Behavioural feasible set: Value alignment constraints on AI decision support

• URL: http://arxiv.org/abs/2603.21435v1
• Date: Sun, 22 Mar 2026 22:52:42 GMT
• Title: Behavioural feasible set: Value alignment constraints on AI decision support
• Abstract summary: When organisations adopt commercial AI systems for decision support, they inherit value embedded by vendors that are neither transparent nor renegotiable.<n>I formalise this as a feasible set, the range of recommendations reachable under vendor-imposed alignment constraints, and characterise diagnostic thresholds for when organisational requirements exceed the system's flexibility.
• Score: 4.770039226643351
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 when organisational requirements exceed the system's flexibility. In scenario-based experiments using binary decision scenarios and multi-stakeholder ranking tasks, I show that alignment materially compresses this set. Comparing pre- and post-alignment variants of an open-weight model isolates the mechanism: alignment makes the system substantially less able to shift its recommendation even under legitimate contextual pressure. Leading commercial models exhibit comparable or greater rigidity. In multi-stakeholder tasks, alignment shifts implied stakeholder priorities rather than neutralising them, meaning organisations adopt embedded value orientations set upstream by the vendor. Organisations thus face a governance problem that better prompting cannot resolve: selecting a vendor partially determines which trade-offs remain negotiable and which stakeholder priorities are structurally embedded.

