Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605. 10807v4 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) and hardware security is rapidly reshaping the semiconductor industry.
arXiv:2606. 05781v1 Announce Type: new Abstract: Deploying frontier large language models (LLMs) for domain-specific structured evaluation tasks often incurs substantial latency, cost, and data privacy overhead.
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
arXiv:2606. 05497v1 Announce Type: new Abstract: Given the inherently multimodal nature of human experience, vision-language models (VLMs) hold substantial promise for modeling human cognition as it grows and develops with experience.
arXiv:2606. 06288v1 Announce Type: cross Abstract: Causal representation learning aims to infer the high-level latent causal concepts that give rise to observed low-level measurements.
arXiv:2606. 06224v1 Announce Type: cross Abstract: Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology.
arXiv:2606. 06011v1 Announce Type: cross Abstract: In this work, we propose a framework that combines multi-agent reinforcement learning (MARL) with model-based control to achieve safe, dynamically feasible actions in cooperative multi-agent tasks.
arXiv:2606. 05885v1 Announce Type: new Abstract: Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards.
arXiv:2602. 05056v2 Announce Type: replace-cross Abstract: Online scams increasingly leverage fluent and context-aware social engineering strategies, creating growing demand for AI systems that explain why a message may be risky.
arXiv:2606. 05737v1 Announce Type: cross Abstract: Diffusion-based vision-language-action (VLA) models often inherit the image-generation view: actions are generated by iterative denoising.
arXiv:2606. 06335v1 Announce Type: new Abstract: Performance estimation under distribution shift aims to predict how a model behaves on an unlabeled test set whose distribution differs from the training data, a scenario that requires reliable indicators that can faithfully reflect model behavior without ground-truth labels.
arXiv:2603. 03955v2 Announce Type: replace Abstract: Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation.
arXiv:2606. 06133v1 Announce Type: cross Abstract: TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols.
arXiv:2606. 05308v1 Announce Type: new Abstract: With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set.
arXiv:2605. 27292v2 Announce Type: replace Abstract: Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters.
arXiv:2512. 15783v3 Announce Type: replace-cross Abstract: This paper proposes a measurement standardisation framework that compresses expert-AI interactions into structured, comparable fields for prospective risk detection in deployed AI systems, without access to model internals.
arXiv:2602. 12124v2 Announce Type: replace Abstract: While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerable environments.
arXiv:2604. 07709v4 Announce Type: replace-cross Abstract: A heavily safety-trained model will hand a physician the full, patient-followable benzodiazepine taper and refuse it to the patient who needs it, over identical clinical facts; the knowledge is present either way.
arXiv:2606. 05400v1 Announce Type: cross Abstract: Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work.
arXiv:2606. 06077v1 Announce Type: cross Abstract: Autonomous underwater vehicle (AUV) launch and recovery (LAR) into the hull of an advancing host platform requires traversal of a complex, three-dimensional propeller wake whose hydrodynamic structure cannot be characterised by a uniform current model.