REVIEW 5 cited by
An In-Context Learning Agent for Formal Theorem-Proving
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present an in-context learning agent for formal theorem-proving in environments like Lean and Coq. Current state-of-the-art models for the problem are finetuned on environment-specific proof data. By contrast, our approach, called COPRA, repeatedly asks a high-capacity, general-purpose large language model (GPT-4) to propose tactic applications from within a stateful backtracking search. Proposed tactics are executed in the underlying proof environment. Feedback from the execution is used to build the prompt for the next model query, along with selected information from the search history and lemmas retrieved from an external database. We evaluate our implementation of COPRA on the miniF2F benchmark for Lean and a set of Coq tasks from the CompCert project. On these benchmarks, COPRA significantly outperforms few-shot invocations of GPT-4. It also compares favorably against finetuning-based approaches, outperforming ReProver, a state-of-the-art finetuned approach for Lean, in terms of the pass@1 metric. Our code and data are available at https://github.com/trishullab/copra.
Forward citations
Cited by 5 Pith papers
-
Discovering New Theorems via LLMs with In-Context Proof Learning in Lean
LLMs in a conjecturing-proving loop that conditions on their own prior verified Lean proofs discover more hard-to-prove theorems than baselines that generate statements and proofs together.
-
MATP-BENCH: Can MLLM Be a Good Automated Theorem Prover for Multimodal Problems?
MATP-BENCH pairs 1,056 multimodal math problems with formal theorem statements in Lean 4, Coq, and Isabelle; the strongest tested model solves only 5.68% of Lean 4 end-to-end proving tasks at pass@10.
-
Solving Formal Math Problems by Decomposition and Iterative Reflection
An agent that decomposes Lean 4 goals into subproblems and iteratively repairs proofs achieves a 95.9% pass rate on miniF2F-test using a stock Gemini model.
-
Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
The proposed Faithful-Refiner, combining syntactic parsing, quantifier and consistency checks, logical-relation guidance, and detailed proof feedback, raises explanation refinement rates on three NLI benchmarks by lar...
-
Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
A grammar-based model of LLM-generated SMT-LIB code produces uncertainty signals that predict formalization errors on some reasoning tasks, with fused signals giving large error reductions only in an in-sample evaluation.
Discussion (0). Continue with ORCID to comment.