mlsanityData to 14 Oct 2026

Do Reasoning Representations Help Humans Evaluate LLM Outputs?

arXiv 2609.09038 ↗First posted 8 Sep 2026cs.LG cs.HCcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

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 order. The study collects fine-grained judgments of structural understanding, error detection and localization, and trust calibration. Our study shows a mismatch between perceived preference and support for human evaluation. Participants prefer planning- and decomposition-based representations, but simpler chain-of-thought traces better support verification, trust, and interpretability. Preferred representations also introduce calibration risks, with more false alarms on correct traces and high trust despite low willingness to verify.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 10 of its 53 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

10 of 53 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Cumulative Reasoning with Large Language Models8 Aug
  2. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Models30 Nov

Other references · 8

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2023Teaching Large Language Models to Self-Debugcited by 988
  3. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  4. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 703
  5. 2025Thought Anchors: Which LLM Reasoning Steps Matter?cited by 129
  6. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  7. 2024Evaluating LLMs at Detecting Errors in LLM Responsescited by 50
  8. 2025Improving Human Verification of LLM Reasoning through Interactive Explanation Interfacescited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Cognitive Foundations for Reasoning and Their Manifestation in LLMs
  2. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
  3. 2026Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning
  4. 2026Evaluating the False Trust Engendered by LLM Explanations
  5. 2026Seeing the Reasoning: How LLM Rationales Influence User Trust and Decision-Making in Factual Verification Tasks
  6. 2025Position: On the Methodological Pitfalls of Evaluating Base LLMs for Reasoning
  7. 2025What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation
  8. 2026Explaining Too Much? Understanding How Large Language Model Reasoning Traces Influence Performance and Metacognition