Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.19735v1 Announce Type: new Abstract: Scenario-based validation is essential for automated road vehicles but cannot cover the full variability of openworld traffic. We present MakSafe, a fo...
arXiv:2610.19762v1 Announce Type: new Abstract: Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem fro...
arXiv:2610.19817v1 Announce Type: new Abstract: Human values shape how we expect language models to behave. Dominant alignment approaches treat values as global objectives, although the appropriate v...
arXiv:2610.19848v1 Announce Type: new Abstract: We present OpenTWBench, an open evaluation suite for Taiwan-domain knowledge in large language models, built around two benchmarks. tw-exam-bench conta...
arXiv:2610.20051v1 Announce Type: new Abstract: In recent years, with advances in multimodal interaction technologies and the growing demand for intelligent emotional support, Multimodal Emotional Su...
arXiv:2610.20139v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have emerged as a promising approach to mechanistic interpretability by decomposing language-model activations into sparse,...
arXiv:2610.20417v1 Announce Type: new Abstract: Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures a...
arXiv:2610.20570v1 Announce Type: new Abstract: Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or valid...
arXiv:2610.19267v1 Announce Type: cross Abstract: Online memes are often carriers of unsafe content such as disinformation and propaganda. Their rapid evolution in response to news events and strong...
arXiv:2610.19728v1 Announce Type: cross Abstract: Video large language models (Video LLMs) often generate responses unsupported by the input video. Contrastive decoding (CD) can mitigate these halluc...
arXiv:2507.12553v4 Announce Type: replace Abstract: Language models (LMs) are used for a diverse range of tasks, from question answering to writing fantastical stories. In order to reliably accomplis...
arXiv:2603.01502v2 Announce Type: replace Abstract: End-to-end speech large language models (LLMs) often answer the same question less accurately from speech than from text, even when the spoken cont...
arXiv:2608.03154v2 Announce Type: replace Abstract: Biomedical relation extraction (BioRE) supports knowledge graph construction and hypothesis generation. In real-world settings, most candidate enti...
arXiv:2608.13304v2 Announce Type: replace Abstract: A common way to improve jailbreak robustness is to train on harmful requests rewritten as role-play, translation, or other forms. When used only fo...
arXiv:2610.19052v1 Announce Type: new Abstract: Video-based remote physiological measurement (RPM) has broad applications, while Vision-Language Models (VLMs) provide a promising opportunity to enabl...
arXiv:2610.19559v1 Announce Type: new Abstract: Lipreading remains challenging due to the inherent ambiguity of visual speech cues and their sensitivity to head pose and video resolution. In this wor...
arXiv:2610.19717v1 Announce Type: new Abstract: Recent advances in diffusion models have enabled high-fidelity, identity-preserving image generation for personalized applications such as digital avat...
arXiv:2610.20055v1 Announce Type: new Abstract: The rapid advancement of large vision language models (LVLMs) has made geolocation inference from images highly accurate and accessible. This poses ser...
arXiv:2610.20141v1 Announce Type: new Abstract: In various industries, smoke and fire are two of the most important threats in the workplace. One of the common methods for detecting smoke and fire is...
arXiv:2610.20160v1 Announce Type: new Abstract: Learning world models across diverse domains calls for a unified control space, yet ac- tion interfaces vary across domains and action annotations are...