Saved in:
Bibliographic Details
Main Authors: Kumar, Adarsh, Kim, Hwiyoon, Nathani, Jawahar Sai, Roy, Neil
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.09031
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909610134208512
author Kumar, Adarsh
Kim, Hwiyoon
Nathani, Jawahar Sai
Roy, Neil
author_facet Kumar, Adarsh
Kim, Hwiyoon
Nathani, Jawahar Sai
Roy, Neil
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09031
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification
Kumar, Adarsh
Kim, Hwiyoon
Nathani, Jawahar Sai
Roy, Neil
Artificial Intelligence
Computation and Language
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.
title Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2505.09031