Out-of-Distribution Generalization of Risk Aversion in Language Models
This paper investigates whether risk aversion trained in low-stakes scenarios can generalize to astronomically high-stakes scenarios, as a potential failsafe against AI misalignment. Introducing the RiskAverseOOD benchmark, initial experiments on Qwen3-8B show that learned risk aversion can partially generalize across 98 orders of magnitude, boosting cooperation rates from 2% to 70% (SFT), 52% (DPO), and 39% (activation steering). However, consistency is insufficient for a reliable failsafe.
-->
[Submitted on 2 Jul 2026]
Title:Out-of-Distribution Generalization of Risk Aversion in Language Models
View a PDF of the paper titled Out-of-Distribution Generalization of Risk Aversion in Language Models, by Kristina Zhang and 5 other authors
View PDF HTML (experimental)
Abstract:Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned. Misaligned but risk-averse AIs would tend to prefer low-risk, low-reward strategies like cooperation over high-risk, high-reward strategies like rebellion, limiting the downsides of any misalignment. But we can only feasibly train AIs to be risk-averse on low-stakes gambles, and we will only be safe if their risk aversion generalizes to astronomically-high-stakes gambles. Will it? To shed light on this question, we introduce RiskAverseOOD: a benchmark for measuring how well risk aversion generalizes out of distribution. We then offer some initial results. Using a variety of methods to make Qwen3-8B choose risk-aversely when the stakes are low, we find that we can induce substantial risk aversion when the stakes are astronomically high. Our models' learned risk aversion generalizes at least partially across 98 orders of magnitude. From a baseline 2% rate of choosing a safe `Cooperate' option, we see rates around 70% (SFT and tie training), 52% (DPO), and 39% (activation steering). In another experiment, our fine-tuned reward model reliably scores risk-averse reasoning above risk-neutral or excessively risk-averse alternatives (99.6% pairwise accuracy). We replicate these effects at different scales (Qwen3-1.7B and Qwen3-14B) and across model families (Gemma-3-12B-IT and Llama-3.1-8B-Instruct). Overall, we find that risk aversion learned at low stakes can generalize OOD to astronomically high stakes, though not yet consistently enough to serve as a reliable failsafe. Achieving that level of consistency is an open problem.
Comments: ICML 2026 Agents in the Wild workshop
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2607.02755 [cs.LG]
(or arXiv:2607.02755v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.02755
arXiv-issued DOI via DataCite
Submission history
From: Elliott Thornley [view email] [v1] Thu, 2 Jul 2026 20:41:30 UTC (70 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Out-of-Distribution Generalization of Risk Aversion in Language Models, by Kristina Zhang and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-07
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
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.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)