Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 03803v1 Announce Type: cross Abstract: Multilingual language models are deployed across a hundred or more languages, yet most benchmarks test whether a model can perform a task _in_ a language rather than whether it commands the language itself, conflating fluency with proficiency.
arXiv:2608. 03887v1 Announce Type: new Abstract: Fine-tuning a large language model on new data degrades what it previously learned.
arXiv:2608. 03324v1 Announce Type: new Abstract: Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy.
arXiv:2604. 23954v2 Announce Type: replace Abstract: Artificial Intelligence (AI) and Machine Learning (ML) models used in clinical settings are increasingly deployed to support clinical decision-making.
arXiv:2608. 03875v1 Announce Type: cross Abstract: Designing effective reward functions remains a major bottleneck in Reinforcement Learning (RL).
arXiv:2608. 00076v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text.
arXiv:2608. 03782v1 Announce Type: new Abstract: Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs).
arXiv:2608. 02616v1 Announce Type: cross Abstract: We present the first independent, systematic evaluation of OpenAI's Privacy Filter (OPF), a 1.
arXiv:2608. 03087v1 Announce Type: cross Abstract: Fine-grained energy consumption data are essential for applications such as demand forecasting, demand response planning, and grid reliability assessment.
arXiv:2511. 21214v4 Announce Type: replace-cross Abstract: Explicit safety policies can improve reasoning-model safety, but their effective coverage may lag behind evolving jailbreak strategies.
arXiv:2608. 02632v1 Announce Type: new Abstract: Circuit tracing is an exciting technique for revealing the internal computation of language models, but it requires a time-intensive manual step of grouping individual features or MLP neurons into supernodes.
arXiv:2606. 20880v2 Announce Type: replace-cross Abstract: Decision-making under partial or adversarial observability requires accurate inference of the environment's latent state and its associated uncertainty.
arXiv:2608. 01755v2 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models for autonomous driving (AD) increasingly utilize chain-of-thought (CoT) supervision to enhance the reasoning capabilities of their Vision-Language Model (VLM) components, yet existing annotation pipelines commonly expose the teacher model to the logged ground-truth (GT) future trajectory.
arXiv:2406. 14429v4 Announce Type: replace-cross Abstract: In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images.
arXiv:2608. 02674v1 Announce Type: cross Abstract: With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward white-box attacks that directly identify and disrupt internal safety neurons or routes.
arXiv:2601. 03321v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have substantially advanced Radiology Report Generation (RRG), yet aligning them through reinforcement learning (RL) remains challenging due to heterogeneous medical supervision.
arXiv:2605. 13801v2 Announce Type: replace-cross Abstract: As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount.
arXiv:2510. 22014v2 Announce Type: replace-cross Abstract: Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input prompts, elicit disallowed content.
arXiv:2608. 03691v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway them toward visually incorrect yet pattern-consistent outputs.
arXiv:2608. 03294v1 Announce Type: new Abstract: We study the problem of learning multi-head softmax attention from black-box input-output access.