Knowledge syntheses (literature reviews) are essential to health professions education (HPE), consolidating findings to advance theory and practice. However, they are labor-intensive, especially during data extraction. Artificial Intelligence (AI)-assisted extraction promises efficiency but raises concerns about accuracy, making it critical to distinguish AI 'hallucinations' (fabricated content) from legitimate interpretive differences. We developed an extraction platform using large language models (LLMs) to automate data extraction and compared AI to human responses across 187 publications and 17 extraction questions from a published scoping review. AI-human, human-human, and AI-AI consistencies were measured using interrater reliability (categorical) and thematic similarity ratings (open-ended). Errors were identified by comparing extracted responses to source publications. AI was highly consistent with humans for concrete, explicitly stated questions (e.g., title, aims) and lower for questions requiring subjective interpretation or absent in text (e.g., Kirkpatrick's outcomes, study rationale). Human-human consistency was not higher than AI-human and showed the same question-dependent variability. Discordant AI-human responses (769/3179 = 24.2%) were mostly due to interpretive differences (18.3%); AI inaccuracies were rare (1.51%), while humans were nearly three times more likely to state inaccuracies (4.37%). Findings suggest AI variability depends more on interpretability than hallucination. Repeating AI extraction can identify interpretive complexity or ambiguity, refining processes before human review. AI can be a transparent, trustworthy partner in knowledge synthesis, though caution is needed to preserve critical human insights.

Large language models (LLMs) have revolutionized natural language processing, yet their tendency to hallucinate poses serious challenges for reliable deployment. Despite numerous hallucination detection methods, their evaluations often rely on ROUGE, a metric based on lexical overlap that misaligns with human judgments. Through comprehensive human studies, we demonstrate that while ROUGE exhibits high recall, its extremely low precision leads to misleading performance estimates. In fact, several established detection methods show performance drops of up to 45.9\% when assessed using human-aligned metrics like LLM-as-Judge. Moreover, our analysis reveals that simple heuristics based on response length can rival complex detection techniques, exposing a fundamental flaw in current evaluation practices. We argue that adopting semantically aware and robust evaluation frameworks is essential to accurately gauge the true performance of hallucination detection methods, ultimately ensuring the trustworthiness of LLM outputs.

In settings where human decision-making relies on AI input, both the predictive accuracy of the AI system and the reliability of its confidence estimates influence decision quality. We highlight the role of AI metacognitive sensitivity -- its ability to assign confidence scores that accurately distinguish correct from incorrect predictions -- and introduce a theoretical framework for assessing the joint impact of AI's predictive accuracy and metacognitive sensitivity in hybrid decision-making settings. Our analysis identifies conditions under which an AI with lower predictive accuracy but higher metacognitive sensitivity can enhance the overall accuracy of human decision making. Finally, a behavioral experiment confirms that greater AI metacognitive sensitivity improves human decision performance. Together, these findings underscore the importance of evaluating AI assistance not only by accuracy but also by metacognitive sensitivity, and of optimizing both to achieve superior decision outcomes.

Most work on estimating mixture models assumes an iid sampling scheme.

Machine learning models trained on private datasets have been shown to leak their private data. While recent work has found that the average data point is rarely leaked, the outlier samples are frequently subject to memorization and, consequently, privacy leakage.

It suggests that, for any m { k,...,n 1 } and z R, L A.2 Proofs for Lemma 2 and 3 for the case when K is unknown in 4 Lemma 2 . It suggests that, for any m { 0,...,n 1 } and z R, L For any m { 0,...,n 1 } and z R, we have L A.3 Additional tricks for methods proposed in 3. Finding optimal CP vector when z = in paraCP(n,k, ˆ T Additional pruning condition for parametric DP when K is fixed. In 3.3, we showed that Lemma 4. F orn [ N ], and k [ K ], let T Therefore, it fails to control the false positive rate. This is asymptotic test for multiple detected CPs. Fused Lasso (proposed by the same authors), is worse than BinSeg-SI. BinSeg-SI had been considered as a computationally efficient approximation of the problem in (7), where the authors additionally condition on extra information for computational tractability, e.g., the order that CPs are detected.