Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 01084v1 Announce Type: cross Abstract: Combinatorial routing problems such as the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) are fundamental NP-hard problems with broad real-world applications.
arXiv:2606. 01850v1 Announce Type: new Abstract: Model compression techniques such as quantization and pruning are widely used to reduce the deployment cost of large language models (LLMs), with existing evaluations focusing almost exclusively on accuracy preservation.
arXiv:2605. 05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.
arXiv:2509. 12263v3 Announce Type: replace Abstract: Large multimodal models (LMMs) encode physical laws observed during training, such as momentum conservation, as parametric knowledge.
arXiv:2601. 17952v2 Announce Type: replace-cross Abstract: Interpretability remains a key challenge for deploying language models (LM) in clinical settings such as progression diagnosis of Alzheimer disease, where early and trustworthy predictions are essential.
arXiv:2604. 14514v2 Announce Type: replace Abstract: Healthcare disparities persist across socioeconomic boundaries, often attributed to unequal access to screening, diagnostics, and therapeutics.
arXiv:2606. 00930v1 Announce Type: cross Abstract: Mechanistic interpretability often assumes that probes identifying a representational signature also identify the circuit executing the corresponding computation.
arXiv:2606. 01508v1 Announce Type: cross Abstract: Traditional operating systems were designed around deterministic programs, explicit control flow, and human initiated workflows.
arXiv:2606. 01322v1 Announce Type: cross Abstract: Safety evaluation of Large Language Models (LLMs) remains heavily English-centric, leaving Low-Resource Languages (LRLs), particularly African ones, critically underexplored.
arXiv:2511. 00206v3 Announce Type: replace Abstract: Cognitive science faces ongoing challenges in research integration, formalization, conceptual clarity, and other areas, in part due to its multifaceted and interdisciplinary nature.
arXiv:2606. 01196v1 Announce Type: cross Abstract: Safety alignment learned in high-resource languages transfers poorly to low-resource languages.
arXiv:2602. 01962v2 Announce Type: replace-cross Abstract: Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions.
arXiv:2512. 20806v3 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment.
arXiv:2606. 00813v1 Announce Type: cross Abstract: Safety alignment in LLMs does not improve monotonically across model generations.
arXiv:2606. 01612v1 Announce Type: cross Abstract: Can internal attention patterns in Large Vision Language Models (LVLMs) identify reliable small-object boxes without fine-tuning?
arXiv:2509. 05367v5 Announce Type: replace-cross Abstract: Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe.
arXiv:2509. 24467v3 Announce Type: replace Abstract: Self-supervised learning (SSL) learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necessitating domain-specific explanations.
arXiv:2505. 13273v2 Announce Type: replace Abstract: Large text-to-image diffusion models rarely expose reliable signals of when a prompt is likely to produce a poorly aligned generation, especially when training data is undisclosed.
arXiv:2606. 02119v1 Announce Type: cross Abstract: Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining retain data.
arXiv:2602. 11852v2 Announce Type: replace Abstract: While state-of-the-art language models (LMs) surpass most humans in certain domains, their reasoning remains largely opaque, reducing trust and increasing the risk of deception and hallucination.