While document summarization with LLMs has enhanced access to textual information, concerns about the factual accuracy of these summaries persist (e.g., hallucination), especially in the medical domain. Tracing source evidence from which summaries are derived enables users to assess their accuracy, thereby alleviating this concern. In this paper, we introduce TracSum, a novel benchmark for traceable, aspect-based summarization, in which generated summaries are paired with sentence-level citations, enabling users to trace back to the original context. First, we annotate 500 medical abstracts for seven key medical aspects, yielding 3.5K summary-citations pairs. We then propose a fine-grained evaluation framework for this new task, designed to assess the completeness and consistency of generated content using four metrics. Finally, we introduce a summarization pipeline, Track-Then-Sum, which serves as a baseline method for comparison. In experiments, we evaluate both this baseline and a set of LLMs on TracSum, and conduct a human evaluation to assess the evaluation results. The findings demonstrate that TracSum can serve as an effective benchmark for traceable, aspect-based summarization tasks. We also observe that explicitly performing sentence-level tracking prior to summarization enhances generation accuracy, while incorporating the full context further improves summary completeness. Source code and dataset are available at https://github.com/chubohao/TracSum.

Prior manual studies of rumours suggested that crowd stance can give insights into the actual rumour veracity. Even though numerous studies of automatic veracity classification of social media rumours have been carried out, none explored the effectiveness of leveraging crowd stance to determine veracity. We use stance as an additional feature to those commonly used in earlier studies. We also model the veracity of a rumour using variants of Hidden Markov Models (HMM) and the collective stance information. This paper demonstrates that HMMs that use stance and tweets’ times as the only features for modelling true and false rumours achieve F1 scores in the range of 80%, outperforming those approaches where stance is used jointly with content and user based features.