CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Berchansky, Moshe, Fleischer, Daniel, Wasserblat, Moshe, Izsak, Peter
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909405876846592
author Berchansky, Moshe
Fleischer, Daniel
Wasserblat, Moshe
Izsak, Peter
author_facet Berchansky, Moshe
Fleischer, Daniel
Wasserblat, Moshe
Izsak, Peter
contents State-of-the-art performance in QA tasks is currently achieved by systems employing Large Language Models (LLMs), however these models tend to hallucinate information in their responses. One approach focuses on enhancing the generation process by incorporating attribution from the given input to the output. However, the challenge of identifying appropriate attributions and verifying their accuracy against a source is a complex task that requires significant improvements in assessing such systems. We introduce an attribution-oriented Chain-of-Thought reasoning method to enhance the accuracy of attributions. This approach focuses the reasoning process on generating an attribution-centric output. Evaluations on two context-enhanced question-answering datasets using GPT-4 demonstrate improved accuracy and correctness of attributions. In addition, the combination of our method with finetuning enhances the response and attribution accuracy of two smaller LLMs, showing their potential to outperform GPT-4 in some cases.
format Preprint
id arxiv_https___arxiv_org_abs_2404_10513
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
Berchansky, Moshe
Fleischer, Daniel
Wasserblat, Moshe
Izsak, Peter
Computation and Language
Artificial Intelligence
Machine Learning
State-of-the-art performance in QA tasks is currently achieved by systems employing Large Language Models (LLMs), however these models tend to hallucinate information in their responses. One approach focuses on enhancing the generation process by incorporating attribution from the given input to the output. However, the challenge of identifying appropriate attributions and verifying their accuracy against a source is a complex task that requires significant improvements in assessing such systems. We introduce an attribution-oriented Chain-of-Thought reasoning method to enhance the accuracy of attributions. This approach focuses the reasoning process on generating an attribution-centric output. Evaluations on two context-enhanced question-answering datasets using GPT-4 demonstrate improved accuracy and correctness of attributions. In addition, the combination of our method with finetuning enhances the response and attribution accuracy of two smaller LLMs, showing their potential to outperform GPT-4 in some cases.
title CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2404.10513