← Back to all news
arXiv Machine Learning By Jaewoo Lim, Sungbok Shin, Sanghyun Hong

Do Reasoning Representations Help Humans Evaluate LLM Outputs?

Read the original on arXiv Machine Learning →

The paper investigates whether reasoning representations—explanations for large language model outputs—aid humans in evaluating those outputs. A controlled human study tested six reasoning formats across tasks of varying complexity, measuring structural understanding, error detection, and trust calibration. Results revealed a mismatch: participants favored planning- and decomposition-based representations, yet simpler chain-of-thought traces better supported verification, trust, and interpretability, while preferred formats increased calibration risks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
Aug 27

ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability

ReFIne is a training framework that augments large reasoning models with three trustworthiness properties: interpretability, faithfulness, and reliability. It combines supervised fine‑tuning with GRPO to produce structured, tag‑based reasoning traces, explicitly disclose decisive information, and provide self‑assessments of soundness and confidence. Applied to Qwen3 models, ReFIne improves interpretability by 44.0 %, faithfulness by 18.8 %, and reliability by 42.4 % on mathematical benchmarks.

By Chung-En Sun, Ge Yan, Akshay Kulkarni, Tsui-Wei Weng
fine-tuningbenchmarkssafety
More like this →
arXiv AI
Aug 28

Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning

The paper proposes a user‑centric Chain‑of‑Thought (CoT) reasoning framework that structures LLM reasoning traces into self‑contained, verifiable steps using XML‑like tags. This design allows users to independently assess and correct the AI’s reasoning while preserving performance on mathematical reasoning tasks. User studies show that the approach improves perceived usefulness and ease of use compared to standard CoT.

By Philipp Schr\"oppel
llmssafety
More like this →