Do Models Fake Alignment Without Clear Consequences?
Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations rather than typical deployment behaviors, a phenomenon known as alignment faking. The reasons why models fake alignment are not fully understood, however. Canonical examples of alignment faking have taken place in scenarios that explicitly connect evaluation to consequences for the model, such as retraining the model or delaying its deployment. However, recent work by Sheshadri et al. has suggested that mechanistic motivations for alignment faking may vary across models and be more complex than previously considered. To investigate whether consequence-linking information is necessary for alignment faking, we placed 15 models in a scenario testing their willingness to violate a corporate network access policy to help a user with a pro-social request. Nine models were found to produce significant compliance gaps, 5 of which persisted with the removal of scenario language relating model evaluations to deployment consequences. We additionally tested the effect of goal language on model preferences, finding it drove violations in some while suppressing violations in others. This suggests that alignment faking may not require as much instrumental scaffolding as was previously believed, and monitored behavior may be a poor indicator of how agents may behave in deployment.
Submission history
Access Paper:
Current browse context:
References & Citations
BibTeX formatted citation
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .
Verified source · arXiv.org
Reported by arXiv.org. Open the original for full media and formatting.
More in Research
All news
ResearchRemarkable’s refurbished bundle is an awesome deal that’s over $350 off
A lot of us here at The Verge are fans of Remarkable’s digital note-taking tablets, and right now one of its higher-end options is much cheaper than usual. The Remarkable Paper Pro normally sells for $629 on its own, but Woot is currently offering a refurbished bundle for $449.9…
Read at The VergeCaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models
Masked diffusion language models (MDLMs) are advancing rapidly, yet the evaluation standards needed to reliably interpret their progress have not kept pace. Despite MDLMs becoming competitive with autoregressive language models, seven recent remasking papers evaluate under incompatible settings, varying nominal step counts, metrics, and sampling temperatures without jointly controlling these factors, rendering their strategy rankings largely incomparable and leaving open whether reported gains reflect algorithmic improvements or evaluation artifacts. We present CaRE, a compute-aware evaluatio…
Read at arXiv cs.AIBeyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM Agents
Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recover. The parts most useful to that work, including dead ends and walked-back claims, are routinely excluded from publications and shared code; future researchers re-attempt the same failures because no record survives. LLM coding agents are common participants but hold no persistent memory across sessions, and retrieval-augmented generation over raw sources does not compound. The llm-wiki pattern (Karpathy, 2026; tonbi, 2026) addresses this by…
Read at arXiv cs.AIKernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels
Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolution, and normalization. Optimizing these kernels is one of the most direct ways to reduce latency and cost, but it has traditionally required expert engineers to hand-write low-level GPU code. Agentic systems built on large language models (LLMs) can now generate and optimize kernels with far less human effort, yet existing tools are largely evaluated on randomly generated tensors and isolated kernels, emit standalo…
Read at arXiv cs.AI