SOURCE-LINKED INTELLIGENCE

Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce FACE-Eval (Faithful Attribution of Cue Effects Evaluation), a 5,100-sample evaluation that varies cue location (user message or tool return) and explicitness (direct summary or raw artifact). We measure verbalized commitment among cue-following answers and unverbalized adoption among all cued samples

Read original source ↗ Open in workspace

recordType

paper

region

Global