Hugging Face Trending Papers
DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Jun 18
Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection
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 AI
Sep 17
Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
The paper introduces "cunning questions"—non‑safety prompts that contain misleading premises or subtle inconsistencies—to train large language models (LLMs) to scrutinize underlying intent and assumptions. Experiments show that incorporating these questions improves robustness against out‑of‑distribution jailbreak attacks and enhances subsequent safety fine‑tuning, achieving a new state‑of‑the‑art reduction in mean ASR from 17.40% to 15.05% across nine backbone–benchmark combinations. The authors argue that this training fosters vigilance, enabling models to prioritize safety judgments before engaging in harmful planning.
arXiv AI
Jul 7
Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types
arXiv:2604. 09544v2 Announce Type: replace-cross Abstract: Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly.
arXiv AI
3d ago
TRACE: Temporal Risk Assessment and Concept Editing for Safer Language Generation
arXiv:2610.15365v1 Announce Type: new Abstract: Large language models (LLMs) can produce harmful content while generating a response. A useful safeguard should not only detect this risk during genera...
arXiv AI
Aug 11
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
arXiv:2608. 09095v1 Announce Type: new Abstract: Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is crucial for developing trustworthy artificial intelligence.
arXiv AI
Jun 6
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.