Hallucination Reduction in Long Input Text Summarization

• URL: http://arxiv.org/abs/2309.16781v1
• Date: Thu, 28 Sep 2023 18:22:16 GMT
• Title: Hallucination Reduction in Long Input Text Summarization
• Authors: Tohida Rehman, Ronit Mandal, Abhishek Agarwal, Debarshi Kumar Sanyal
• Abstract summary: Hallucination in text summarization poses significant obstacles to the accuracy and reliability of the generated summaries. We have incorporated the techniques of data filtering and joint entity and summary generation (JAENS) in the fine-tuning of the Longformer-Decoder (LED) model. Our experiments show that the fine-tuned LED model performs well in generating the paper abstract.
• Score: 2.6745438139282283
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Hallucination in text summarization refers to the phenomenon where the model generates information that is not supported by the input source document. Hallucination poses significant obstacles to the accuracy and reliability of the generated summaries. In this paper, we aim to reduce hallucinated outputs or hallucinations in summaries of long-form text documents. We have used the PubMed dataset, which contains long scientific research documents and their abstracts. We have incorporated the techniques of data filtering and joint entity and summary generation (JAENS) in the fine-tuning of the Longformer Encoder-Decoder (LED) model to minimize hallucinations and thereby improve the quality of the generated summary. We have used the following metrics to measure factual consistency at the entity level: precision-source, and F1-target. Our experiments show that the fine-tuned LED model performs well in generating the paper abstract. Data filtering techniques based on some preprocessing steps reduce entity-level hallucinations in the generated summaries in terms of some of the factual consistency metrics.

Related papers

• ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models [65.12177400764506]
  Large language models (LLMs) exhibit hallucinations in long-form question-answering tasks across various domains and wide applications. Current hallucination detection and mitigation datasets are limited in domains and sizes. This paper introduces an iterative self-training framework that simultaneously and progressively scales up the hallucination annotation dataset.
  arXiv  Detail & Related papers  (2024-07-05T17:56:38Z)
• German also Hallucinates! Inconsistency Detection in News Summaries with the Absinth Dataset [3.5206745486062636]
  This work presents absinth, a manually annotated dataset for hallucination detection in German news summarization. We open-source and release the absinth dataset to foster further research on hallucination detection in German.
  arXiv  Detail & Related papers  (2024-03-06T14:37:30Z)
• Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization [37.55557353462219]
  Pruning is a technique that reduces model size by removing redundant weights, enabling more efficient sparse inference. This paper provides an empirical study across five summarization datasets, two state-of-the-art pruning methods, and five instruction-tuned LLMs. Surprisingly, we find that hallucinations are less prevalent from pruned LLMs than the original models.
  arXiv  Detail & Related papers  (2023-11-15T19:49:24Z)
• AutoHall: Automated Hallucination Dataset Generation for Large Language Models [56.92068213969036]
  This paper introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall. We also propose a zero-resource and black-box hallucination detection method based on self-contradiction.
  arXiv  Detail & Related papers  (2023-09-30T05:20:02Z)
• Do Multi-Document Summarization Models Synthesize? [24.170828395176727]
  We run experiments over opinion and evidence synthesis datasets using a suite of summarization models. We find that existing models partially perform synthesis, but imperfectly. We propose a simple, general, effective method for improving model synthesis capabilities.
  arXiv  Detail & Related papers  (2023-01-31T18:40:46Z)
• Mutual Information Alleviates Hallucinations in Abstractive Summarization [73.48162198041884]
  We find a simple criterion under which models are significantly more likely to assign more probability to hallucinated content during generation: high model uncertainty. This finding offers a potential explanation for hallucinations: models default to favoring text with high marginal probability, when uncertain about a continuation. We propose a decoding strategy that switches to optimizing for pointwise mutual information of the source and target token--rather than purely the probability of the target token--when the model exhibits uncertainty.
  arXiv  Detail & Related papers  (2022-10-24T13:30:54Z)
• Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search [54.286450484332505]
  We analyze the connection between hallucinations and training data, and find evidence that models hallucinate because they train on target summaries that are unsupported by the source. We present PINOCCHIO, a new decoding method that improves the consistency of a transformer-based abstractive summarizer by constraining beam search to avoid hallucinations.
  arXiv  Detail & Related papers  (2022-03-16T07:13:52Z)
• Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection [54.38512834521367]
  We study contrast candidate generation and selection as a model-agnostic post-processing technique. We learn a discriminative correction model by generating alternative candidate summaries. This model is then used to select the best candidate as the final output summary.
  arXiv  Detail & Related papers  (2021-04-19T05:39:24Z)
• Entity-level Factual Consistency of Abstractive Text Summarization [26.19686599842915]
  Key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document. We propose a set of new metrics to quantify the entity-level factual consistency of generated summaries.
  arXiv  Detail & Related papers  (2021-02-18T03:07:28Z)
• Detecting Hallucinated Content in Conditional Neural Sequence Generation [165.68948078624499]
  We propose a task to predict whether each token in the output sequence is hallucinated (not contained in the input) We also introduce a method for learning to detect hallucinations using pretrained language models fine tuned on synthetic data.
  arXiv  Detail & Related papers  (2020-11-05T00:18:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.