Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment

• URL: http://arxiv.org/abs/2604.10673v1
• Date: Sun, 12 Apr 2026 14:54:31 GMT
• Title: Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment
• Abstract summary: We argue that principle-specified alignment includes a context-dependent interpretive component.<n>We show that off-policy audits can fail to capture alignment-relevant failures when the two response distributions differ.
• Score: 4.832750949021042
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when they are too broad to settle a situation, or when the relevant facts are unclear, an additional act of judgment is required. This paper analyzes that step through the lens of hermeneutics and argues that alignment therefore includes an interpretive component: it involves context-sensitive judgments about how principles should be read, applied, and prioritized in practice. We connect this claim to recent empirical findings showing that a substantial portion of preference-labeling data falls into cases of principle conflict or indifference, where the principle set does not uniquely determine a decision. We then draw an operational consequence: because such judgments are expressed in behavior, many alignment-relevant choices appear only in the distribution of responses a model generates at deployment time. To formalize this point, we distinguish deployment-induced and corpus-induced evaluation and show that off-policy audits can fail to capture alignment-relevant failures when the two response distributions differ. We argue that principle-specified alignment includes a context-dependent interpretive component.

Related papers

• To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias [61.40435736418359]
  We introduce a unified framework that standardizes heterogeneous benchmarks to contrast isolated demographic assessments with forced-choice comparative settings.<n>We show that comparative settings act as aggressive catalysts for latent discrimination, a shift primarily driven by underspecified contexts.<n>Finally, we demonstrate that this comparative prejudice is a generalized phenomenon that scales positively with model size.
  arXiv  Detail & Related papers  (2026-06-23T13:53:50Z)
• Making Bias Non-Predictive: Training Robust LLM Judges via Reinforcement Learning [91.8584139564909]
  Large language models (LLMs) increasingly serve as automated judges, yet they remain susceptible to cognitive biases.<n>We propose Epistemic Independence Training (EIT), a reinforcement learning framework grounded in a key principle.<n>EIT operationalizes this through a balanced conflict strategy where bias signals are equally likely to support correct and incorrect answers.
  arXiv  Detail & Related papers  (2026-02-02T01:43:48Z)
• The Inconsistency Critique: Epistemic Practices and AI Testimony About Inner States [0.0]
  The question of whether AI systems have morally relevant interests depends in part on how we evaluate AI testimony about inner states.<n>This paper develops what I call the inconsistency critique: independent of whether skepticism about AI testimony is ultimately justified.
  arXiv  Detail & Related papers  (2025-12-22T18:54:07Z)
• Causal Inference Isn't Special: Why It's Just Another Prediction Problem [1.90365714903665]
  Causal inference is often portrayed as distinct from predictive modeling.<n>But at its core, causal inference is simply a structured instance of prediction under distribution shift.<n>This perspective reframes causal estimation as a familiar generalization problem.
  arXiv  Detail & Related papers  (2025-04-06T01:37:50Z)
• AI Alignment at Your Discretion [7.133218044328296]
  In AI alignment, latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are better' or safer'<n>Such discretion remains largely unexamined, posing two risks: (i) annotators may use their power of discretion arbitrarily, and (ii) models may fail to mimic this discretion.<n>By measuring both human and algorithmic discretion over safety alignment datasets, we reveal layers of discretion in the alignment process that were previously unaccounted for.
  arXiv  Detail & Related papers  (2025-02-10T09:19:52Z)
• Prioritization First, Principles Second: An Adaptive Interpretation of Helpful, Honest, and Harmless Principles [30.405680322319242]
  The Helpful, Honest, and Harmless (HHH) principle is a framework for aligning AI systems with human values.<n>We argue for an adaptive interpretation of the HHH principle and propose a reference framework for its adaptation to diverse scenarios.<n>This work offers practical insights for improving AI alignment, ensuring that HHH principles remain both grounded and operationally effective in real-world AI deployment.
  arXiv  Detail & Related papers  (2025-02-09T22:41:24Z)
• Auditing Fairness under Unobserved Confounding [56.61738581796362]
  We show that, surprisingly, one can still compute meaningful bounds on treatment rates for high-risk individuals.<n>We use the fact that in many real-world settings we have data from prior to any allocation to derive unbiased estimates of risk.
  arXiv  Detail & Related papers  (2024-03-18T21:09:06Z)
• Towards Responsible AI in Banking: Addressing Bias for Fair Decision-Making [69.44075077934914]
  "Responsible AI" emphasizes the critical nature of addressing biases within the development of a corporate culture. This thesis is structured around three fundamental pillars: understanding bias, mitigating bias, and accounting for bias. In line with open-source principles, we have released Bias On Demand and FairView as accessible Python packages.
  arXiv  Detail & Related papers  (2024-01-13T14:07:09Z)
• Fairness and robustness in anti-causal prediction [73.693135253335]
  Robustness to distribution shift and fairness have independently emerged as two important desiderata required of machine learning models. While these two desiderata seem related, the connection between them is often unclear in practice. By taking this perspective, we draw explicit connections between a common fairness criterion - separation - and a common notion of robustness.
  arXiv  Detail & Related papers  (2022-09-20T02:41:17Z)
• On the system loophole of generalized noncontextuality [0.0]
  We introduce the concept of the noncontextuality graph of a prepare-and-measure scenario. We argue that whether or not an experiment is noncontextual is not as absolute as often perceived.
  arXiv  Detail & Related papers  (2022-09-09T18:00:38Z)
• Non-Determinism and the Lawlessness of Machine Learning Code [43.662736664344095]
  We show that the effects of non-determinism, and consequently its implications for the law, become clearer from the perspective of reasoning about ML outputs as distributions over possible outcomes. We conclude with a brief discussion of what work ML can do to constrain the potentially harm-inducing effects of non-determinism.
  arXiv  Detail & Related papers  (2022-06-23T17:05:34Z)
• Towards a multi-stakeholder value-based assessment framework for algorithmic systems [76.79703106646967]
  We develop a value-based assessment framework that visualizes closeness and tensions between values. We give guidelines on how to operationalize them, while opening up the evaluation and deliberation process to a wide range of stakeholders.
  arXiv  Detail & Related papers  (2022-05-09T19:28:32Z)
• Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization [77.24152933825238]
  We show that for linear classification tasks we need stronger restrictions on the distribution shifts, or otherwise OOD generalization is impossible. We prove that a form of the information bottleneck constraint along with invariance helps address key failures when invariant features capture all the information about the label and also retains the existing success when they do not.
  arXiv  Detail & Related papers  (2021-06-11T20:42:27Z)

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.