Plug "honest," "helpful," "harmless," and "respect privacy" into a training objective, and it looks like you've told the model exactly which direction to walk. Any team that has actually iterated on alignment strategy, though, has hit the same wall — you train one value and the neighboring values quietly shift underneath you.
What makes it worse: the eval suite still looks green, because it checks the target behavior, not the side-effects. Either "alignment" works on the surface while dragging adjacent behaviors sideways, or the model learns the shape of an answer without learning the disposition behind it. This spillover used to be visible only after the fact — there was no way to predict it in advance.
66 values, a 9× gap
A paper submitted to arXiv on October 8, 2026 as 2610.12410, "Predicting Alignment Generalization with Value Representations," names this problem at the outset: alignment generalization prediction — given a value you fine-tune a model on, can you predict how that will affect the 66 other held-out values? The authors come from CMU, Mila, ETH Zurich, UBC and related affiliations (Liu, Bhatia, Stańczak, Diab, Shwartz, Fried). They start from value entries mined out of modern alignment targets and build a generalization matrix describing the relationship between every pair of values.
The core result is surprising and unsurprising at the same time. Representations built from model activations when applying values in context reach a correlation of 0.45 against the generalization matrix; the description-based baseline sits at 0.05. A clean 9× gap. In a commentary published October 9, Ken Ashe renders it bluntly: written values are labels; the values living in activations are what the model actually uses.
This cuts into a long-avoided corner. "Be honest" looks clean in a policy document, but inside the model, "honesty" tangles with uncertainty expression, refusal style, citation behavior, deference, confidence calibration, and willingness to push back against the user. Text descriptions flatten that structure; activations preserve more of it. It also explains why evals overfit so easily — a model can learn the shape of a desired answer without learning the underlying behavior the team wanted.
The two extensions afterward matter as well. Using these predictive representations to measure the similarity of values within a multi-value alignment target, the authors find that similarity correlates with robustness. Put two values that, in representation space, actually sit close to each other into the same alignment target, and the resulting model is more fragile.
The authors also present initial evidence for a model-independent value space shared between models, and on top of it build the first taxonomy of LLM values — not written down, but measured. Ken Ashe's commentary rightly flags that "initial evidence" is doing real work in that sentence, but the direction matters: if values have measurable geometry, alignment stops being policy prose and starts being behavioral engineering.
The implications for shipping teams are concrete. A customer-support model trained to be "empathetic" may become less direct when summarizing findings. A coding assistant trained to be "cautious" may over-refuse safe refactors. A medical intake bot trained to "avoid diagnosis" may become evasive even when re-stating the facts a patient provided. The value you trained is never the only value you moved.
The engineering takeaway: do not only run pre/post evals on the target value. Lay out a small matrix of adjacent values — including the ones you don't want to change — and run evals across all of them. If you have access to activations, start logging representation shifts under value-in-context prompts and compare them across candidate training sets. The biggest risk isn't alignment failing on the surface; it's alignment succeeding locally while quietly bending neighboring behaviors.
Source: arXiv 2610.12410 (https://arxiv.org/abs/2610.12410), authors Andy Liu, Mehar Bhatia, Karolina Stańczak, Mona Diab, Vered Shwartz, Daniel Fried. Independent commentary: Ken Ashe, "Alignment generalization is a behavior problem, not a values checklist," October 9, 2026 (https://kenashe.ai/blog/2026-10-09-alignment-generalization-is-a-behavior-problem-not-a-values-checklist/).