A Sentiment Consolidation Framework for Meta-Review Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Miao, Lau, Jey Han, Hovy, Eduard
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917684149485568
author Li, Miao
Lau, Jey Han
Hovy, Eduard
author_facet Li, Miao
Lau, Jey Han
Hovy, Eduard
contents Modern natural language generation systems with Large Language Models (LLMs) exhibit the capability to generate a plausible summary of multiple documents; however, it is uncertain if they truly possess the capability of information consolidation to generate summaries, especially on documents with opinionated information. We focus on meta-review generation, a form of sentiment summarisation for the scientific domain. To make scientific sentiment summarization more grounded, we hypothesize that human meta-reviewers follow a three-layer framework of sentiment consolidation to write meta-reviews. Based on the framework, we propose novel prompting methods for LLMs to generate meta-reviews and evaluation metrics to assess the quality of generated meta-reviews. Our framework is validated empirically as we find that prompting LLMs based on the framework -- compared with prompting them with simple instructions -- generates better meta-reviews.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18005
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Sentiment Consolidation Framework for Meta-Review Generation
Li, Miao
Lau, Jey Han
Hovy, Eduard
Computation and Language
Artificial Intelligence
Modern natural language generation systems with Large Language Models (LLMs) exhibit the capability to generate a plausible summary of multiple documents; however, it is uncertain if they truly possess the capability of information consolidation to generate summaries, especially on documents with opinionated information. We focus on meta-review generation, a form of sentiment summarisation for the scientific domain. To make scientific sentiment summarization more grounded, we hypothesize that human meta-reviewers follow a three-layer framework of sentiment consolidation to write meta-reviews. Based on the framework, we propose novel prompting methods for LLMs to generate meta-reviews and evaluation metrics to assess the quality of generated meta-reviews. Our framework is validated empirically as we find that prompting LLMs based on the framework -- compared with prompting them with simple instructions -- generates better meta-reviews.
title A Sentiment Consolidation Framework for Meta-Review Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.18005