Exploring Iterative Controllable Summarization with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ryu, Sangwon, Do, Heejin, Kim, Daehee, Yu, Hwanjo, Kim, Dongwoo, Kim, Yunsu, Lee, Gary Geunbae, Ok, Jungseul
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915713282736128
author Ryu, Sangwon
Do, Heejin
Kim, Daehee
Yu, Hwanjo
Kim, Dongwoo
Kim, Yunsu
Lee, Gary Geunbae
Ok, Jungseul
author_facet Ryu, Sangwon
Do, Heejin
Kim, Daehee
Yu, Hwanjo
Kim, Dongwoo
Kim, Yunsu
Lee, Gary Geunbae
Ok, Jungseul
contents Large language models (LLMs) have demonstrated remarkable performance in abstractive summarization tasks. However, their ability to precisely control summary attributes (e.g., length or topic) remains underexplored, limiting their adaptability to specific user preferences. In this paper, we systematically explore the controllability of LLMs. To this end, we revisit summary attribute measurements and introduce iterative evaluation metrics, failure rate and average iteration count to precisely evaluate controllability of LLMs, rather than merely assessing errors. Our findings show that LLMs struggle more with numerical attributes than with linguistic attributes. To address this challenge, we propose a guide-to-explain framework (GTE) for controllable summarization. Our GTE framework enables the model to identify misaligned attributes in the initial draft and guides it in self-explaining errors in the previous output. By allowing the model to reflect on its misalignment, GTE generates well-adjusted summaries that satisfy the desired attributes with robust effectiveness, requiring surprisingly fewer iterations than other iterative approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12460
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Iterative Controllable Summarization with Large Language Models
Ryu, Sangwon
Do, Heejin
Kim, Daehee
Yu, Hwanjo
Kim, Dongwoo
Kim, Yunsu
Lee, Gary Geunbae
Ok, Jungseul
Computation and Language
Artificial Intelligence
Large language models (LLMs) have demonstrated remarkable performance in abstractive summarization tasks. However, their ability to precisely control summary attributes (e.g., length or topic) remains underexplored, limiting their adaptability to specific user preferences. In this paper, we systematically explore the controllability of LLMs. To this end, we revisit summary attribute measurements and introduce iterative evaluation metrics, failure rate and average iteration count to precisely evaluate controllability of LLMs, rather than merely assessing errors. Our findings show that LLMs struggle more with numerical attributes than with linguistic attributes. To address this challenge, we propose a guide-to-explain framework (GTE) for controllable summarization. Our GTE framework enables the model to identify misaligned attributes in the initial draft and guides it in self-explaining errors in the previous output. By allowing the model to reflect on its misalignment, GTE generates well-adjusted summaries that satisfy the desired attributes with robust effectiveness, requiring surprisingly fewer iterations than other iterative approaches.
title Exploring Iterative Controllable Summarization with Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.12460