AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Do Reasoning Representations Help Humans Evaluate LLM Outputs?

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Reasoning representations are increasingly used as explanations for large language model outputs. Yet they are typically evaluated with model-centric criteria, such as answer accuracy and faithfulness, leaving it unclear whether they help people evaluate model responses. In this work, we study reasoning representations as human-facing interfaces rather than proxies for model reasoning ability. We conduct a controlled human study of six reasoning formats across tasks of varying complexity, supported by a web-based framework that randomizes task domains, problem instances, and representation ord

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T20:02:11.508Z. This is not the publication date.