GAP-NO-EMPIRICS Normative without empirical grounding

Moral dilemmas for moral machines · Travis LaCroix · 2022

“responses to moral dilemmas vary widely across societies and time periods. Trolley problems, specifically, have figured heavily in empirical research in neuroscience and psychology, and, again, human responses to these scenarios are highly dependent on external features.”

why coded: Dilemma responses culturally/temporally variable - unstable as ground truth · unit #2, pp. 741

Disagreement, AI alignment, and bargaining · Harry R. Lloyd · 2024

“One important question that I have not discussed in this paper is that of who should count as a 'stakeholder' for any particular AI system [...] This is a particularly important topic for future alignment research, since it has the potential to significantly affect the verdicts of all three of the voting-, decision-, and bargaining-theoretic approaches to alignment.”

why coded: Stakeholder-identification left open - same all-affected gap G&K flag · unit #12, pp. 1780

Machines that halt resolve the undecidability of artificial intelligence alignment · Gabriel A. Melo; Marcos R. O. A. Máximo; Nei Y. S… · 2025

“The inner alignment problem, which asserts whether an arbitrary artificial intelligence (AI) model satisfices a non-trivial alignment function of its outputs given its inputs, is undecidable. This is rigorously proved by Rice's theorem [...] Nevertheless, there is an enumerable set of provenly aligned AIs that are constructed from a finite set of provenly aligned operations. Therefore, we argue that the alignment should be a guaranteed property from the AI architecture rather than a characteristic imposed post-hoc on an arbitrary AI model.”

why coded: Formal limit on what any audit/verification regime can promise for arbitrary models · unit #1, pp. 1

Moral disagreement and the limits of AI value alignment: a dual challenge of epistemic ju… · Nick Schuster; Daniel Kilov · 2025

“The trouble with morally controversial cases [...] is that even purported moral experts are apt to disagree about them; and there is no straightforward way to independently determine who, if anyone, is right. [...] without independent methods of verification, we cannot rule out the possibility that such a case is instead analogous to an image of an unfamiliar face, in which case the system would not have the right training data to perform well. [...] with enough errant training data, an AI system will learn problematic patterns that undermine its ability to render morally correct judgments and decisions. While the crowdsourcing approach can overcome a lot of incidental error and disagreement in training data by discovering patterns that cut through the noise, systematic error poses a deeper problem.”

why coded: No independent verification for moral correctness - systematic error undetectable in principle · unit #10, pp. 6079

Responsibility Attribution for AI-Mediated Damages with Mechanistic Interpretability · Lena Kästner; Johann Cordes; Herbert Zech · 2026

“Though causation is considered a necessary condition of responsibility and liability (Sect. 2), it may not be sufficient. For instance, identifying relevant difference-makers may not automatically reveal the actor in command of them (see also Sect. 4.3); or we might find that no (human) actor is actually in command of the difference-maker in question. To this end, multi-agent models, Markov-models and game-theoretical methods might be extremely useful [2,52].”

why coded: Gestures at formal tools (game theory, Markov models) but no account of what SHOULD happen in the no-actor case · unit #11, pp. 197

Beyond Preference-based Value-alignment (IEAI Research Brief Q2 2026) · Julia Li · 2026

“A 2025 paper on cultural alignment found that survey methods which assess LLMs' cultural alignment fail to satisfy stability, extrapolability and steerability assumptions (Khan et al., 2025). The findings suggest that in some cases, alignment is often an artefact of evaluation design rather than a genuine property of models. [...] Another paper found that LLMs only displayed coherent value structures consistent with empirically backed theories of human values when they were given person descriptions and prompted to have a 'personality' (Rozen et al., 2024).”

why coded: Ironically: the empirical instability undermines armchair claims about what LLMs value (tentative) · unit #6, pp. 4

Understanding the Process of Human-AI Value Alignment · Jack McKinlay; Marina De Vos; Janina A. Hoffmann;… · 2026

“Value calibration was neglected in the research we analysed, but given the dynamic nature of values, this needs to change. Ways to effectively track stakeholder values in dynamic situations are a component of this.”

why coded: Value calibration (tracking dynamic stakeholder values post-deployment) neglected - what a live corpus provides · unit #8, pp. 28

“Testing approaches to value alignment is one last area that would strongly benefit from attention and unification. The current environment of individual experimental designs, often lacking in complexity or validation, limits the ability to say whether an approach is fit for purpose.”

why coded: Fragmented, non-comparable evaluation - no shared benchmarks for alignment claims · unit #9, pp. 28