相关论文: Enhancing Factuality through Consensus and Consist…
Improving factual consistency of abstractive summarization has been a widely studied topic. However, most of the prior works on training factuality-aware models have ignored the negative effect it has on summary quality. We propose EFACTSUM…
An important problem of the sequence-to-sequence neural models widely used in abstractive summarization is exposure bias. To alleviate this problem, re-ranking systems have been applied in recent years. Despite some performance…
Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting…
Despite substantial progress in abstractive text summarization to generate fluent and informative texts, the factual inconsistency in the generated summaries remains an important yet challenging problem to be solved. In this paper, we…
Despite the recent advances in abstractive summarization systems, it is still difficult to determine whether a generated summary is factual consistent with the source text. To this end, the latest approach is to train a factual consistency…
Multi-document summarization has received a great deal of attention in the past couple of decades. Several approaches have been proposed, many of which perform equally well and it is becoming in- creasingly difficult to choose one…
Minimum Bayes Risk (MBR) decoding is a text generation technique that has been shown to improve the quality of machine translations, but is expensive, even if a sampling-based approximation is used. Besides requiring a large number of…
Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and…
Automatic radiology report summarization is a crucial clinical task, whose key challenge is to maintain factual accuracy between produced summaries and ground truth radiology findings. Existing research adopts reinforcement learning to…
Despite significant progress has been achieved in text summarization, factual inconsistency in generated summaries still severely limits its practical applications. Among the key factors to ensure factual consistency, a reliable automatic…
Although some recent works show potential complementarity among different state-of-the-art systems, few works try to investigate this problem in text summarization. Researchers in other areas commonly refer to the techniques of reranking or…
Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation. MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others. Therefore,…
Current pre-trained models applied to summarization are prone to factual inconsistencies which either misrepresent the source text or introduce extraneous information. Thus, comparing the factual consistency of summaries is necessary as we…
Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability. However, high estimated probability does not always lead to high translation quality. Minimum…
Lack of factual correctness is an issue that still plagues state-of-the-art summarization systems despite their impressive progress on generating seemingly fluent summaries. In this paper, we show that factual inconsistency can be caused by…
Relevance in summarization is typically defined based on textual information alone, without incorporating insights about a particular decision. As a result, to support risk analysis of pancreatic cancer, summaries of medical notes may…
Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon is emphasized in tasks like summarization, in which the…
Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accuracy over beam search in conditional language generation…
Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this…
Minimum Bayes Risk (MBR) decoding is a powerful decoding strategy widely used for text generation tasks, but its quadratic computational complexity limits its practical application. This paper presents a novel approach for approximating MBR…