Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.13393v1 Announce Type: cross Abstract: Deep joint source-channel coding (DeepJSCC) transmits learned semantic features efficiently but can leak sensitive attributes such as gender, race, o...
arXiv:2609.14290v1 Announce Type: cross Abstract: Machine learning models are increasingly deployed in healthcare imaging pipelines for diagnostic support, and training-time attacks against them are...
The paper introduces "capability laundering," a method where a weaker, unaligned language model splits a harmful task into benign subproblems, consults a stronger aligned model on each, and locally combines the answers. Experiments with GPT‑5.5, Claude Opus 4.8, and Grok‑4.3 as consultants to various local orchestrators show significant uplift on CyBench, BountyBench, and a bioweapon attack chain, with Gemma‑4‑31B recovering many more candidates than the aligned models alone. The results reveal that refusing a harmful task does not stop frontier capabilities from being transferred and composed across multiple permitted interactions.
arXiv:2609.15277v1 Announce Type: cross Abstract: Entrepreneurial cognition is a foundation of entrepreneurship research. Yet the growing involvement of large language models (LLMs) in entrepreneuria...
arXiv:2505.17763v2 Announce Type: replace Abstract: The widespread use of sensors in modern power grids has led to the accumulation of large amounts of voltage and current waveform data, especially d...
arXiv:2609.10947v2 Announce Type: replace-cross Abstract: Multimodal large language models predict brain activity, but brain alignment has been a measurement, not a design tool. We propose the Platon...
arXiv:2609.13615v1 Announce Type: new Abstract: For our submission to the WMT26 Creole Language Translation Shared Task, we focus on machine translation (MT) models for Pacific creoles: Tok Pisin, Bi...
arXiv:2609.13737v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed, the generation of harmful content has become a critical safety concern. Existing safeguards...
arXiv:2609.14648v1 Announce Type: new Abstract: Aligning multi-turn dialogue agents is usually framed as matching turn-level human preferences, yet direct optimization of long-term outcomes is often...
arXiv:2609.14823v1 Announce Type: new Abstract: Multimodal clinical decision-making requires reliable reasoning over heterogeneous evidence from electronic health records, medical images, and physiol...
ClinicalReTrial is a multi‑agent AI system that treats clinical trial protocol optimization as an iterative redesign problem on textual documents. It combines failure diagnosis, safety‑aware modifications, and candidate evaluation within a closed‑loop, reward‑driven framework, using a predictive model as a simulation environment for low‑cost, dense feedback. The system achieves a 56.7% conversion of failed protocols to predicted successes, with a 7.4% average success probability increase at a negligible cost, and its redesign patterns align with real‑world expert changes.
arXiv:2604.20677v3 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and bias, particularly when...
arXiv:2605.12225v3 Announce Type: replace Abstract: While deep transformer-based models have advanced rapidly, their internal mechanisms remain largely a mystery. Recent work has prioritized understa...
arXiv:2608.11025v2 Announce Type: replace Abstract: Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A...
arXiv:2609.07474v2 Announce Type: replace Abstract: Language models compute over tokens: language is their input, their output, and increasingly their internal representation. Whether language should...
arXiv:2609.13190v1 Announce Type: new Abstract: Continuous cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) offers a promising solution for personalized healthcare. However, e...
arXiv:2609.13288v1 Announce Type: new Abstract: Video-language models can answer multiple-choice questions with high confidence yet be wrong. We study whether answer-level reliability scores can be i...
arXiv:2609.13823v1 Announce Type: new Abstract: Point cloud data face serious semantic privacy risks during acquisition, transmission, and cross-institutional sharing. Existing methods mostly rely on...
arXiv:2609.15834v1 Announce Type: new Abstract: Detector response nonuniformity introduces systematic projection errors and ring artifacts in photon-counting detector computed tomography (PCD-CT). In...
arXiv:2602.01257v2 Announce Type: replace Abstract: Recently, point-supervised temporal action localization has gained significant attention for its effective balance between labeling costs and local...