AI reasoning effort predicts human decision time in content moderation
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Large language models can now generate intermediate reasoning steps before producing answers, improving performance on difficult problems by interactively developing solutions. This study uses a content moderation task to examine parallels between human decision times and model reasoning effort, measured using the length of the chain-of-thought (CoT). Across three frontier models, CoT length consistently predicts human decision time. Moreover, humans took longer and models produced longer CoTs when important variables were held constant, suggesting similar sensitivity to task difficulty. Analyses of the CoT content shows that models reference various contextual factors more frequently when making such decisions. These findings show parallels between human and AI reasoning on practical tasks and underscore the potential of reasoning traces for enhancing interpretability and decision-making.
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 7 of its 42 references that are in the map. First posted on arXiv 27 Aug 2025.
Builds on
7 of 42 references.
Closest ancestors · 1
Same direction, newest first
Other references · 6
- 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
- 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 703
- 2025Reasoning Models Don't Always Say What They Thinkcited by 415
- 2024Deliberative Alignment: Reasoning Enables Safer Language Modelscited by 308
- 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
- 2025Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetycited by 249
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Reasoning aligns language models to human cognition
- 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
- 2026Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models
- 2026Thinking effort aligns between humans and reasoning models in abductive reasoning
- 2025Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism
- 2026Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective
- 2026To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
- 2023Studying and improving reasoning in humans and machines