AI Paper Atlas

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

Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers

Albert Qiaochu Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzygóźdź, Piotr Miłoś, Yuhuai Wu, Mateja Jamnik

NeurIPS 2022 · Large language models › Agents, code and math · approach: Retrieval-augmented formal theorem proving · 20 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
offload premise selection to Sledgehammer via a learned <hammer> token (Thor) instead of a plain language model700M language model · PISA/testsuccess rate (%): 39.0 -> 57.0Improved
integrate hammer inside the proof search instead of taking the union of separate LM and Sledgehammer resultsThor · PISA/testsuccess rate (%): 48.8 -> 57.0Improved
use Thor on MiniF2F instead of the plain language model700M language model · MiniF2F testsuccess rate (%): 24.2 -> 29.9Improved
train the model to also learn how to select premises (no <hammer> replacement) (ablation)Thor · PISA/testsuccess rate (%): 57.0 -> 55.4Hurt
add most recent proof step as context in the input (ablation)Thor · PISA/testsuccess rate (%): 53.6 -> 57.0Improved
raise sampling temperature from 1.0 to 1.2 (ablation)Thor · PISA/testsuccess rate (%): 55.7 -> 57.0Improved
Thor vs expert iteration at fraction of the computelanguage model for theorem proving · MiniF2F testsuccess rate (%): 29.6 -> 29.9Improved

Later papers that compared with this method

3 later accepted papers report Thor as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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