10 papers · ranked by Valyu relevance
Quanzhi Fu, Qiyu Wu, Dan Williams
With the significant increase in enrollment in computing-related programs over the past 20 years, lecture sizes have grown correspondingly. In large lectures, instructors face challenges on identifying students' knowledge gaps timely, which is critical for effective teaching. Existing classroom response systems rely on…
Yujing Wang, Yuanbang Liang, Yukun Lai, Hainan Zhang + 1 more
Detecting whether a model's internal knowledge is sufficient to correctly answer a given question is a fundamental challenge in deploying responsible LLMs. In addition to verbalising the confidence by LLM self-report, more recent methods explore the model internals, such as the hidden states of the response tokens to…
Luisa Frede, Lisa Bardach, Younes Strittmatter, Eileen Richter + 2 more
Knowledge gaps elicit curiosity and increase people’s willingness to invest resources in seeking information to close them. While previous research used confidence ratings to implicitly infer knowledge gaps, the impact of making these gaps explicitly salient to people on their information-seeking behavior remains…
Yuxin Liu, Chaojie Gu, Yihang Zhang, Qian + 2 more
Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning tasks, yet they often struggle with problems involving missing information, exhibiting issues such as incomplete responses, factual errors, and hallucinations. While forward reasoning approaches like Chain-of-Thought (CoT) [1]…
Siri Lerstøl Olsen, Marte Johanne Tangeraas Hansen, Elin Bø Lunde, Mathias Nikolai Petersen Hella + 1 more
Background Delirium is a common neurocognitive syndrome among older adults, associated with increased morbidity, mortality, and healthcare costs. Emergency departments (EDs) represent a critical point for early detection and prevention, yet delirium often remains under-recognized in this setting. Contributing factors…
Sruti Mallik, Ahana Gangopadhyay
The education sector has benefited enormously through integrating digital technology driven tools and platforms. In recent years, artificial intelligence based methods are being considered as the next generation of technology that can enhance the experience of education for students, teachers, and administrative staff…
Oleg Solozobov
Machine learning systems in fraud detection, credit scoring, and clinical risk assessment operate under delayed ground truth: outcome labels arrive days to months after the decision they evaluate. During this blind period, governance evidence degrades through mechanisms that neither drift detection methods nor…
Mayla R. Boguslav, Nourah M. Salem, Elizabeth K. White, Katherine J. Sullivan + 5 more
Research progresses through the process of making the unknown unknowns into known unknowns, then into knowns. Many knowledge-bases exist to capture the knowns and can be used by graduate students to explore a topic or help researchers contextualize experimental results using concept enrichment methods. The unknowns…
Arun Sharma, Shashi Shekhar
Given trajectories with gaps (i.e., missing data), we investigate algorithms to identify abnormal gaps in trajectories which occur when a given moving object did not report its location, but other moving objects in the same geographic region periodically did. The problem is important due to its societal applications…
Yuanping Shi, Yanheng Ma, Liang Geng, Lina Chu + 4 more
'Wei Li' 'Jiangtao Qi' 'Gang Wang'] Apple-detection performance in orchards degrades markedly under low-light conditions, where intensified noise and non-uniform exposure blur edge cues critical for precise localisation. We propose Knowledge Distillation with Geometry-Consistent Feature Alignment (KDFA), a compact…