Lean 4 Programming Language
PulseAugur coverage of Lean 4 Programming Language — every cluster mentioning Lean 4 Programming Language across labs, papers, and developer communities, ranked by signal.
15 day(s) with sentiment data
-
Neuro-symbolic framework improves math statement autoformalization
Researchers have developed a new neuro-symbolic framework called Decompose, Structure, and Repair (DSR) to improve the process of autoformalization, which translates natural language mathematical statements into formal …
-
ImProver 2 framework optimizes formal math proofs with small AI models
Researchers have developed ImProver 2, a neurosymbolic framework designed to optimize formal mathematical proofs within the Lean 4 environment. This system employs an expert-iteration pipeline and a scaffold that integr…
-
New tensor algebra embeds equivariance for symmetry discovery
Researchers have developed a new tensor algebra framework called $\star_G$ that intrinsically embeds equivariance, allowing for symmetry-preserving tensor approximation and physical symmetry discovery. This framework of…
-
Research proves feature ranking impossible under collinearity
A new research paper published on arXiv demonstrates that no feature ranking method can be simultaneously faithful, stable, and complete when features are collinear. The study proves this impossibility and quantifies it…
-
AI theorem prover struggles with global math proof in Lean 4
This paper details a case study using the Aristotle API for AI-assisted theorem proving within the Lean 4 formalization environment. The study focused on the Grasshopper problem, a challenge from IMO 2009. While the AI …
-
New method decomposes uncertainty in generative AI for scientific discovery
Researchers have developed a new method to decompose epistemic uncertainty in sequential generative models, particularly those used in AI-driven scientific discovery. By fitting polynomial chaos expansions to ensembles …
-
Formal Conjectures benchmark advances AI math discovery
Researchers have introduced Formal Conjectures, a new benchmark designed to evaluate automated reasoning systems in mathematics. This evolving dataset, formalized in Lean 4, comprises over 2600 mathematical problem stat…
-
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 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…
-
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…
-
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…
-
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…
-
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…
-
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…
-
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…