Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.27620v1 Announce Type: cross Abstract: Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authori...
arXiv:2610.27702v1 Announce Type: cross Abstract: Large language models are expected to estimate their own uncertainty, with confidence signals used to guide retrieval, adaptive compute allocation, r...
arXiv:2610.27726v1 Announce Type: cross Abstract: Learned barrier certificates provide a principled mechanism for establishing safety of stochastic systems, but their validity may deteriorate during...
arXiv:2610.27942v1 Announce Type: cross Abstract: Automated respiratory sound classification enables continuous, non-invasive respiratory assessment, yet long-term deployment remains challenging due...
arXiv:2610.28184v1 Announce Type: cross Abstract: Reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards yet fail to translate that evid...
arXiv:2610.28197v1 Announce Type: cross Abstract: Object-centric reinforcement learning agents typically receive each object's position in a fixed global frame, even though their decisions usually de...
The paper introduces Gated Knowledge‑Guided Prototype Transfer (GProtoT), a training‑free module that enhances zero‑support medical vision‑language models by transferring visual residuals from supported classes to missing ones using VLM similarity and clinical ontology distances. GProtoT employs an evidence gate to scale transfer based on semantic relevance, reducing negative transfer while modestly improving recall and accuracy in realistic one‑shot trials on MESSIDOR. The method requires no gradients, validation data, or extra inference, offering a low‑compute, accountable adaptation path for incomplete clinical supervision.
BitMTP is an algorithm‑system co‑design framework that combines multi‑token prediction (MTP) with ultra‑low‑bit large language model backbones to accelerate decoding while maintaining quality. It introduces joint next‑token and MTP objectives, multiple decoding modes (confidence‑only, speculative‑only, hybrid), and an accepted‑prefix alignment mechanism that keeps causal key‑value boundaries and CUDA Graph replay states consistent. Experiments on NVIDIA H20, RTX 3090, and Jetson Orin show speedups ranging from 2.0× to 3.3× across various ultra‑low‑bit models without sacrificing task performance.
arXiv:2602.02589v2 Announce Type: replace Abstract: Large language model (LLM) evaluation commonly relies on fixed human-authored benchmarks or centralized human/model judges. Fixed benchmarks can ag...
arXiv:2605.30803v2 Announce Type: replace Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rub...
arXiv:2410.03246v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unr...
The paper surveys multimodal generative models (MGMs), outlining six main text‑conditioned modalities and four key techniques—self‑supervised learning, mixture of experts, reinforcement learning from human feedback, and chain‑of‑thought prompting—used across them. It evaluates models on faithfulness, compositionality, and robustness, and reports four empirical findings about preference gains, reward optimisation, intermediate planning, and expert granularity. The study also discusses trustworthiness risks such as bias, privacy leakage, and media misuse, and reviews mitigation evidence.
arXiv:2510.03223v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, cri...
arXiv:2601.11663v2 Announce Type: replace-cross Abstract: Post-training quantization (PTQ) methods for large language models compress pretrained weights to low bit-widths without retraining by optimi...
arXiv:2603.11413v5 Announce Type: replace-cross Abstract: A recent Nature Medicine study reported that ChatGPT Health under-triages 51.6% of emergencies and concluded that consumer-facing AI triage p...
arXiv:2603.18280v4 Announce Type: replace-cross Abstract: Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the...
arXiv:2610.03759v3 Announce Type: replace-cross Abstract: Ocean wave forecasting is essential for maritime safety, offshore operations, and coastal resilience, yet remains challenging due to systemat...
arXiv:2610.25916v2 Announce Type: replace-cross Abstract: As coding models and agent harnesses become more capable, reliable security verification is becoming a central bottleneck. Improving secure c...
arXiv:2610.26443v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) on downstream tasks often weakens their previously aligned safety behavior, creating an inherent tra...
arXiv:2610.27882v1 Announce Type: new Abstract: Multispectral object detection requires detectors to exploit material-dependent spectral responses while maintaining consistent localization under geom...