Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605. 07663v2 Announce Type: replace-cross Abstract: Data valuation methods allocate payments and audit training data's contribution to machine-learning pipelines; however, they often assume passive contributors.
arXiv:2607. 28669v1 Announce Type: new Abstract: We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen model rather than in its weights.
arXiv:2604. 26051v2 Announce Type: replace-cross Abstract: The increasing number of satellites has improved the temporal resolution of Earth observation, making satellite-based flood mapping a promising approach for operational flood monitoring.
arXiv:2510. 24598v2 Announce Type: replace Abstract: Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability.
arXiv:2607. 29093v1 Announce Type: cross Abstract: Metasignal is an open-source Python package for signal detection theory (SDT) and metacognitive measurement.
arXiv:2607. 29053v1 Announce Type: new Abstract: Standard model comparison is global, aggregating losses across the covariate space to declare a single winner.
arXiv:2607. 00064v2 Announce Type: replace Abstract: As technology advances, various algorithms have been proposed for air traffic management, yet their operational adoption in tactical control remains limited.
arXiv:2603. 13683v4 Announce Type: replace-cross Abstract: Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts.
arXiv:2510. 23634v4 Announce Type: replace-cross Abstract: Motivated by applications for set containment problems, we consider the following fundamental problem: can we design set-to-vector functions so that the natural partial order on sets is preserved, namely $S\subseteq T \text{ if and only if } F(S)\leq F(T) $.
arXiv:2607. 29675v1 Announce Type: cross Abstract: Density modes provide a localized and interpretable summary of multimodal distributions, but their estimation under rigorous differential privacy constraints remains largely unexplored.
arXiv:2607. 28641v1 Announce Type: cross Abstract: We introduce the \textit{Agentic Formalism Trap} and the Evaluative Dissonance Index ($D_E$), quantifying how LLM-as-a-Judge systems conflate structural proceduralism with semantic truth under adversarial load.
arXiv:2607. 29240v1 Announce Type: cross Abstract: In vision--language models, commonsense-driven hallucination (CDH) occurs when a model's commonsense prior overrides clear visual evidence of an atypical state.
arXiv:2607. 28946v1 Announce Type: new Abstract: Despite its many benefits, widespread access to individuals' personal data also causes severe privacy concerns for consumers, companies, and policymakers.
arXiv:2607. 29112v1 Announce Type: cross Abstract: Audio-visual speech recognition (AVSR) relies on effective fusion of audio and visual modalities, yet existing approaches treat cross-modal interaction as a single-step operation without structured iterative refinement.
arXiv:2607. 28639v1 Announce Type: cross Abstract: We show that knowledge distillation in small instruction-tuned language models has asymmetric effects on bias.
arXiv:2410. 06665v4 Announce Type: replace-cross Abstract: This paper explores the characterization of equivariant linear layers for representations of permutations and related groups.
arXiv:2607. 28826v1 Announce Type: new Abstract: Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication.
arXiv:2607. 28945v1 Announce Type: new Abstract: Synthetic tabular data is increasingly used in privacy-preserving data sharing, data augmentation, and to mitigate downstream classifier bias.
arXiv:2607. 28649v1 Announce Type: cross Abstract: COSI-Lab presents a multimodal, multi-sensor dataset of an interdisciplinary scientific workshop containing 32 academics at an international conference.
arXiv:2607. 29008v1 Announce Type: cross Abstract: Modern opaque AI models prize performance over interpretability, which makes testing difficult.