mlsanityData to 7 Oct 2026

Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information

arXiv 2404.09480 ↗First posted 15 Apr 2024cs.CL cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

A primary challenge in abstractive summarization is hallucination -- the phenomenon where a model generates plausible text that is absent in the source text. We hypothesize that the domain (or topic) of the source text triggers the model to generate text that is highly probable in the domain, neglecting the details of the source text. To alleviate this model bias, we introduce a decoding strategy based on domain-conditional pointwise mutual information. This strategy adjusts the generation probability of each token by comparing it with the token's marginal probability within the domain of the source text. According to evaluation on the XSUM dataset, our method demonstrates improvement in terms of faithfulness and source relevance. The code is publicly available at urlhttps://github.com/qqplot/dcpmi.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 16 of its 24 references that are in the map. First posted on arXiv 15 Apr 2024.

Builds on

16 of 24 references.

References · 16

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  3. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  4. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  5. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  6. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  7. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  8. 2023How Language Model Hallucinations Can Snowballcited by 310
  9. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 284
  10. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  11. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  12. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 151
4 more
  1. 2022Mutual Information Alleviates Hallucinations in Abstractive Summarizationcited by 67
  2. 2022FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarizationcited by 49
  3. 2020Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generationcited by 26
  4. 2022Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Searchcited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 4.

6 papers.

  1. 2024Model-based Preference Optimization in Abstractive Summarization without Human Feedbackcited by 7
  2. 2025What Makes a Good Natural Language Prompt?cited by 6
  3. 2026TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learningcited by 1
  4. 2026NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoningcited by 0
  5. 2026Decoupling Generation and Selection for Budget-Constrained Faithful Summarizationcited by 0
  6. 2026Does This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agentscited by 0