arXiv:2604. 07967v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, weaken, or correct the false proposition they are supposed to preserve.
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
arXiv:2607. 12650v1 Announce Type: cross Abstract: Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny.
arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.
arXiv:2606. 19819v1 Announce Type: cross Abstract: Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking.
arXiv:2606. 01441v1 Announce Type: new Abstract: Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve intent while triggering commonsense hallucinations.
arXiv:2607. 05397v1 Announce Type: cross Abstract: Agent systems increasingly execute rather than advise.
arXiv:2605. 12813v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs.
arXiv:2607. 20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it.
arXiv:2607. 08066v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces can surface misaligned or deceptive behavior.
As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.
arXiv:2606. 21678v2 Announce Type: replace-cross Abstract: Language models can generate plausible rationales for their predictions, but these explanations may not faithfully represent the model's internal reasoning.
arXiv:2606. 12703v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) agents increasingly run with persistent memory that accumulates across user sessions.