Chain-of-Verification Reduces Hallucination in Large Language Models

Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li +2 more
9/20/2023
cs.CLcs.AI

No official code found. Best implementation: thuanystuart/DD3412-chain-of-verification-reproduction (6 stars, last commit 2023-12-15).

Abstract

Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their mistakes. We develop the Chain-of-Verification (CoVe) method whereby the model first (i) drafts an initial response; then (ii) plans verification questions to fact-check its draft; (iii) answers those questions independently so the answers are not biased by other responses; and (iv) generates its final verified response. In experiments, we show CoVe decreases hallucinations across a variety of tasks, from list-based questions from Wikidata, closed book MultiSpanQA and longform text generation.

View on arXivView PDF

Code Implementations(1)

thuanystuart/DD3412-chain-of-verification-reproductionCommunity61%

Re-implementation of the paper "Chain-of-Verification Reduces Hallucination in Large Language Models" for hallucination reduction. Developed as a final project of the Advanced Deep Learning course (DD3412) at KTH.

62Shell, PythonNov 21, 20232 years ago
deep-learninghallucinationprompt-engineeringpython

Similar Papers

Zero-Resource Hallucination Prevention for Large Language Models

91% match1 repo82023

Building Reliable Long-Form Generation via Hallucination Rejection Sampling

90% match1 repo12026

HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering

90% match2026

Alleviating Hallucinations of Large Language Models through Induced Hallucinations

90% match2 repos72.8k2023

HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models

90% match1 repo5952023

A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation

89% match2023

Cite this paper

@article{dhuliawala2023chainofverification,
  title  = {Chain-of-Verification Reduces Hallucination in Large Language Models},
  author = {Shehzaad Dhuliawala and Mojtaba Komeili and Jing Xu and Roberta Raileanu and Xian Li and Asli Celikyilmaz and Jason Weston},
  year   = {2023},
  eprint = {2309.11495},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.11495v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.11495.svg)](https://codeofpaper.com/paper/2309.11495)

Discussion