Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 23639v1 Announce Type: cross Abstract: This paper studies convolution rank regression (CRR) over decentralized distributed learning networks.
arXiv:2607. 24275v1 Announce Type: cross Abstract: Ethical governance of AI-driven systems is often expressed through high-level principles and static documentation, creating a gap between regulatory requirements and system-level verification.
arXiv:2607. 23408v1 Announce Type: new Abstract: Expensive black-box optimization is ubiquitous in science and engineering, where function evaluations are costly and the evaluation budget is limited.
arXiv:2607. 24586v1 Announce Type: cross Abstract: Large Language Models can produce fluent text that is false, unsupported by the available evidence, or inconsistent with information that appears to be internally represented by the model.
arXiv:2607. 23055v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting can fail severely on constraint-dense logical reasoning tasks, where unverified errors accumulate silently across steps.
arXiv:2607. 22709v1 Announce Type: cross Abstract: The proliferation of internet memes has introduced new complexities to automated content moderation, particularly in detecting misogyny.
arXiv:2607. 22695v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment.
arXiv:2607. 22635v1 Announce Type: new Abstract: Target-oriented dialogue systems have demonstrated strong capabilities in completing user goals through interactive conversations.
arXiv:2607. 24331v1 Announce Type: new Abstract: As the inference phase of Large Language Models (LLMs) requires handling long context windows, the Key-Value (KV) cache initially appears to address this challenge but eventually becomes a significant bottleneck as the context window continues to grow.
arXiv:2607. 22651v1 Announce Type: new Abstract: Large language models (LLMs) have enabled increasingly capable conversational agents, but reliably controlling their behavior in real-time interactive environments remains a significant challenge.
arXiv:2607. 23772v1 Announce Type: cross Abstract: We study a restless multi-armed bandit (RMAB) problem for a stochastic deadline scheduling application.
arXiv:2607. 23480v1 Announce Type: new Abstract: Variational autoencoders (VAEs) transform high-dimensional, often noisy data into a compact latent representation, making downstream optimization more tractable.
arXiv:2603. 03536v2 Announce Type: replace-cross Abstract: Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction.
arXiv:2607. 23379v1 Announce Type: cross Abstract: Activation Oracles (AOs) are language models trained to answer natural-language questions about another model's internal activations.
arXiv:2606. 24941v2 Announce Type: replace-cross Abstract: Reviewing recorded interviews for affective cues such as composure and agitation is slow and subjective, and cloud services that could automate the task require sensitive audio to leave the device.
arXiv:2607. 24392v1 Announce Type: cross Abstract: Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility.
arXiv:2607. 23388v1 Announce Type: cross Abstract: As constrained learning becomes increasingly common, models are trained under explicit feasibility requirements to enforce fairness, safety, robustness, regulariza- tion, and physics or logic constraints.
arXiv:2601. 18350v5 Announce Type: replace-cross Abstract: Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interference after adapter merging, including the re-emergence of explicit reasoning traces under strict decoding.
arXiv:2607. 24391v1 Announce Type: cross Abstract: AI systems already govern.
arXiv:2607. 22545v1 Announce Type: cross Abstract: Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and general harm, a combination no existing open guardrail addresses in a single inference pass.