Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.35815v1 Announce Type: cross Abstract: Researchers across academia increasingly base significance claims on LLM judge scores and small-sample AI evaluations. Yet without well-calibrated co...
arXiv:2609.35860v1 Announce Type: cross Abstract: Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors a...
arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that ag...
arXiv:2609.37000v1 Announce Type: cross Abstract: Cross-organizational collaboration is widely regarded as a key promise of SysML-based Model-Based Systems Engineering (MBSE), yet practitioners still...
arXiv:2609.37011v1 Announce Type: cross Abstract: Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into...
arXiv:2609.38036v1 Announce Type: cross Abstract: Understanding gender biases in large language models (LLMs) is increasingly important as these systems become embedded in decision-support tools with...
arXiv:2603.04410v3 Announce Type: replace-cross Abstract: While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hi...
arXiv:2604.15086v3 Announce Type: replace-cross Abstract: Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-gra...
arXiv:2609.37857v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly scaled to wider dictionaries to recover fine-grained structure from large language model activations. Howev...
arXiv:2604.25415v2 Announce Type: replace-cross Abstract: People increasingly turn to general-purpose AI chatbots for advice about emotional and mental health problems, but the ability of these syste...
arXiv:2609.37788v1 Announce Type: cross Abstract: Rubrics support the structured evaluation of language models. We propose a rubric for assessing expressed clinical reasoning in model responses, draw...
arXiv:2609.36116v1 Announce Type: new Abstract: We study how to build more capable general-purpose agents by extending large language models (LLMs) with native typed decision-making. We introduce Dya...
arXiv:2609.36240v1 Announce Type: new Abstract: Does representation learning stop when the training loss stops improving? We study this question for matrix Muon, whose polar-normalised updates have a...
arXiv:2609.36612v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conte...
arXiv:2609.36614v1 Announce Type: new Abstract: A commercial incentive need not enter the final ranking algorithm to affect a shopping assistant's recommendation: it may instead influence which prefe...
arXiv:2609.36740v1 Announce Type: new Abstract: Many recommender systems such as for e-commerce and news platforms aim to provide users with rankings they are likely to interact with. Off-Policy Lear...
arXiv:2609.36859v1 Announce Type: new Abstract: We identify and study a structural mechanism for Markovian nonconvex ADMM in reinforcement learning. Using finite discounted MDPs as a canonical provin...
arXiv:2609.36873v1 Announce Type: new Abstract: Multivariate Time Series (MTS) clustering is an important tool in temporal data mining, aiming to discover latent group structures from complex observa...
arXiv:2609.37189v1 Announce Type: new Abstract: We study sparse linear contextual bandits with knapsack constraints under joint reward and consumption corruption. Consumption corruption creates a cha...
arXiv:2609.37209v1 Announce Type: new Abstract: Pairwise losses are increasingly used for reward learning even when pointwise rewards are observed, with mixed empirical results. When and why do pairw...