Fast and Accurate Factual Inconsistency Detection Over Long Documents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lattimer, Barrett Martin, Chen, Patrick, Zhang, Xinyuan, Yang, Yi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914951948402688
author Lattimer, Barrett Martin
Chen, Patrick
Zhang, Xinyuan
Yang, Yi
author_facet Lattimer, Barrett Martin
Chen, Patrick
Zhang, Xinyuan
Yang, Yi
contents Generative AI models exhibit remarkable potential; however, hallucinations across various tasks present a significant challenge, particularly for longer inputs that current approaches struggle to address effectively. We introduce SCALE (Source Chunking Approach for Large-scale inconsistency Evaluation), a task-agnostic model for detecting factual inconsistencies using a novel chunking strategy. Specifically, SCALE is a Natural Language Inference (NLI) based model that uses large text chunks to condition over long texts. This approach achieves state-of-the-art performance in factual inconsistency detection for diverse tasks and long inputs. Additionally, we leverage the chunking mechanism and employ a novel algorithm to explain SCALE's decisions through relevant source sentence retrieval. Our evaluations reveal that SCALE outperforms existing methods on both standard benchmarks and a new long-form dialogue dataset ScreenEval we constructed. Moreover, SCALE surpasses competitive systems in efficiency and model explanation evaluations. We have released our code and data publicly to GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2310_13189
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Fast and Accurate Factual Inconsistency Detection Over Long Documents
Lattimer, Barrett Martin
Chen, Patrick
Zhang, Xinyuan
Yang, Yi
Computation and Language
Artificial Intelligence
Generative AI models exhibit remarkable potential; however, hallucinations across various tasks present a significant challenge, particularly for longer inputs that current approaches struggle to address effectively. We introduce SCALE (Source Chunking Approach for Large-scale inconsistency Evaluation), a task-agnostic model for detecting factual inconsistencies using a novel chunking strategy. Specifically, SCALE is a Natural Language Inference (NLI) based model that uses large text chunks to condition over long texts. This approach achieves state-of-the-art performance in factual inconsistency detection for diverse tasks and long inputs. Additionally, we leverage the chunking mechanism and employ a novel algorithm to explain SCALE's decisions through relevant source sentence retrieval. Our evaluations reveal that SCALE outperforms existing methods on both standard benchmarks and a new long-form dialogue dataset ScreenEval we constructed. Moreover, SCALE surpasses competitive systems in efficiency and model explanation evaluations. We have released our code and data publicly to GitHub.
title Fast and Accurate Factual Inconsistency Detection Over Long Documents
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2310.13189