Summary of Llm-arc: Enhancing Llms with An Automated Reasoning Critic, by Aditya Kalyanpur et al.
LLM-ARC: Enhancing LLMs with an Automated Reasoning Critic
by Aditya Kalyanpur, Kailash Karthik Saravanakumar, Victor Barres, Jennifer Chu-Carroll, David Melville, David Ferrucci
First submitted to arxiv on: 25 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This neuro-symbolic framework combines Large Language Models (LLMs) with an Automated Reasoning Critic (ARC) to enhance logical reasoning capabilities. The Actor-Critic method involves generating declarative logic programs, testing their semantic correctness, and refining the code through iterative feedback from the critic. Implemented using Answer Set Programming (ASP), LLM-ARC achieves a new state-of-the-art accuracy of 88.32% on the FOLIO benchmark, significantly outperforming LLM-only baselines. The framework’s best result is achieved through fully automated self-supervised training, utilizing end-to-end dialog traces with critic feedback. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary We developed a new way to make computers better at understanding and reasoning about language. Our approach combines two ideas: large language models (LLMs) that are great at generating text and logical reasoning systems that can evaluate the correctness of that text. We call this combined system LLM-ARC, or Large Language Model-Automated Reasoning Critic. LLM-ARC does a much better job than just using an LLM alone at understanding complex language-based problems. |
Keywords
» Artificial intelligence » Large language model » Self supervised
