mlsanityData to 7 Oct 2026

Improved Beam Search for Hallucination Mitigation in Abstractive Summarization

arXiv 2212.02712 ↗First posted 6 Dec 2022cs.CL cs.AI cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Advancement in large pretrained language models has significantly improved their performance for conditional language generation tasks including summarization albeit with hallucinations. To reduce hallucinations, conventional methods proposed improving beam search or using a fact checker as a postprocessing step. In this paper, we investigate the use of the Natural Language Inference (NLI) entailment metric to detect and prevent hallucinations in summary generation. We propose an NLI-assisted beam re-ranking mechanism by computing entailment probability scores between the input context and summarization model-generated beams during saliency-enhanced greedy decoding. Moreover, a diversity metric is introduced to compare its effectiveness against vanilla beam search. Our proposed algorithm significantly outperforms vanilla beam decoding on XSum and CNN/DM datasets.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 32 of its 38 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

32 of 38 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  5. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  6. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  7. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  8. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  9. 2015Teaching Machines to Read and Comprehendcited by 1,039
  10. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  11. 2020SummEval: Re-evaluating Summarization Evaluationcited by 666
  12. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
20 more
  1. 2019Text Summarization with Pretrained Encoderscited by 553
  2. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
  3. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  4. 2021QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarizationcited by 233
  5. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 137
  6. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
  7. 2021Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarizationcited by 128
  8. 2020If beam search is the answer, what was the question?cited by 114
  9. 2022Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectorscited by 103
  10. 2020Improved Natural Language Generation via Loss Truncationcited by 75
  11. 2022Mutual Information Alleviates Hallucinations in Abstractive Summarizationcited by 67
  12. 2020GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extractioncited by 43
  13. 2022Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inferencecited by 40
  14. 2022Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infillingcited by 38
  15. 2020Understanding Neural Abstractive Summarization Models via Uncertaintycited by 34
  16. 2022Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Searchcited by 23
  17. 2022Improving the Faithfulness of Abstractive Summarization via Entity Coverage Controlcited by 21
  18. 2022Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarizationcited by 20
  19. 2021Attention Head Masking for Inference Time Content Selection in Abstractive Summarizationcited by 9
  20. 2021Incremental Beam Manipulation for Natural Language Generationcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 4; 2025: 2.

10 papers.

  1. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  2. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 130
  3. 2024ALOHa: A New Measure for Hallucination in Captioning Modelscited by 44
  4. 2023Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representationcited by 4
  5. 2023Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decodingcited by 3
  6. 2024On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarizationcited by 2
  7. 2025PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arisecited by 1
  8. 2024Multilingual Fine-Grained News Headline Hallucination Detectioncited by 0
  9. 2024QUILL: Quotation Generation Enhancement of Large Language Modelscited by 0
  10. 2025CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Predictioncited by 0