Related papers

• Agentic AI: User Empowerment or Enclosure? [3.9727752701702728]
  We argue that the answer to whether Agentic AI will empower users is an open question.<n>We conduct a comparative case analysis of four more mature domains where similar forms of agency arose.<n>We identify this as depoliticization, a concept from political theory, here at work in technological systems.
  arXiv  Detail & Related papers  (2026-08-06T18:49:13Z)
• Seeing Is Not Deciding: Can Multimodal LLMs Act as Effective CEOs? [53.05042283845008]
  We introduce C-SUITEBENCH, a controlled multimodal benchmark for executive business decisions.<n>We place nine models in the role of a chief executive officer and evaluate their decision-making ability.<n>We uncover a multimodal integration paradox: adding visual business information degrades constrained resource allocation for all nine models.
  arXiv  Detail & Related papers  (2026-08-06T10:43:33Z)
• Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models [121.70781851874035]
  Large language models (LLMs) are increasingly used in decision support.<n>It is important to understand whether their choices under uncertainty exhibit stable and interpretable behavioural regularities.<n>Here we examine this question using a controlled multi-model framework based on no-limit Texas Hold'em.
  arXiv  Detail & Related papers  (2026-07-11T10:33:39Z)
• Selective Ensemble Based on Preference-Directed Multi-Objective Bandits [90.75513823660775]
  We formalize a sequential decision problem under partially specified linear preferences.<n>We then propose a preference-directed upper confidence bound (PrefUCB) algorithm.<n> Experiments on large pre-trained model selective ensemble tasks and online asset allocation under institutional mandates validate our method.
  arXiv  Detail & Related papers  (2026-06-20T07:52:46Z)
• Minimal Oversight: Uncertainty-Aware Governance for Delegated AI Systems [0.0]
  central AI problem is how much autonomy to grant, which evidence should calibrate trust, what performance ceiling a delegated AI system can sustain, and when human intervention becomes necessary.<n>We propose the Minimum Sufficient Oversight Principle (MSO), a variational principle for principled autonomy delegation.<n>The resulting Euler-Lagrange solution yields a water-filling allocation of governed delegation across the task space.
  arXiv  Detail & Related papers  (2026-06-04T22:29:45Z)
• AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning? [7.373294811303388]
  Current practice collects one-directional comments from self-selected attendees, leaving participant mix as an uncontrolled source of outcome variation.<n>We present AGORA, a framework that holds the network, demand, and solver fixed while systematically varying meeting composition through stakeholder agents, structured deliberation, and governance gates.
  arXiv  Detail & Related papers  (2026-05-31T08:00:37Z)
• Position: agentic AI orchestration should be Bayes-consistent [92.04373485710285]
  This paper argues that coherent decision-making requires Bayesian principles at the orchestration level of the agentic system.<n>It provides examples and design patterns to illustrate how beliefs and utility-aware policies can improve agentic AI orchestration.
  arXiv  Detail & Related papers  (2026-05-01T15:43:43Z)
• HIPO: Instruction Hierarchy via Constrained Reinforcement Learning [57.40686733111483]
  textscHIPO is a novel alignment framework that formulates HIF as a Constrained Markov Decision Process.<n>textscHIPO elevates system prompts from mere input context to strict algorithmic boundaries.
  arXiv  Detail & Related papers  (2026-03-17T06:12:41Z)
• DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding [59.16244104797919]
  We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**.<n>DARC frames response selection as distributionally robust, risk-sensitive decision making.<n>Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality.
  arXiv  Detail & Related papers  (2026-03-09T09:21:29Z)
• Selection as Power: Constrained Reinforcement for Bounded Decision Authority [0.0]
  We introduce incentivized selection governance, where reinforcement updates are applied to scoring and reducer parameters under externally enforced sovereignty constraints.<n>We show that learning dynamics can coexist with structural diversity when sovereignty constraints are enforced at every update step.<n>These results demonstrate that learning dynamics can coexist with structural diversity when sovereignty constraints are enforced at every update step.
  arXiv  Detail & Related papers  (2026-03-02T16:02:34Z)
• Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive [0.0]
  AI systems are increasingly deployed in high-stakes contexts under the assumption they can be governed by norms.<n>This paper demonstrates that the assumption is formally invalid for optimization-based systems.
  arXiv  Detail & Related papers  (2026-02-26T17:16:17Z)
• Position: General Alignment Has Hit a Ceiling; Edge Alignment Must Be Taken Seriously [51.03213216886717]
  We take the position that the dominant paradigm of General Alignment reaches a structural ceiling in settings with conflicting values.<n>We introduce Edge Alignment as a distinct approach in which systems preserve multi dimensional value structure.
  arXiv  Detail & Related papers  (2026-02-23T16:51:43Z)
• Towards Selection as Power: Bounding Decision Authority in Autonomous Agents [0.0]
  We propose a governance architecture that separates cognition, selection, and action into distinct domains and models autonomy as a vector of sovereignty.<n>We evaluate the system across multiple regulated financial scenarios under adversarial stress targeting variance manipulation, threshold gaming, framing skew, ordering effects, and entropy probing.<n>Results show that mechanical selection governance is implementable, auditable, and prevents deterministic outcome capture while preserving reasoning capacity.
  arXiv  Detail & Related papers  (2026-02-16T10:10:47Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Admissibility Alignment [0.0]
  We present MAP-AI, a new control-plane system architecture for aligned decision-making under uncertainty.<n>It enforces alignment through Monte Carlo estimation of outcome distributions and admissibility-controlled policy selection.<n>We show how alignment evaluation can be integrated into decision-making itself, yielding an admissibility-controlled action selection mechanism.
  arXiv  Detail & Related papers  (2026-01-05T05:58:19Z)
• DecisionFlow: Advancing Large Language Model as Principled Decision Maker [49.088778182807395]
  DecisionFlow is a novel decision modeling framework that guides models to reason over structured representations of actions, attributes, and constraints.<n>Rather than predicting answers directly from prompts, DecisionFlow builds a semantically grounded decision space and infers a latent utility function.<n> Empirical results show that DecisionFlow achieves up to 30% accuracy gains over strong prompting baselines.
  arXiv  Detail & Related papers  (2025-05-27T16:23:53Z)
• Online Decision Mediation [72.80902932543474]
  Consider learning a decision support assistant to serve as an intermediary between (oracle) expert behavior and (imperfect) human behavior. In clinical diagnosis, fully-autonomous machine behavior is often beyond ethical affordances.
  arXiv  Detail & Related papers  (2023-10-28T05:59:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.