# A Sentiment Consolidation Framework for Meta-Review Generation

arXiv: https://arxiv.org/abs/2402.18005 · HTML: https://mlsanity.com/paper/2402.18005/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 10 of 10)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text](https://mlsanity.com/paper/2202.06935/) (2022)
- [Investigating Efficiently Extending Transformers for Long Input Summarization](https://mlsanity.com/paper/2208.04347/) (2022)
- [MReD: A Meta-Review Dataset for Structure-Controllable Text Generation](https://mlsanity.com/paper/2110.07474/) (2021)
- [Unsupervised Opinion Summarization with Content Planning](https://mlsanity.com/paper/2012.07808/) (2020)
- [Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation](https://mlsanity.com/paper/2305.01498/) (2023)
- [Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation](https://mlsanity.com/paper/2305.14647/) (2023)
- [A Unified Dual-view Model for Review Summarization and Sentiment Classification with Inconsistency Loss](https://mlsanity.com/paper/2006.01592/) (2020)

## Built on by (most cited first, 10 of 10)

- [WritingBench: A Comprehensive Benchmark for Generative Writing](https://mlsanity.com/paper/2503.05244/) (2025)
- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems](https://mlsanity.com/paper/2503.01424/) (2025)
- [Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future](https://mlsanity.com/paper/2604.27924/) (2026)
- [Decomposed Opinion Summarization with Verified Aspect-Aware Modules](https://mlsanity.com/paper/2501.17191/) (2025)
- [PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality](https://mlsanity.com/paper/2606.20897/) (2026)
- [SEAGraph: Unveiling the Whole Story of Paper Review Comments](https://mlsanity.com/paper/2412.11939/) (2024)
- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)
- [MOSAIC: Modular Opinion Summarization using Aspect Identification and Clustering](https://mlsanity.com/paper/2603.19277/) (2026)
- [When Evidence Conflicts: Reliability-aware Meta-review Generation](https://mlsanity.com/paper/2609.24028/) (2026)

## Abstract (arXiv)

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.