Enhancing Answer Attribution for Faithful Text Generation with Large Language Models

Juraj Vladika, Luca Mülln, Florian Matthes

2024

Abstract

The increasing popularity of Large Language Models (LLMs) in recent years has changed the way users interact with and pose questions to AI-based conversational systems. An essential aspect for increasing the trustworthiness of generated LLM answers is the ability to trace the individual claims from responses back to relevant sources that support them, the process known as answer attribution. While recent work has started exploring the task of answer attribution in LLMs, some challenges still remain. In this work, we first perform a case study analyzing the effectiveness of existing answer attribution methods, with a focus on subtasks of answer segmentation and evidence retrieval. Based on the observed shortcomings, we propose new methods for producing more independent and contextualized claims for better retrieval and attribution. The new methods are evaluated and shown to improve the performance of answer attribution components. We end with a discussion and outline of future directions for the task.

Paper Citation

in Harvard Style

Vladika J., Mülln L. and Matthes F. (2024). Enhancing Answer Attribution for Faithful Text Generation with Large Language Models. In Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-716-0, SciTePress, pages 147-158. DOI: 10.5220/0013066600003838

in Bibtex Style

@conference{kdir24,
author={Juraj Vladika and Luca Mülln and Florian Matthes},
title={Enhancing Answer Attribution for Faithful Text Generation with Large Language Models},
booktitle={Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2024},
pages={147-158},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013066600003838},
isbn={978-989-758-716-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Enhancing Answer Attribution for Faithful Text Generation with Large Language Models
SN - 978-989-758-716-0
AU - Vladika J.
AU - Mülln L.
AU - Matthes F.
PY - 2024
SP - 147
EP - 158
DO - 10.5220/0013066600003838
PB - SciTePress