Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.13595v1 Announce Type: cross Abstract: Predicting potential dangers is core to safety. Forecasting the presence of other traffic agents is core to danger prediction. Occluded traffic agent...
arXiv:2609.13778v1 Announce Type: cross Abstract: Human trajectory prediction requires modeling both individual motion patterns and social interactions among agents. Existing methods have made substa...
arXiv:2609.13869v1 Announce Type: cross Abstract: Automatic sentence function identification is important for many downstream natural language processing (NLP) applications such as dialogue systems,...
arXiv:2609.13909v1 Announce Type: cross Abstract: Continuous-latent Autoregressive Diffusion Transformer (AR-DiT) models have demonstrated immense potential in zero-shot speech generation. However, t...
arXiv:2609.13980v1 Announce Type: cross Abstract: Arabic large-language-model (LLM) evaluation has matured around Modern Standard Arabic (MSA): aggregated leaderboards such as the Open Arabic LLM Lea...
arXiv:2609.14003v1 Announce Type: cross Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provid...
arXiv:2609.14060v1 Announce Type: cross Abstract: Quantization is one of the default deployment paths for open-weight LLM agents, but it is not behavior-preserving: an adversary can release a full-pr...
arXiv:2609.14115v1 Announce Type: cross Abstract: Safety-critical control of autonomous systems requires formal safety certificates, such as controlled invariant sets, that must be computed online as...
arXiv:2609.14151v1 Announce Type: cross Abstract: Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model b...
arXiv:2609.14187v1 Announce Type: cross Abstract: Memory-efficient feature representations are increasingly important in machine learning settings where storage, transmission cost, bandwidth, or priv...
arXiv:2609.14234v1 Announce Type: cross Abstract: Financial fraud in corporate transaction networks has grown more coordinated and harder to detect with rule-based engines and with classical learning...
arXiv:2609.14448v1 Announce Type: cross Abstract: Hallucination in large language models reduces their reliability and slows adoption. Various white-box studies have used internal representations to...
arXiv:2609.14467v1 Announce Type: cross Abstract: Automating clinical documentation from long-form doctor-patient conversations remains challenging for modern audio-language models. While cascaded AS...
arXiv:2609.14498v1 Announce Type: cross Abstract: Sensor-based human activity recognition (HAR) is fundamental to ubiquitous and wearable computing, yet existing foundation models are largely designe...
arXiv:2609.14593v1 Announce Type: cross Abstract: Living-Off-the-Land (LOTL) is the dominant evasion technique of Advanced Persistent Threat (APT) actors, exploiting legitimate Windows utilities to c...
arXiv:2609.14754v1 Announce Type: cross Abstract: Causal claims about large language model (LLM) internals rest on measurements. Those might include a projection, a cosine, an ablation delta, or an i...
arXiv:2609.14762v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy ris...
arXiv:2609.14849v1 Announce Type: cross Abstract: We characterize how people are turning to LLMs as oracles: all-knowing authorities on subjective personal questions. Motivated by risks to users' aut...
arXiv:2609.14969v1 Announce Type: cross Abstract: Realignment is a promising approach for improving the cross-lingual transfer ability of multilingual language models, particularly for extremely low-...
arXiv:2609.15017v1 Announce Type: cross Abstract: Prompt-injection detectors are typically evaluated using aggregate F1 on in-distribution test data, which offers limited insight into behavior under...