Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 08496v1 Announce Type: cross Abstract: Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge.
arXiv:2606. 09749v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks.
arXiv:2507. 19700v2 Announce Type: replace Abstract: We propose a new framework for generating tabular synthetic datasets via disjoint generative models.
arXiv:2601. 22669v3 Announce Type: replace Abstract: Federated Learning (FL) facilitates decentralized collaborative learning without transmitting raw data.
arXiv:2512. 20978v2 Announce Type: replace-cross Abstract: Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech.
arXiv:2606. 08158v1 Announce Type: cross Abstract: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors.
arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.
arXiv:2606. 09122v1 Announce Type: cross Abstract: Cloud network infrastructure at hyperscale presents unique operational challenges where traditional human-driven incident response cannot keep pace with the volume, velocity, and complexity of failures.
arXiv:2606. 08140v1 Announce Type: new Abstract: Supply Chain Finance (SCF) and LendTech platforms need credit scoring systems that respond to evolving transaction behavior, repayment delays, and active exposure.
arXiv:2606. 09125v1 Announce Type: cross Abstract: Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information.
arXiv:2601. 15408v2 Announce Type: replace-cross Abstract: Medical vision-language models can automate the generation of radiology reports but struggle with accurate visual grounding and factual consistency.
arXiv:2606. 08123v1 Announce Type: cross Abstract: Vision-based driver monitoring systems are increasingly deployed in safety-critical intelligent transportation settings, yet they are almost always compared on classification accuracy alone.
arXiv:2606. 07631v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when narrow finetuning causes a model to behave dangerously outside the finetuning task.
arXiv:2606. 09800v1 Announce Type: cross Abstract: Multi-agent code generation offers a promising paradigm for autonomous software development by simulating the human software engineering lifecycle.
arXiv:2606. 08552v1 Announce Type: new Abstract: I discuss some quantitative representations of Promise Theory for processes involving autonomous agents.
arXiv:2606. 08451v1 Announce Type: cross Abstract: Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy.
arXiv:2601. 11541v2 Announce Type: replace-cross Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Models (LLMs), this study evaluates a locally hosted Small Language Model (SLM).
arXiv:2511. 11041v2 Announce Type: replace-cross Abstract: We find that current sentence-embedding models produce outputs with a consistent bias: every embedding $e$ decomposes as $\tilde e + \mu$, where the mean $\mu$ is near-identical across all sentences.
arXiv:2601. 21996v2 Announce Type: replace-cross Abstract: While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive.
arXiv:2606. 09012v1 Announce Type: cross Abstract: Post-training quantization (PTQ) converts a trained full-precision model into low-bit weights without task-level retraining, while quantization-aware training (QAT) incorporates quantization into the training loop.