arXiv:2607. 18295v1 Announce Type: new Abstract: We study whether alignment schemes that reshape a base model's output distribution, combined with bounded safety filters, can drive the probability of harmful behavior to zero in modern large language models.
arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.
arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.
arXiv:2604. 22167v2 Announce Type: replace-cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale.
arXiv:2605.29224v2 Announce Type: replace-cross Abstract: AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incor...
arXiv:2503. 11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images.
arXiv:2607. 08883v1 Announce Type: new Abstract: Behavioral alignment in large language models often masks fragile internal safety representations.
arXiv:2508.20766v2 Announce Type: replace-cross Abstract: Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent researc...
arXiv:2510. 01529v3 Announce Type: replace Abstract: Ball et al.
arXiv:2606. 19168v1 Announce Type: new Abstract: To achieve deeper safety alignment for large language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by filtering unsafe data or rewriting it into safer forms.
arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.
arXiv:2607. 26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning: maliciously injected passages that manipulate retrieved evidence.
Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the response violates a policy. This distinction is cri...