Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.06155v1 Announce Type: cross Abstract: Neural models, including dense retrievers, have been widely adopted in Information Retrieval (IR), often delivering state-of-the-art performance. Des...
arXiv:2609.06708v1 Announce Type: cross Abstract: Large language models are transforming many industries with their text generation abilities. However, their outputs can be easily tampered with, crea...
arXiv:2609.06991v1 Announce Type: cross Abstract: Recent text-to-audio-video (T2AV) models jointly generate video, speech, sound effects, and ambience from a single text prompt. This capability poses...
arXiv:2609.07022v1 Announce Type: cross Abstract: Reasoning over privacy-constrained records requires combining structured attributes with evidence from free-text narratives. We introduce CIPHER (Cro...
arXiv:2609.07047v1 Announce Type: cross Abstract: Robotic manipulation often requires acting on information that is no longer visible, yet Vision-Language-Action policies are usually evaluated when t...
arXiv:2609.07111v1 Announce Type: cross Abstract: Quadruped robot locomotion policies are often trained using reinforcement learning, which in turn relies heavily on hand-crafted reward functions. De...
arXiv:2609.07160v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) generate text via bidirectional iterative denoising, naturally supporting user-specified constraints anchored...
arXiv:2609.07192v1 Announce Type: cross Abstract: Asynchronous federated learning improves scalability by updating the global model from a server-side buffer of client updates as they arrive, rather...
arXiv:2609.07403v1 Announce Type: cross Abstract: Privacy-sensitive surveillance systems could benefit from large vision-language models (VLMs), but such models typically require centralized access t...
arXiv:2609.07500v1 Announce Type: cross Abstract: The evolution of DNA sequences can be viewed as stochastic dynamics on a high-dimensional discrete space, but it is unclear when empirical transition...
arXiv:2609.07534v1 Announce Type: cross Abstract: Contact-rich assembly remains challenging because it requires submillimeter spatial accuracy and reliable interpretation of forces during sustained c...
arXiv:2609.07675v1 Announce Type: cross Abstract: Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets,...
arXiv:2609.08683v1 Announce Type: cross Abstract: Adversarial robustness in computer vision is still largely achieved through adversarial training or test-time adversarial purification, both of which...
arXiv:2609.08789v1 Announce Type: cross Abstract: Frontier AI developers publish safety frameworks that commit them to evidencing whether their models are dangerous. The European Union and California...
arXiv:2509.24877v3 Announce Type: replace Abstract: The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform hum...
arXiv:2510.08831v2 Announce Type: replace Abstract: As AI writing tools become widespread, we need to understand how both humans and machines evaluate literary style, a domain where objective standar...
arXiv:2604.01461v2 Announce Type: replace Abstract: Reducing hallucinations in Large Language Models (LLMs) is essential for accurate data extraction from large text corpora. Current methods, like pr...
arXiv:2605.09395v3 Announce Type: replace Abstract: In this paper, we propose the first VL\underline{\textbf{M}} \underline{\textbf{a}}gentic \underline{\textbf{r}}easoning framework for few-\underli...
arXiv:2605.14259v3 Announce Type: replace Abstract: Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning....
arXiv:2605.18163v2 Announce Type: replace Abstract: Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor...