arXiv AI
Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 13
How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment
arXiv:2608. 11816v1 Announce Type: cross Abstract: State-aligned distortion has been documented in China-origin text-based large language models (LLMs), but whether, and in what form, it arises in multimodal systems has not been systematically examined.
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
Aug 13
Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models
arXiv:2608. 11583v1 Announce Type: new Abstract: Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters.
arXiv Computation and Language
Oct 12
The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs
The paper investigates how alignment training in large language models (LLMs) can suppress cultural knowledge rather than erase it. By surveying 1.53 million humans across 16 MENA countries and testing 26 models, the authors find that when models refuse to answer, their internal logit distributions still align closely with human responses, a phenomenon they term the "alignment veto." They distinguish between suppression failures—where accurate internal representations are blocked at output—and representational bias failures—where the encoding itself diverges from human values, and show that these require different interventions. The study also reveals significant inequities in the safety tax, with a 37.6 % cost and a 19.8 % alignment-quality gap between best- and worst-served nations, and notes that native-language prompting actually widens this gap. Sparse autoencoder analysis identifies a candidate feature in the DPO stage that mediates suppression in the Tulu-3-8B model.
Hugging Face Trending Papers
Jul 26
Auditing Alignment Controllability in LLMs via Political Axes
Political audits of large language models (LLMs) usually reduce each to one point on a political compass. But that resting point barely matters in deployment: a model must land somewhere, and what counts is how far, and in which directions, its answers can be steered.
arXiv AI
Jul 8
ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety
arXiv:2605. 14152v2 Announce Type: replace-cross Abstract: Safety evaluations for large language models (LLMs) increasingly target high-stakes National Security and Public Safety (NSPS) risks, yet multilingual safety is mostly assessed through translation-only benchmarks that preserve the underlying scenario, leaving how language and geopolitical context interact largely unexamined beyond a few language pairs.