AI Paper Atlas

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

LoC-Decomp: LLM Autoformalization via Logical Concept Decomposition and Iterative Feedback Correction

Jiangze Shi, Zhiwei Zhang, Baoquan Ma, Shuai Zhao, Ye Yuan, Guoren Wang

ICLR 2026 · Large language models › Agents, code and math · approach: Formal verification and proof data

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 iterative rectification (3 rounds) (ablation)LoC-Decomp · MATH-500 (ASCC-3-MV)pass rate: 63.20 -> 84.00Improved
add iterative rectification (3 rounds) (ablation)LoC-Decomp · miniF2F (ASCC-3-MV)pass rate: 77.25 -> 90.16Improved
add iterative rectification (3 rounds) (ablation)LoC-Decomp · PutnamBench (ASCC-3-MV)pass rate: 48.37 -> 81.50Improved
add iterative rectification (3 rounds) (ablation)LoC-Decomp · MATH-Level5-50 (human eval)pass rate: 70.00 -> 84.00Improved
use LoC-Decomp template and few-shot examples (no iteration) vs basic few-shot baseline (ablation)DeepSeek-V3 · MATH-Level5-50 (human eval)pass rate: 52.00 -> 70.00Improved
use ASCC semantic checker instead of basic semantic checker in the iterative loop (ablation)iterative formalization · MATH-Level5-50 (human eval)pass rate: 54.00 -> 84.00Improved
use ASCC-3-MV (majority vote) checker instead of plain SC-Baseline (ablation)semantic consistency checking · MATH-ASCC-Eval-150precision: 0.68 -> 0.90Improved
compare LoC-Decomp with DeepSeek-Prover-V2 on ProofNetLoC-Decomp · ProofNet (LLM-judge pass rate)pass rate: 73.57 vs 83.10Hurt

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