The reviewed record of science sign in
Pith

arxiv: 2410.19000 · v1 · pith:U3X4PSA5 · submitted 2024-10-18 · cs.LG

Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:U3X4PSA5record.jsonopen to challenge →

classification cs.LG
keywords reasoningstructure-orientedanalysisllmsprocesssystemtasksbetter
0
0 comments X
read the original abstract

Zero-shot reasoning methods with Large Language Models (LLMs) offer significant advantages including great generalization to novel tasks and reduced dependency on human-crafted examples. However, the current zero-shot methods still have limitations in complex tasks, e.g., answering questions that require multi-step reasoning. In this paper, we address this limitation by introducing a novel structure-oriented analysis method to help LLMs better understand the question and guide the problem-solving process of LLMs. We first demonstrate how the existing reasoning strategies, Chain-of-Thought and ReAct, can benefit from our structure-oriented analysis. In addition to empirical investigations, we leverage the probabilistic graphical model to theoretically explain why our structure-oriented analysis can improve the LLM reasoning process. To further improve the reliability in complex question-answering tasks, we propose a multi-agent reasoning system, Structure-oriented Autonomous Reasoning Agents (SARA), that can better enforce the reasoning process following our structure-oriented analysis by refinement techniques and is equipped with external knowledge retrieval capability to reduce factual errors. Extensive experiments verify the effectiveness of the proposed reasoning system. Surprisingly, in some cases, the system even surpasses few-shot methods. Finally, the system not only improves reasoning accuracy in complex tasks but also demonstrates robustness against potential attacks that corrupt the reasoning process.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems

    cs.CR 2025-06 unverdicted novelty 6.0

    Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.

  2. Retrieval-Augmented Generation with Graphs (GraphRAG)

    cs.IR 2024-12 unverdicted novelty 5.0

    A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.