Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Sentiment Consolidation Framework for Meta-Review Generation (2402.18005v2)

Published 28 Feb 2024 in cs.CL and cs.AI

Abstract: Modern natural language generation systems with 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (15)
  1. Unsupervised opinion summarization with content planning. In AAAI, pages 12489–12497.
  2. Metagen: An academic meta-review generation system. In SIGIR, pages 1653–1656.
  3. Automatic text summarization: A comprehensive survey. Expert Systems with Applications, 165:113679.
  4. Repairing the cracked foundation: A survey of obstacles in evaluation practices for generated text. JAIR, 77:103–166.
  5. Exploring sentiments in summarization: Sentitextrank, an emotional variant of textrank. In Proceedings of the 9th Italian Conference on Computational Linguistics, volume 3596.
  6. Comprehensive review of opinion summarization.
  7. Summarizing multiple documents with conversational structure for meta-review generation. In Findings of EMNLP.
  8. Compressed heterogeneous graph for abstractive multi-document summarization. In AAAI.
  9. Chin-Yew Lin and Eduard H. Hovy. 2003. Automatic evaluation of summaries using n-gram co-occurrence statistics. In HLT-NAACL, pages 71–78.
  10. G-eval: NLG evaluation using GPT-4 with better human alignment. CoRR, abs/2303.16634.
  11. Summarization is (almost) dead. CoRR, abs/2309.09558.
  12. Incorporating peer reviews and rebuttal counter-arguments for meta-review generation. In CIKM, pages 2189–2198.
  13. Bertscore: Evaluating text generation with BERT. In ICLR.
  14. A survey of large language models. CoRR, abs/2303.18223.
  15. Towards a unified multi-dimensional evaluator for text generation. In EMNLP, pages 2023–2038.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Miao Li (156 papers)
  2. Jey Han Lau (67 papers)
  3. Eduard Hovy (115 papers)
Citations (1)