arXiv Machine Learning
Jun 25
Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment
arXiv:2606. 26071v1 Announce Type: new Abstract: A central goal of safety research is determining whether a model is misaligned.
Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations
arXiv:2607. 04645v1 Announce Type: cross Abstract: Safety alignment in large language models is typically evaluated against direct, imperative harmful requests.
Related stories
Hugging Face Trending Papers
Jun 17
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
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.
arXiv AI
Jul 23
Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations
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 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.
arXiv Machine Learning
Jun 25
Do Thinking Tokens Help with Safety?
arXiv:2606. 25013v1 Announce Type: new Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts.
arXiv AI
Jun 30
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.
Hugging Face Trending Papers
Jun 28
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned models (7-31B) and five attack types (GCG, AutoDAN, DeepInception, prefilling, intent laundering).
arXiv AI
Jun 10
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
arXiv:2606. 10740v1 Announce Type: new Abstract: Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation.
arXiv AI
Jun 12
Prefill Awareness in Large Language Models
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.
Hugging Face Trending Papers
Jun 4
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
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. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
arXiv AI
Jul 1
The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs
arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
arXiv AI
23h ago
Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models
arXiv:2608. 17202v1 Announce Type: new Abstract: Safety alignment in open-weight language models is trivially removable: abliteration projects a refusal-mediating direction out of the weights in minutes, and no release-time defense we are aware of prevents it durably.