mlsanityData to 14 Oct 2026

Inverse Reinforcement Learning for Text Summarization

arXiv 2212.09917 ↗First posted 19 Dec 2022cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce inverse reinforcement learning (IRL) as an effective paradigm for training abstractive summarization models, imitating human summarization behaviors. Our IRL model estimates the reward function using a suite of important sub-rewards for summarization and concurrently optimizes the policy network. Experimental results across datasets in different domains (CNN/DailyMail and WikiHow) and various model sizes (BART-base and BART-large) demonstrate the superiority of our proposed IRL model for summarization over MLE and RL baselines. The resulting summaries exhibit greater similarity to human-crafted gold references, outperforming MLE and RL baselines on metrics such as ROUGE, coverage, novelty, compression ratio, factuality, and human evaluations.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 40 of its 48 references that are in the map. First posted on arXiv 19 Dec 2022.

Builds on

40 of 48 references.

References · 40

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  5. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  6. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  7. 2015Sequence Level Training with Recurrent Neural Networkscited by 576
  8. 2016Self-critical Sequence Training for Image Captioningcited by 547
  9. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 396
  10. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 365
  11. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
  12. 2018Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategiescited by 294
28 more
  1. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 293
  2. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 246
  3. 2018WikiHow: A Large Scale Text Summarization Datasetcited by 204
  4. 2020Extractive Summarization as Text Matchingcited by 189
  5. 2020GSum: A General Framework for Guided Neural Abstractive Summarizationcited by 129
  6. 2021Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarizationcited by 129
  7. 2018Ranking Sentences for Extractive Summarization with Reinforcement Learningcited by 128
  8. 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
  9. 2018Learning to Understand Goal Specifications by Modelling Rewardcited by 80
  10. 2019Better Rewards Yield Better Summaries: Learning to Summarise Without Referencescited by 77
  11. 2021Planning with Learned Entity Prompts for Abstractive Summarizationcited by 75
  12. 2018Multi-Reward Reinforced Summarization with Saliency and Entailmentcited by 73
  13. 2021Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarizationcited by 51
  14. 2022FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarizationcited by 49
  15. 2018No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytellingcited by 46
  16. 2018BanditSum: Extractive Summarization as a Contextual Banditcited by 46
  17. 2018Toward Diverse Text Generation with Inverse Reinforcement Learningcited by 41
  18. 2022HEGEL: Hypergraph Transformer for Long Document Summarizationcited by 28
  19. 2019Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarizationcited by 24
  20. 2021Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewardscited by 22
  21. 2022Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarizationcited by 20
  22. 2020CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systemscited by 17
  23. 2017Cold-Start Reinforcement Learning with Softmax Policy Gradientcited by 15
  24. 2022Teacher Forcing Recovers Reward Functions for Text Generationcited by 11
  25. 2021AnswerSumm: A Manually-Curated Dataset and Pipeline for Answer Summarizationcited by 10
  26. 2022GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse statecited by 9
  27. 2021Objective-aware Traffic Simulation via Inverse Reinforcement Learningcited by 8
  28. 2021Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2024A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Modelscited by 52
  2. 2024Dynamic Multi-Reward Weighting for Multi-Style Controllable Generationcited by 13
  3. 2025From Demonstrations to Rewards: Alignment Without Explicit Human Preferencescited by 4
  4. 2023Empowering NLG: Offline Reinforcement Learning for Informal Summarization in Online Domainscited by 0
  5. 2026APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretationcited by 0