arXiv AI

Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models

arXiv:2602. 19101v2 Announce Type: replace-cross Abstract: Value alignment of Large Language Models (LLMs) requires us to empirically measure these models' actual, acquired representation of value.

arXiv AI
Aug 18

Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture

The article argues that current evaluations of large language models’ moral competence focus mainly on whether outputs align with human moral values—the so‑called moral value problem—while neglecting the moral norm problem, which concerns the models’ ability to identify and apply context‑sensitive moral norms. It attributes this imbalance to the field’s reliance on descriptive ethics frameworks that emphasize value representation over normative application. The authors review existing benchmarks, highlight three gaps—lack of ground‑truth norm data, insufficient evaluation of intermediate reasoning, and limited focus on context‑relevant features—and propose a research agenda to develop formal normative representations, expert‑annotated datasets, and evaluation protocols that distinguish between value‑level and norm‑level competence.

By Aidan Kierans, Ritam Dutt, Kaley Rittichier, Shiri Dori-Hacohen, Avijit Ghosh
arXiv AI
1d ago

How Language Models Organize and Structure Moral Knowledge

The study investigates how large language models encode moral knowledge by training linear probes for each category of Moral Foundations Theory. It finds that the model’s representations for different moral foundations occupy distinct, largely independent dimensions yet share a common positive component, indicating an integrated but nuanced moral structure. This geometry is consistent across model architectures and scales, emerges early in pre‑training, and reflects corpus statistics rather than the individualizing/binding distinction of the theory.

By Orion Reblitz-Richardson