What question did this study set out to answer?

This research aims to determine if log-probabilities from language models can indicate how social-moral judgments are resolved.

June 22, 2026Open Access

Reading "Friction" in LLM Logprobs: A Substrate-Level Correlate of Present Route-Competition in Social-Moral Judgments

View Full Paper

Ask AI

Bookmark

This research aims to determine if log-probabilities from language models can indicate how social-moral judgments are resolved.
Conducted three experiments examining moral commitment and route-competition signals.
Analyzed data from language models, focusing on log-probabilities and internal disparities.
Controlled for variables such as fairness reactions and moral scripts across experiments.
E1: Moral commitments were specific and robust, with measurable friction in ambiguous judgments.
E2: Binary rule-evaluation revealed generalized capability effects without defining social-moral signatures.
E3: Disengagement in disadvantaged agents was influenced more by comparison rather than reward amount.

No takes yet. Share an insight, caveat, or question.

Randomized trials evaluate token-level signals in language models influencing social-moral judgments, suggesting potential implications.

Tomas Pødenphant Lund (2026) studied this question.

View Full Paper

Ask AI

Bookmark