Behavioural feasible set: Value alignment constraints on AI decision support
When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support decisions but which recommendations the system can actually produce given how its vendor has configured it. I formalise this as a behavioural feasible set, the range of recommendations reachable under vendor-imposed alignment constraints, and characterise diagnostic thresholds for
Record details
Published: 22 March 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment · Healthcare · Transparency
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Adoption and Effectiveness of AI-Based Anomaly Detection for Cross Provider Health Data Exchange
arXiv · 19 March 2026
A Proposed Biomedical Data Policy Framework to Reduce Fragmentation, Improve Quality, and Incentivize Sharing in Indian Healthcare in the era of Artificial Intelligence and Digital Health
arXiv · 13 April 2026
Transparency of AI in Healthcare as a Multilayered System of Accountabilities: Between Legal Requirements and Technical Limitations
OpenAlex · 30 May 2022
VCFSE Infrastructure Services - AWARD
UK Contracts Finder — AI procurement · 16 December 2025
VCFSE Infrastructure Services
UK Contracts Finder — AI procurement · 6 February 2025
Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
arXiv · 18 March 2026
How to cite this record
ethics.ai (22 March 2026), “Behavioural feasible set: Value alignment constraints on AI decision support,” evidence record 6883, https://ethics.ai/record/6883 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.