Related papers: Concurrent Criterion Validation of a Validity Scre…
Large Vision-Language Models (LVLMs) excel at captioning, visual question answering, and robotics by combining vision and language, yet they often miss obvious objects or hallucinate nonexistent ones in atypical scenes. We examine these…
Reliable uncertainty quantification is critical in high-stakes applications, such as medical diagnosis, where confidently incorrect predictions can erode trust in automated decision-making systems. Traditional uncertainty quantification…
Large language models are increasingly used as automated evaluators in research and enterprise settings, a practice known as LLM-as-a-judge. While prior work has examined accuracy, bias, and alignment with human preferences, far less…
Vision Language models (VLMs) often hallucinate non-existent objects. Detecting hallucination is analogous to detecting deception: a single final statement is insufficient, one must examine the underlying reasoning process. Yet existing…
Reinforcement Learning with Verifiable Rewards (RLVR) has become a prominent method for post-training Large Language Models (LLMs). However, verifiers are rarely error-free; even deterministic checks can be inaccurate, and the growing…
Error detection (ED), which aims to identify incorrect or inconsistent cell values in tabular data, is important for ensuring data quality. Recent state-of-the-art ED methods leverage the pre-trained knowledge and semantic capability…
Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing…
This technical report presents research results achieved in the field of verification of trained Convolutional Neural Network (CNN) used for image classification in safety-critical applications. As running example, we use the obstacle…
The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirical contradiction: some studies find models stubbornly retain their trained answers,…
Link prediction is a paradigmatic and challenging problem in network science, which aims to predict missing links, future links and temporal links based on known topology. Along with the increasing number of link prediction algorithms, a…
Containerization has emerged as a revolutionary technology in the software development and deployment industry. Containers offer a portable and lightweight solution that allows for packaging applications and their dependencies…
Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its own outputs, which can…
We present a method that "meta" classifies whether seg-ments predicted by a semantic segmentation neural networkintersect with the ground truth. For this purpose, we employ measures of dispersion for predicted pixel-wise class probability…
We introduce and analyze a discrete soft-decision channel called the linear reliability channel (LRC) in which the soft information is the rank ordering of the received symbol reliabilities. We prove that the LRC is an appropriate…
Large language models (LLMs) are often confidently wrong, making reliable uncertainty estimation (UE) essential. Output-based heuristics are cheap but brittle, while probing internal representations is effective yet high-dimensional and…
Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident…
LLM-judged benchmarks are increasingly used to evaluate complex model behaviors, yet their design introduces failure modes absent in conventional ground-truth based benchmarks. We argue that without tight objectives and verifiable…
Validation accuracy is a necessary, but not sufficient, measure of a neural network classifier's quality. High validation accuracy during development does not guarantee that a model is free of serious flaws, such as vulnerability to…
In the pharmaceutical industry the screening of opaque vaccines containing suspensions is currently a manual task carried out by trained human visual inspectors. We show that deep learning can be used to effectively automate this process. A…
LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence. These signals are sometimes treated as direct readouts of model uncertainty, but their comparison depends on…