Induction and Inquiry via Probabilistic Reasoning over Language and Code
Source
Wasu Top Piriyakulkij, Sam Acquaviva, Cassidy Langenfeld, Joshua Tenenbaum, Kevin Ellis
Author
Wasu Top Piriyakulkij, Sam Acquaviva, Cassidy Langenfeld, Joshua Tenenbaum, Kevin Ellis
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
Offers a usable representation for uncertainty-aware learning: hypotheses as language-plus-code programs updated by LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →-guided Bayesian inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition →, which supports choosing the next informative question instead of guessing.
articleModular Cognitive Architecture Emerges in Large Language ModelsPengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda
articleNeuro-Formal Verification: Agentic Language-Agnostic Formal Program ReasoningShuvendu K. Lahiri
articleMemorization Diagnostics for Code LLMs Should be Scale-AwarePrateek Kumar Rajput, Abdoul Aziz Bonkoungou, Alberick Euraste Djir\'e, Xunzhu Tang, Yewei Song, Iyiola Emmanuel Olatunji, El Hacen Diallo, Jacques Klein, Tegawend\'e F. Bissyand\'e