CLAIFeb 28, 2024

A Sentiment Consolidation Framework for Meta-Review Generation

arXiv:2402.18005v230 citationsh-index: 36ACL
AI Analysis

This addresses the challenge of sentiment summarization in scientific domains, but it is incremental as it builds on existing LLM capabilities.

The paper tackles the problem of generating meta-reviews by proposing a three-layer sentiment consolidation framework, and finds that prompting LLMs with this framework yields better results compared to simple instructions.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes