Correction with Backtracking Reduces Hallucination in Summarization
Abstractive summarization aims at generating natural language summaries of a source document that are succinct while preserving the important elements. Despite recent advances, neural text summarization models are known to be susceptible to hallucinating (or more correctly confabulating), that is to produce summaries with details that are not grounded in the source document. In this paper, we introduce a simple yet efficient technique, CoBa, to reduce hallucination in abstractive summarization. The approach is based on two steps: hallucination detection and mitigation. We show that the former can be achieved through measuring simple statistics about conditional word probabilities and distance to context words. Further, we demonstrate that straight-forward backtracking is surprisingly effective at mitigation. We thoroughly evaluate the proposed method with prior art on three benchmark datasets for text summarization. The results show that CoBa is effective and efficient in reducing hallucination, and offers great adaptability and flexibility. Code can be found at https://github.com/zhenzhel/CoBa.
Code (1)
Tasks
Abstractive Text SummarizationHallucinationText SummarizationSimilar Papers 제목 키워드 기반
Hallucination Detection-Guided Preference Optimization for Clinical Summarization
Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applicat…
Tackling Hallucinations in Neural Chart Summarization
Hallucinations in text generation occur when the system produces text that is not grounded in the input. In this work, we tackle the problem of hallucinations in neural chart summarization. Our analysis shows that the ta…
Data-to-Text GenerationTable-to-Text GenerationText GenerationGradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation
In tasks like summarization and open-book question answering (QA), Large Language Models (LLMs) often encounter "contextual hallucination", where they produce irrelevant or incorrect responses despite having access to ac…
Computational EfficiencyHallucinationQuestion AnsweringImproving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection
Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the original context. To address the issue, we …
Abstractive Text SummarizationHallucinationDensity- and elongation speed-dependent error correction in RNA polymerization
Backtracking of RNA polymerase (RNAP) is an important pausing mechanism during DNA transcription that is part of the error correction process that enhances transcription fidelity. We model the backtracking mechanism of R…