AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

Why think step by step? Reasoning emerges from the locality of experience

Ben Prystawski, Michael Y. Li, Noah Goodman

NeurIPS 2023 · Large language models › Reasoning and chain of thought · approach: Search and self-correction in reasoning · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
generate intermediate variables (free/scaffolded) before target instead of direct prediction (ablation)autoregressive transformer on Bayes net samples · held-out high-MI pairs, local trainingMSE to true conditional probabilityImproved
generate intermediate variables when training data is fully observed (ablation)autoregressive transformer · held-out pairs, fully observed trainingMSE to true conditional probabilityNo clear effect
use wrong-locality training data (ablation)autoregressive transformer · held-out pairsMSE to true conditional probability: MSE vs true on seen pairs .004 -> .052Hurt
use irrelevant (negative) scaffold variables instead of relevant scaffold (ablation)scaffolded generation · held-out pairs, local trainingMSE to true conditional probabilityHurt
combine local training data with free generation reasoningautoregressive transformer · data efficiencytraining tokens to match conditional probabilities: direct prediction on fully observed data needs over 3x more trainingImproved
resample intermediate variables more times (more Monte Carlo samples) (ablation)free/scaffolded generation · held-out pairsMSEImproved
train on local data, direct prediction on pairs that co-occur (ablation)direct prediction · non-held-out pairsMSE to true conditional probability: .013 (fully observed) -> .004 (local geom)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy