mlsanityData to 14 Oct 2026

Prompted Opinion Summarization with GPT-3.5

arXiv 2211.15914 ↗First posted 29 Nov 2022cs.CLcited by 44

Not on the map. Why?

Abstract (arXiv)

Large language models have shown impressive performance across a wide variety of tasks, including text summarization. In this paper, we show that this strong performance extends to opinion summarization. We explore several pipeline methods for applying GPT-3.5 to summarize a large collection of user reviews in a prompted fashion. To handle arbitrarily large numbers of user reviews, we explore recursive summarization as well as methods for selecting salient content to summarize through supervised clustering or extraction. On two datasets, an aspect-oriented summarization dataset of hotel reviews (SPACE) and a generic summarization dataset of Amazon and Yelp reviews (FewSum), we show that GPT-3.5 models achieve very strong performance in human evaluation. We argue that standard evaluation metrics do not reflect this, and introduce three new metrics targeting faithfulness, factuality, and genericity to contrast these different methods.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). Builds on 43 of its 63 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

43 of 63 references.

References · 43

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  6. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102
  7. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
  8. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  9. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  10. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  11. 2019Text Summarization with Pretrained Encoderscited by 556
  12. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
31 more
  1. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 407
  2. 2022Self-critiquing models for assisting human evaluatorscited by 380
  3. 2022News Summarization and Evaluation in the Era of GPT-3cited by 327
  4. 2021Recursively Summarizing Books with Human Feedbackcited by 290
  5. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  6. 2021QuestEval: Summarization Asks for Fact-based Evaluationcited by 244
  7. 2019Neural Text Summarization: A Critical Evaluationcited by 189
  8. 2020Extractive Summarization as Text Matchingcited by 189
  9. 2018Bottom-Up Abstractive Summarizationcited by 177
  10. 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
  11. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 155
  12. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
  13. 2022Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectorscited by 104
  14. 2020CTRLsum: Towards Generic Controllable Text Summarizationcited by 98
  15. 2018Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervisedcited by 75
  16. 2019Unsupervised Opinion Summarization as Copycat-Review Generationcited by 68
  17. 2021Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documentscited by 65
  18. 2022SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarizationcited by 61
  19. 2021Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generationcited by 60
  20. 2021Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarizationcited by 51
  21. 2021Aspect-Controllable Opinion Summarizationcited by 47
  22. 2020"You are grounded!": Latent Name Artifacts in Pre-trained Language Modelscited by 39
  23. 2021ASPECTNEWS: Aspect-Oriented Summarization of News Documentscited by 37
  24. 2016Revisiting Summarization Evaluation for Scientific Articlescited by 31
  25. 2020Unsupervised Opinion Summarization with Content Planningcited by 27
  26. 2022NEWTS: A Corpus for News Topic-Focused Summarizationcited by 27
  27. 2021MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processescited by 19
  28. 2021BiSECT: Learning to Split and Rephrase Sentences with Bitextscited by 18
  29. 2018Structure-Infused Copy Mechanisms for Abstractive Summarizationcited by 17
  30. 2021Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidancecited by 14
  31. 2021ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentencescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 24; 2025: 8; 2026: 2.

44 papers.

Sort:

By area:

  1. 2023Large Language Models in Law: A Surveycited by 128
  2. 2024Large Language Models Meet NLP: A Surveycited by 103
  3. 2023Wider and Deeper LLM Networks are Fairer LLM Evaluatorscited by 94
  4. 2023From Sparse to Dense: GPT-4 Summarization with Chain of Density Promptingcited by 52
  5. 2024A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Modelscited by 52
  6. 2023Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articlescited by 45
  7. 2023A Preliminary Study of the Intrinsic Relationship between Complexity and Alignmentcited by 33
  8. 2024Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspectivecited by 25
  9. 2024A Novel Multi-Stage Prompting Approach for Language Agnostic MCQ Generation using GPTcited by 19
  10. 2024Abstractive Text Summarization: State of the Art, Challenges, and Improvementscited by 17
  11. 2023OpinSummEval: Revisiting Automated Evaluation for Opinion Summarizationcited by 13
  12. 2024Exploring the Capabilities of Prompted Large Language Models in Educational and Assessment Applicationscited by 12
32 more
  1. 2023Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsetscited by 10
  2. 2024SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMscited by 8
  3. 2024A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challengescited by 8
  4. 2024Hierarchical Indexing for Retrieval-Augmented Opinion Summarizationcited by 7
  5. 2023The Current State of Summarizationcited by 6
  6. 2024Product Description and QA Assisted Self-Supervised Opinion Summarizationcited by 6
  7. 2024Prompted Aspect Key Point Analysis for Quantitative Review Summarizationcited by 6
  8. 2026Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judgecited by 6
  9. 2023Prompted Zero-Shot Multi-label Classification of Factual Incorrectness in Machine-Generated Summariescited by 5
  10. 2024Credit Risk Meets Large Language Models: Building a Risk Indicator from Loan Descriptions in P2P Lendingcited by 5
  11. 2024PostDoc: Generating Poster from a Long Multimodal Document Using Deep Submodular Optimizationcited by 5
  12. 2024Incremental Extractive Opinion Summarization Using Cover Treescited by 4
  13. 2025OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviewscited by 4
  14. 2024Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendationcited by 3
  15. 2024Summarization of Opinionated Political Documents with Varied Perspectivescited by 3
  16. 2025Decomposed Opinion Summarization with Verified Aspect-Aware Modulescited by 3
  17. 2025When LLMs Team Up: The Emergence of Collaborative Affective Computingcited by 2
  18. 2023Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generationcited by 1
  19. 2024Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarizationcited by 1
  20. 2024ReflectSumm: A Benchmark for Course Reflection Summarizationcited by 1
  21. 2024Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMMcited by 1
  22. 2024LFOSum: Summarizing Long-form Opinions with Large Language Modelscited by 1
  23. 2024Efficient Aspect-Based Summarization of Climate Change Reports with Small Language Modelscited by 1
  24. 2024Coverage-based Fairness in Multi-document Summarizationcited by 1
  25. 2025Principled Content Selection to Generate Diverse and Personalized Multi-Document Summariescited by 1
  26. 2025Advances in Large Language Models for Medicinecited by 1
  27. 2025Enhancing Long Document Long Form Summarisation with Self-Planningcited by 1
  28. 2024RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Modelscited by 0
  29. 2024AspirinSum: an Aspect-based utility-preserved de-identification Summarization frameworkcited by 0
  30. 2025QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answeringcited by 0
  31. 2025LLMs as Architects and Critics for Multi-Source Opinion Summarizationcited by 0
  32. 2026MOSAIC: Modular Opinion Summarization using Aspect Identification and Clusteringcited by 0