Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization
Despite recent advances in abstractive summarization, current summarization systems still suffer from content hallucinations where models generate text that is either irrelevant or contradictory to the source document. However, prior work has been predicated on the assumption that any generated facts not appearing explicitly in the source are undesired hallucinations. Methods have been proposed to address this scenario by ultimately improving `faithfulness' to the source document, but in reality, there is a large portion of entities in the gold reference targets that are not directly in the source. In this work, we show that these entities are not aberrations, but they instead require utilizing external world knowledge to infer reasoning paths from entities in the source. We show that by utilizing an external knowledge base, we can improve the faithfulness of summaries without simply making them more extractive, and additionally, we show that external knowledge bases linked from the source can benefit the factuality of generated summaries.
Code (0)
등록된 구현이 없습니다.
Tasks
Abstractive Text SummarizationWorld KnowledgeSimilar Papers 제목 키워드 기반
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents. It does not check whether retrieved evidence is attributed to the correct entity. A clinical RAG respon…
Detecting and Mitigating Hallucinations in Multilingual Summarisation
Hallucinations pose a significant challenge to the reliability of neural models for abstractive summarisation. While automatically generated summaries may be fluent, they often lack faithfulness to the original document.…
Cross-Lingual TransferSeeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
Recent advancements in multimodal large language models have enhanced document understanding by integrating textual and visual information. However, existing models exhibit incompleteness within their paradigm in real-wo…
document understandingHallucinationOptical Character Recognition (OCR)Mitigating Large Language Model Hallucination with Faithful Finetuning
Large language models (LLMs) have demonstrated remarkable performance on various natural language processing tasks. However, they are prone to generating fluent yet untruthful responses, known as "hallucinations". Halluc…
HallucinationLanguage ModelingLanguage ModellingLarge Language Model+3MedHal-Loc: Are "Explainable-by-Architecture" Medical Hallucination Detectors Faithful Localizers? A Localization Benchmark
Detecting hallucinations in clinical text is increasingly framed as an explainability problem: systems should not merely flag an unreliable response but point to the offending span. Architectures built around knowledge-g…