Related papers: Learning to Revise References for Faithful Summari…
Increasingly larger datasets have become a standard ingredient to advancing the state-of-the-art in NLP. However, data quality might have already become the bottleneck to unlock further gains. Given the diversity and the sizes of modern…
Multi-document summarization entails producing concise synopses of collections of inputs. For some applications, the synopsis should accurately synthesize inputs with respect to a key aspect, e.g., a synopsis of film reviews written about a…
Despite the remarkable performance of generative large language models (LLMs) on abstractive summarization, they face two significant challenges: their considerable size and tendency to hallucinate. Hallucinations are concerning because…
Improvements in large language models have led to increasing optimism that they can serve as reliable evaluators of natural language generation outputs. In this paper, we challenge this optimism by thoroughly re-evaluating five…
The abundance of data produced daily from large variety of sources has boosted the need of novel approaches on causal inference analysis from observational data. Observational data often contain noisy or missing entries. Moreover, causal…
Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line…
Long-form clinical summarization of hospital admissions has real-world significance because of its potential to help both clinicians and patients. The faithfulness of summaries is critical to their safe usage in clinical settings. To better…
Many recent studies endeavor to improve open-source language models through imitation learning, and re-training on the synthetic instruction data from state-of-the-art proprietary models like ChatGPT and GPT-4. However, the innate nature of…
Distantly supervision automatically generates plenty of training samples for relation extraction. However, it also incurs two major problems: noisy labels and imbalanced training data. Previous works focus more on reducing wrongly labeled…
Split and Rephrase is a text simplification task of rewriting a complex sentence into simpler ones. As a relatively new task, it is paramount to ensure the soundness of its evaluation benchmark and metric. We find that the widely used…
Automated code summarization is a long-standing goal for code comprehension. This task automatically generates documentation using a given method. Deep Learning (DL)-based approaches have been proven beneficial for various software…
Dialogue summarization is abstractive in nature, making it suffer from factual errors. The factual correctness of summaries has the highest priority before practical applications. Many efforts have been made to improve faithfulness in text…
One challenge with neural ranking is the need for a large amount of manually-labeled relevance judgments for training. In contrast with prior work, we examine the use of weak supervision sources for training that yield pseudo query-document…
Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in…
Opinion summarization is the task of automatically creating summaries that reflect subjective information expressed in multiple documents, such as product reviews. While the majority of previous work has focused on the extractive setting,…
Distant supervised relation extraction has been successfully applied to large corpus with thousands of relations. However, the inevitable wrong labeling problem by distant supervision will hurt the performance of relation extraction. In…
Summarization refinement faces challenges when extending to multi-dimension. In this paper, we introduce ReFeed, a powerful summarization refinement pipeline that enhances multiple dimensions through reflective reasoning on feedback. To…
Reliability analysis aims at estimating the failure probability of an engineering system. It often requires multiple runs of a limit-state function, which usually relies on computationally intensive simulations. Traditionally, these…
In the field of medical image analysis, deep learning models have demonstrated remarkable success in enhancing diagnostic accuracy and efficiency. However, the reliability of these models is heavily dependent on the quality of training…
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…