AI Paper Atlas

Research map / Large language models / Agents, code and math

Question Asking as Program Generation

Anselm Rothe, Brenden M Lake, Todd Gureckis

NeurIPS 2017 · Large language models › Agents, code and math · approach: LLM-guided program synthesis · 9 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
Add informativeness features to the full model (ablation)Question generation model · Held-out contextslog likelihood: -1464.65 -> -1400.06Improved
Add informativeness features to the full model (ablation)Question generation model · Held-out contextsSpearman's rank correlation: 0.65 -> 0.64Mixed
Add the complexity feature to the full model (ablation)Question generation model · Held-out contextslog likelihood: -22993.38 -> -1400.06Improved
Add the complexity feature to the full model (ablation)Question generation model · Held-out contextsSpearman's rank correlation: -0.36 -> 0.64Improved
Add answer type features to the full model (ablation)Question generation model · Held-out contextslog likelihood: -1419.26 -> -1400.06Improved
Add answer type features to the full model (ablation)Question generation model · Held-out contextsSpearman's rank correlation: 0.55 -> 0.64Improved

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