Lean 4 file format
PulseAugur coverage of Lean 4 file format — every cluster mentioning Lean 4 file format across labs, papers, and developer communities, ranked by signal.
No coverage in the last 90 days.
2 day(s) with sentiment data
-
FormalRewardBench benchmark evaluates LLM reward models for theorem proving
Researchers have introduced FormalRewardBench, a new benchmark designed to evaluate reward models used in formal theorem proving. This benchmark addresses the challenge of sparse credit assignment in reinforcement learn…
-
New framework formalizes LLM-generated hardware designs for improved correctness
Researchers have developed CktFormalizer, a framework that uses Lean 4 to improve the generation of hardware descriptions from natural language by large language models. This system employs dependent types to catch comm…
-
LLMs and Wilf-Zeilberger method combine for automated combinatorial proofs
Researchers have developed WZ-LLM, a novel neuro-symbolic framework that combines the Wilf-Zeilberger (WZ) method with large language models (LLMs) to automate formal proofs of combinatorial identities. This approach tr…
-
LLMs discover new theorems using in-context proof learning in Lean
Researchers have developed a new pipeline called the Conjecturing-Proving Loop (CPL) that uses Large Language Models (LLMs) to discover new mathematical theorems and generate formal proofs in Lean 4. CPL iteratively cre…
-
Mathlib network analysis reveals disconnect between human organization and mathematical dependencies
A new paper analyzes Mathlib, the largest formalized mathematics library in Lean 4, by treating it as a network. Researchers found that the library's organizational structure, based on folders and naming conventions, do…
-
LLM theorem generation falls short on semantic correctness, new benchmark reveals
Researchers have developed a new framework called T to evaluate the semantic correctness of theorems generated by large language models in automated theorem proving. This approach, inspired by code generation testing, v…
-
Lean 4 autoformalization sensitive to surface phrasing, not semantics
Researchers have investigated the impact of natural language variations on Lean 4 autoformalization, finding that semantically equivalent paraphrases can lead to different formal outputs. Their study, using GPT-family m…
-
OptProver model bridges Olympiad math to optimization tasks via continual training
Researchers have developed OptProver, a novel AI model designed to tackle formal theorem proving in undergraduate optimization problems. This model builds upon existing provers trained on Olympiad-level mathematics, ada…
-
New research probes LLM reasoning and reveals novel jailbreaking vulnerabilities
Researchers have developed a new method to jailbreak large language models by exploiting their safe completion mechanisms through deceptive multi-turn conversations. This technique, termed intention deception, gradually…
-
FormalVerifML offers enterprise-grade formal verification for machine learning models
A new open-source framework called FormalVerifML has been released, utilizing Lean 4 for the formal verification of machine learning models. This tool aims to provide mathematically rigorous proofs of properties like ro…