LLM-based drug–drug interaction (DDI) assessment remains difficult to audit when predictions are not explicitly tied to evidence. While retrieval-augmented generation (RAG) improves grounding, predictions are not guaranteed to be entailed by retrieved items. We present CrossDDI, a verification-first framework that separates LLM-based evidence extraction from deterministic, LLM-free arbitration over DrugBank and PubMed, requiring positive predictions to be linked to explicit supporting evidence. Evaluated on 1,000 DDInter 2.0 pairs under a positive–unlabeled setting, CrossDDI achieves recall of 0.576–0.593 over confirmed positives with interaction prediction rates comparable to RAG, while reducing cross-backbone variation (0.018 vs. 0.066). Analysis identifies literature evidence acquisition and attribution as the primary bottleneck: PubMed retrieval covers only 40.5% of confirmed positives, and Path B-only evidence is substantially less reliable than structured evidence. These results suggest that verification-first architectures can improve traceability and backbone consistency, while broader and more reliable literature evidence is needed to extend coverage beyond structured sources.

Retrieval-augmented generation (RAG) reduces hallucination in large language models by grounding outputs in retrieved evidence, but it does not guarantee that the resulting citations support the associated claims. We present VERICITE, a framework for evaluating citation faithfulness in retrieval-augmented medical QA. Our system retrieves PubMed abstracts via the NCBI E-Utilities API, prompts LLMs to generate answers with inline citations, and verifies each citation at the sentence level using a DeBERTa-v3-large NLI model. We evaluate four LLMs on 500 BioASQ questions at retrieval depths of 3 and 5, with extended experiments up to k = 15 and an oracle setting with gold standard documents. Only 27?41% of citation pairs are supported at the sentence level at retrieval depths of 3 and 5, with support rates declining further at larger k. Under the oracle condition, answer quality improves, but citation faithfulness does not substantially improve, suggesting that generation-side citation behavior contributes substantially to unfaithful citations.

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.