arXiv:2608.29118v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) on narrowly harmful datasets can lead to misalignment broadly, a phenomenon known as emergent misalignment (EM...
The paper introduces FAID, a fine‑grained adaptive framework for detecting implicit hate speech. It first classifies samples into Shallow, Targeted, or Context‑Dependent categories and then applies tailored strategies—prompt‑tuning for shallow cases, knowledge augmentation for targeted ones, and an agentic prompt‑generation system for context‑dependent posts. Experiments on four benchmark datasets show that FAID outperforms state‑of‑the‑art baselines by allocating computational effort only where needed.
arXiv:2608.23264v1 Announce Type: new Abstract: Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably lea...
arXiv:2610.28092v1 Announce Type: cross Abstract: Persuasive writing exploits cognitive biases, recruiting a reader's mental shortcuts to shape belief, often without the reader noticing. We call the...
The paper introduces FAID, a fine‑grained adaptive framework for detecting implicit hate speech. It first classifies samples into Shallow, Targeted, or Context‑Dependent categories and then applies tailored strategies—Prompt‑Tuning for Shallow, knowledge augmentation for Targeted, and an agentic prompt‑generation system for Context‑Dependent cases. Experiments on four benchmark datasets show that FAID outperforms state‑of‑the‑art baselines.
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
arXiv:2602. 05056v2 Announce Type: replace-cross Abstract: Online scams increasingly leverage fluent and context-aware social engineering strategies, creating growing demand for AI systems that explain why a message may be risky.
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. However, this assumption remains underexplored and exposes a vulnerability in low-resource languages.
The study investigates whether large language models (LLMs) rely on textual evidence or on their pre‑existing knowledge when annotating text. Using counterfactual prompts for 995 public figures, the authors find that LLMs often default to memory shortcuts—providing correct facts about a figure even when the text contains no supporting evidence. These shortcuts are amplified by evaluation design and incentives, but can be mitigated by name reminders or masking, though with trade‑offs in gender annotation.
arXiv:2608. 14577v1 Announce Type: cross Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis.