Challenge: Existing abstractive summarization systems are hampered by content hallucinations in which models generate text that is not directly inferable from the source alone.
Approach: They propose to use external knowledge to latently connect entities and concepts to latences to lend provenance to many of these unfaithful yet factual entities.
Outcome: The proposed model can be used to improve the factuality of summarizations without simply making them more extractive.

Similar Papers

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization (2022.acl-long)

Copied to clipboard

Challenge: State-of-the-art abstractive summarization systems often generate hallucinations, i.e., content that is not directly inferable from the source document.
Approach: They propose a detection approach that separates factual from non-factual hallucinations of entities by masked language models.
Outcome: The proposed method outperforms baselines in accuracy and F1 scores and has a strong correlation with human judgments on factuality classification tasks.
On Faithfulness and Factuality in Abstractive Summarization (2020.acl-main)

Copied to clipboard

Challenge: Existing conditional text generation models produce unfaithful and unfaithed summaries . current models accomplish a high level of fluency and coherence .
Approach: They propose to use pretrained models for document summarization to better understand hallucinations . they find that textual entailment measures better correlate with faithfulness .
Outcome: The proposed models generate faithful and factual summaries as evaluated by humans.
Entity-level Factual Consistency of Abstractive Text Summarization (2021.eacl-main)

Copied to clipboard

Challenge: Existing models exhibit entity hallucination, generating names of entities that are not present in the source document.
Approach: They propose to use entity-level factual consistency to improve model quality . they propose to filter the training data to reduce entity hallucination problem .
Outcome: The proposed model can reduce the entity hallucination problem by filtering the training data.
Not all Hallucinations are Good to Throw Away When it Comes to Legal Abstractive Summarization (2025.naacl-long)

Copied to clipboard

Challenge: Existing models for summarization of legal documents rely on external knowledge to generate abstracts.
Approach: They propose an entity-driven approach that learns the model to generate factual hallucinations . they evaluate legal documents in English and French to evaluate their results .
Outcome: The proposed approach reduces non-factual hallucinations and maximizes summary coverage and factual hallucines at entity-level.
Reducing Quantity Hallucinations in Abstractive Summarization (2020.findings-emnlp)

Copied to clipboard

Challenge: Abstractive summaries are subject to hallucination, but they are not very informative.
Approach: They propose to use a beam-worth of abstractive summaries to up-rank summary that is not supported by the original text.
Outcome: The proposed system up-ranks summaries whose quantity terms are supported by the original text without losing Recall, and shows higher Precision.
Mitigating Intrinsic Named Entity-Related Hallucinations of Abstractive Text Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Abstractive text summarization (ATS) is important and challenging, but some hallucinations remain a challenge.
Approach: They propose an adaptive margin ranking loss to facilitate two entity-alignment learning methods to tackle named entity-related hallucinations.
Outcome: The proposed method improves the baseline model on automatic evaluation scores.
Improving Faithfulness by Augmenting Negative Summaries from Fake Documents (2022.emnlp-main)

Copied to clipboard

Challenge: Current abstractive summarization systems tend to hallucinate unfaithful content . however, the most common method does not disentangle factual errors from other errors.
Approach: They propose a back-translation-style approach to augment negative samples that mimic factual errors made by the model.
Outcome: The proposed method improves faithfulness without sacrificing informativeness . it incorporates negative samples into training, and produces faithful/unfaithful summaries .
Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control (2022.findings-naacl)

Copied to clipboard

Challenge: Abstractive summarization systems have been shown to be more prone to unfaithful facts . 30% of summaries generated by pre-trained language models suffer from hallucination .
Approach: They propose a method to remedy entity-level extrinsic hallucinations with Entity Coverage Control . they first compute entity coverage precision and prepend the corresponding control code . a further fine-tuning is performed to unlock zero-shot summarization .
Outcome: The proposed method leads to more faithful and salient abstractive summarization in fine-tuning and zero-shot settings.
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information (2024.findings-naacl)

Copied to clipboard

Challenge: Prior studies have attempted to enhance faithfulness of abstractive summarization, yet hallucination remains a persistent challenge.
Approach: They propose a decoding strategy that adjusts the generation probability of each token by comparing it with the token’s marginal probability within the domain of the source text.
Outcome: The proposed method significantly improves faithfulness and source relevance on the XSUM dataset.
Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization (2023.acl-long)

Copied to clipboard

Challenge: Abstractive summarization is less prone to unfaithfulness issues than abstractive summaries . but, unfaitfulness problems, i.e., hallucinating new information, are still a problem in extractive summarisation .
Approach: They propose a typology with five types of broad unfaithfulness problems that can appear in extractive summaries, including and beyond not-entailment.
Outcome: The proposed metric shows that it detects unfaithful summaries faster than existing faithfulness evaluation metrics.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations