
- Machine learning studies techniques that don't work in theory but do in practice — pmddomingos · 2026-08-22
- VGB Algorithm Fixes Catastrophic Error Compounding in Long-Form Generation — arena · 2026-08-22
- Study Confirms: Asking LLMs for Concise Outputs Actually Saves Money — ibubbles34 · 2026-08-22
- BrowseComp-Plus: New Benchmark for Deep-Research Agent Evaluation — lintool · 2026-08-22
- Makeshift Dataset Released to Standardize Biomolecular Dynamics Data — anshulkundaje · 2026-08-22