LeanTool

“LeanTool: Helping LLMs Be Better at Lean”

LeanTool is a simple utility that connects LLMs with a “Code Interpreter” for Lean. This is implemented as tool calls from the LLM to the Lean executable, hence the name. … This is part of a a broader effort to create safe and hallucination-free coding AIs.

자연어 기반 AI-인간 인터렉션의 한계 ‘린 (프로그래밍 언어)’를 함께 참조
환각 (AI) “Fact-conflicting hallucination, where LLMs generate content that is not faithful to established world knowledge.”
Siren's song in the AI ocean: A survey on hallucination in large language models “Fact-conflicting hallucination, where LLMs generate content that is not faithful to established world knowledge.”
열린 도메인 환각 “Outdatedness Hallucination: This type of hallucination refers to situations where the generated content of LLMs…”
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions “Nevertheless, LLMs are prone to hallucination, generating plausible yet nonfactual content.”
AI Hallucinations: A Misnomer Worth Clarifying “As large language models continue to advance in Artificial Intelligence (AI), text generation systems have been…”
Survey of hallucination in natural language generation “In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination p…”
A comprehensive taxonomy of hallucinations in Large Language Models “Large language models (LLMs) have revolutionized natural language processing, yet their propensity for hallucin…”
LLMs will always hallucinate, and we need to live with this “This work introduces the concept of Structural Hallucination as an intrinsic nature of these systems.”
Why Language Models Hallucinate “Such "Hallucination|hallucinations" persist even in state-of-the-art systems and undermine trust.”
CodeAct: Your LLM Agent Acts Better when Generating Code “This work proposes to use executable Python code to consolidate LLM agents' actions into a unified action space…”
Self determination “Those who made proposals are expected to be responsible for implementing them - immediately.”
Language Models Know More Than They Show: Exploring Hallucinations From the Model's Viewpoint “Large language models (LLMs) often produce errors, including factual inaccuracies, biases, and reasoning failur…”
When to annotate type “This is especially important in a language like Lean that has a very expressive type system.”