https://github.com/ezelikman/parsel
공식 코드Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs
GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation
Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis
Autoformalization in the Era of Large Language Models: A Survey
Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving
AI Descartes: Combining Data and Theory for Derivable Scientific Discovery
Neural Unification for Logic Reasoning over Natural Language
Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
Logical Inferences with Comparatives and Generalized Quantifiers
Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions
Proof Artifact Co-training for Theorem Proving with Language Models
Proof Artifact Co-training for Theorem Proving with Language Models
Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
Proof Artifact Co-training for Theorem Proving with Language Models
Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
ProoFVer: Natural Logic Theorem Proving for Fact Verification
Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.