Pentagon Inspector General report reveals Defense Department lacks clear policies for counter-drone operations, leaving bases unsure of response authority.

These instances range from active learning over multi-armed bandits to self-training. We show that all these algorithms not only learn parameters from data but also vice versa: They iteratively alter training data in a way that depends on the current model fit. We introduce reciprocal learning as a generalization of these algorithms using the language of decision theory. This allows us to study under what conditions they converge.

Hallucinations are outputs by Large Language Models (LLMs) that are factually incorrect yet appear plausible [1]. This paper investigates how such hallucinations influence users' trust in LLMs and users' interaction with LLMs. To explore this in everyday use, we conducted a qualitative study with 192 participants. Our findings show that hallucinations do not result in blanket mistrust but instead lead to context-sensitive trust calibration. Building on the calibrated trust model by Lee & See [2] and Afroogh et al.'s trust-related factors [3], we confirm expectancy [3], [4], prior experience [3], [4], [5], and user expertise & domain knowledge [3], [4] as userrelated (human) trust factors, and identify intuition as an additional factor relevant for hallucination detection. Additionally, we found that trust dynamics are further influenced by contextual factors, particularly perceived risk [3] and decision stakes [6]. Consequently, we validate the recursive trust calibration process proposed by Blöbaum [7] and extend it by including intuition as a user-related trust factor. Based on these insights, we propose practical recommendations for responsible and reflective LLM use.

As AI-based code generation becomes widespread, researchers are investigating the calibration of code LLMs - ensuring their confidence scores faithfully represent the true likelihood of code correctness. To do so, we investigate multicalibration, which can capture additional factors about a coding problem, such as complexity, code length, or programming language used. We study four multicalibration approaches on three function synthesis benchmarks, using latest-generation code LLMs (Qwen3 Coder, GPT-OSS, DeepSeek-R1-Distill). Our results demonstrate that multicalibration can yield distinct improvements over both uncalibrated token likelihoods (+1.03 in skill score) and baseline calibrations (+0.37 in skill score). We study the influence of the aforementioned factors in ablations, and make our dataset (consisting of code generations, likelihoods, and correctness labels) available for future research on code LLM calibration.

We theoretically demonstrate that the generalization error of interpolators for machine learning models under teacher-student settings becomes 0 once the number of training samples exceeds a certain threshold. Understanding the high generalization ability of large-scale models such as deep neural networks (DNNs) remains one of the central open problems in machine learning theory. While recent theoretical studies have attributed this phenomenon to the implicit bias of stochastic gradient descent (SGD) toward well-generalizing solutions, empirical evidences indicate that it primarily stems from properties of the model itself. Specifically, even randomly sampled interpolators, which are parameters that achieve zero training error, have been observed to generalize effectively. In this study, under a teacher-student framework, we prove that the generalization error of randomly sampled interpolators becomes exactly zero once the number of training samples exceeds a threshold determined by the geometric structure of the interpolator set in parameter space. As a proof technique, we leverage tools from algebraic geometry to mathematically characterize this geometric structure.

The reliable operation of autonomous vehicles, automated driving functions, and advanced driver assistance systems across a wide range of relevant scenarios is critical for their development and deployment. Identifying a near-complete set of relevant driving scenarios for such functionalities is challenging due to numerous degrees of freedom involved, each affecting the outcomes of the driving scenario differently. Moreover, with increasing technical complexity of new functionalities, the number of potentially relevant, particularly "unknown unsafe" scenarios is increasing. To enhance validation efficiency, it is essential to identify relevant scenarios in advance, starting with simpler domains like highways before moving to more complex environments such as urban traffic. To address this, this paper focuses on analyzing lane change scenarios in highway traffic, which involve multiple degrees of freedom and present numerous safetyrelevant scenarios. We describe the process of data acquisition and processing of real-world data from public highway traffic, followed by the application of criticality measures on trajectory data to evaluate scenarios, as conducted within the AVEAS project (www.aveas.org). By linking the calculated measures to specific lane change driving scenarios and the conditions under which the data was collected, we facilitate the identification of safetyrelevant driving scenarios for various applications. Further, to tackle the extensive range of "unknown unsafe" scenarios, we propose a way to generate relevant scenarios by creating synthetic scenarios based on recorded ones. Consequently, we demonstrate and evaluate a processing chain that enables the identification of safety-relevant scenarios, the development of data-driven methods for extracting these scenarios, and the generation of synthetic critical scenarios via sampling on highways.

We introduce TurBLiMP, the first Turkish benchmark of linguistic minimal pairs, designed to evaluate the linguistic abilities of monolingual and multilingual language models (LMs). Covering 16 linguistic phenomena with 1000 minimal pairs each, TurBLiMP fills an important gap in linguistic evaluation resources for Turkish. In designing the benchmark, we give extra attention to two properties of Turkish that remain understudied in current syntactic evaluations of LMs, namely word order flexibility and subordination through morphological processes. Our experiments on a wide range of LMs and a newly collected set of human acceptability judgments reveal that even cutting-edge Large LMs still struggle with grammatical phenomena that are not challenging for humans, and may also exhibit different sensitivities to word order and morphological complexity compared to humans.

Synthetic data generation is an important tool for privacy-preserving data sharing. While diffusion models have set recent benchmarks, flow matching (FM) offers a promising alternative. This paper presents different ways to implement flow matching for tabular data synthesis. We provide a comprehensive empirical study that compares flow matching (FM and variational FM) with a state-of-the-art diffusion method (TabDDPM and TabSyn) in tabular data synthesis. We evaluate both the standard Optimal Transport (OT) and the Variance Preserving (VP) probability paths, and also compare deterministic and stochastic samplers -- something possible when learning to generate using \textit{variational} flow matching -- characterising the empirical relationship between data utility and privacy risk. Our key findings reveal that flow matching, particularly TabbyFlow, outperforms diffusion baselines. Flow matching methods also achieves better performance with remarkably low function evaluations ($\leq$ 100 steps), offering a substantial computational advantage. The choice of probability path is also crucial, as using the OT path demonstrates superior performance, while VP has potential for producing synthetic data with lower disclosure risk. Lastly, our results show that making flows stochastic not only preserves marginal distributions but, in some instances, enables the generation of high utility synthetic data with reduced disclosure risk.