LLM-ARC: Enhancing LLMs with an Automated Reasoning Critic

• URL: http://arxiv.org/abs/2406.17663v2
• Date: Fri, 19 Jul 2024 12:59:11 GMT
• Title: LLM-ARC: Enhancing LLMs with an Automated Reasoning Critic
• Authors: Aditya Kalyanpur, Kailash Karthik Saravanakumar, Victor Barres, Jennifer Chu-Carroll, David Melville, David Ferrucci,
• Abstract summary: We introduce LLM-ARC, a neuro-symbolic framework designed to enhance the logical reasoning capabilities of Large Language Models (LLMs) LLMs-ARC employs an Actor-Critic method where the LLM Actor generates declarative logic programs along with tests for semantic correctness, while the Automated Reasoning Critic evaluates the code, runs the tests and provides feedback on test failures for iterative refinement. Our experiments demonstrate significant improvements over LLM-only baselines, highlighting the importance of logic test generation and iterative self-refinement.
• Score: 2.1073328551105623
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce LLM-ARC, a neuro-symbolic framework designed to enhance the logical reasoning capabilities of Large Language Models (LLMs), by combining them with an Automated Reasoning Critic (ARC). LLM-ARC employs an Actor-Critic method where the LLM Actor generates declarative logic programs along with tests for semantic correctness, while the Automated Reasoning Critic evaluates the code, runs the tests and provides feedback on test failures for iterative refinement. Implemented using Answer Set Programming (ASP), LLM-ARC achieves a new state-of-the-art accuracy of 88.32% on the FOLIO benchmark which tests complex logical reasoning capabilities. Our experiments demonstrate significant improvements over LLM-only baselines, highlighting the importance of logic test generation and iterative self-refinement. We achieve our best result using a fully automated self-supervised training loop where the Actor is trained on end-to-end dialog traces with Critic feedback. We discuss potential enhancements and provide a detailed error analysis, showcasing the robustness and efficacy of LLM-ARC for complex natural language reasoning tasks.

Related papers

• RuAG: Learned-rule-augmented Generation for Large Language Models [62.64389390179651]
  We propose a novel framework, RuAG, to automatically distill large volumes of offline data into interpretable first-order logic rules. We evaluate our framework on public and private industrial tasks, including natural language processing, time-series, decision-making, and industrial tasks.
  arXiv  Detail & Related papers  (2024-11-04T00:01:34Z)
• Automated Theorem Provers Help Improve Large Language Model Reasoning [0.18416014644193066]
  We show how accuracy can be improved with a neuro-symbolic architecture. We define a framework of syntactic and semantic error categories. We extend our method with capabilities for automatically correcting syntactic and semantic errors.
  arXiv  Detail & Related papers  (2024-08-07T01:03:56Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing [56.75702900542643]
  We introduce AlphaLLM for the self-improvements of Large Language Models. It integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop. Our experimental results show that AlphaLLM significantly enhances the performance of LLMs without additional annotations.
  arXiv  Detail & Related papers  (2024-04-18T15:21:34Z)
• RITFIS: Robust input testing framework for LLMs-based intelligent software [6.439196068684973]
  RITFIS is the first framework designed to assess the robustness of intelligent software against natural language inputs. RITFIS adapts 17 automated testing methods, originally designed for Deep Neural Network (DNN)-based intelligent software. It demonstrates the effectiveness of RITFIS in evaluating LLM-based intelligent software through empirical validation.
  arXiv  Detail & Related papers  (2024-02-21T04:00:54Z)
• Are Large Language Models Good Prompt Optimizers? [65.48910201816223]
  We conduct a study to uncover the actual mechanism of LLM-based Prompt Optimization. Our findings reveal that the LLMs struggle to identify the true causes of errors during reflection, tending to be biased by their own prior knowledge. We introduce a new "Automatic Behavior Optimization" paradigm, which directly optimize the target model's behavior in a more controllable manner.
  arXiv  Detail & Related papers  (2024-02-03T09:48:54Z)
• LLMs for Relational Reasoning: How Far are We? [8.840750655261251]
  Large language models (LLMs) have revolutionized many areas by achieving state-of-the-art performance on downstream tasks. Recent efforts have demonstrated that the LLMs are poor at solving sequential decision-making problems.
  arXiv  Detail & Related papers  (2024-01-17T08:22:52Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• Exploring Self-supervised Logic-enhanced Training for Large Language Models [59.227222647741094]
  In this paper, we make the first attempt to investigate the feasibility of incorporating logical knowledge through self-supervised post-training. We devise an auto-regressive objective variant of MERIt and integrate it with two LLM series, i.e., FLAN-T5 and LLaMA, with parameter size ranging from 3 billion to 13 billion. The results on two challenging logical reasoning benchmarks demonstrate the effectiveness of LogicLLM.
  arXiv  Detail & Related papers  (2023-05-23T06:13:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.