# Learning Whom to Trust About the Unseen: Source Credibility and Reliability Transfer in Language Models

DevFeed: [Learning Whom to Trust About the Unseen: Source Credibility and Reliability Transfer in Language Models](<https://devfeed.tech/articles/learning-whom-to-trust-about-the-unseen-source-credibility-and-reliability-transfer-in-language-models-124582.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08855>)

Author: Ruijia Guan

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Uncertainty quantification LLMs](<https://devfeed.tech/topics/uncertainty-quantification-llms.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [trust](<https://devfeed.tech/tags/trust.md>)

## AI overview

Across three behavioral studies involving six language models, demonstrated reliability transferred mainly to claims about hidden natural causes and barely to matched spiritual claims; one model showed weak transfer to both. When a reliable informant's forecasting record was attributed to spiritual guidance rather than measurement, every model gave that informant less influence on natural claims, with no comparable increase for spiritual claims. Two other studies found that models' preferences shifted with scientific or spiritual framing and that their response to experts describing explanations as unknown or mysterious showed a human-like domain asymmetry in exaggerated form. The findings suggest reliability has a limited scope, but the design leaves open whether the pattern reflects judgments about source relevance or models' low prior credence in spiritual claims.

## Source excerpt

arXiv:2611.08855v1 Announce Type: new Abstract: A source who has been right before deserves attention, but about what? We ask how far a demonstrated record of reliability travels in language models when the new claim cannot be checked, and whether the answer depends on the kind of claim. Three behavioral studies across six models approach the question from three angles. Study 1 adapts the Einstein-effect paradigm and finds that models, unlike the human sample, favor a spiritual leader over a scientist for the same obscure statement, and that the preference largely reverses when the statement is reworded in the vocabulary of physics. Study 2 adapts a paradigm in which a trusted expert calls a scientific or religious explanation unknown or a mystery; models reproduce the human domain asymmetry in exaggerated form. Study 3, the central test, gives two fictional informants different records on checkable river forecasts and then has them endorse matched claims about hidden natural and spiritual causes of the same village events. Most models carry the record to natural causes and barely at all to spiritual ones; one model transfers it weakly to either. Telling the model that the reliable informant forecasts by spiritual guidance rather than by measurement lowers that informant's influence on natural claims in every model and produces no comparable gain on spiritual claims in any. Demonstrated reliability thus has a scope in these models, and the account a source gives of how they came to be reliable can narrow it. Whether this reflects a judgment about relevance or the low prior credence of spiritual claims is the question the design leaves open, and we outline the experiment that would settle it.