通过融合多种技术提升大模型推理可靠性
Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification
- 结合思维链、外部检索与自校验机制增强推理
- 自校验策略使事实错误率显著降低
- 适合需要高可信度回答的复杂任务场景
大语言模型在处理复杂开放任务时，常因幻觉问题生成看似合理却错误或无关的信息。思维链（CoT）提示法通过引导模型经历中间推理步骤，提升了多步推理能力，但无法完全解决幻觉问题。本文研究将思维链与检索增强生成（RAG）结合，并引入自一致性与自校验策略，以减少幻觉并提升事实准确性。通过在推理过程中引入外部知识源，并让模型自主验证或修正自身输出，从而生成更准确、连贯的回答。我们对基线模型与不同方法组合进行了对比评估，结果表明各技术均有效，且综合自校验与RAG的方案在保持语言流畅性和推理深度的同时，最有效地抑制了幻觉。
原文摘要 · Abstract (English)
Hallucination, where large language models (LLMs) generate confident but incorrect or irrelevant information, remains a key limitation in their application to complex, open-ended tasks. Chain-of-thought (CoT) prompting has emerged as a promising method for improving multistep reasoning by guiding models through intermediate steps. However, CoT alone does not fully address the hallucination problem. In this work, we investigate how combining CoT with retrieval-augmented generation (RAG), as well as applying self-consistency and self-verification strategies, can reduce hallucinations and improve factual accuracy. By incorporating external knowledge sources during reasoning and enabling models to verify or revise their own outputs, we aim to generate more accurate and coherent responses. We present a comparative evaluation of baseline LLMs against CoT, CoT+RAG, self-consistency, and self-verification techniques. Our results highlight the effectiveness of each method and identify the most robust approach for minimizing hallucinations while preserving fluency and reasoning depth.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。