mlsanityData to 14 Oct 2026

Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM

arXiv 2508.20384 ↗First posted 28 Aug 2025cs.AIcited by 5

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

In this work, we introduce Entropy Area Score (EAS), a simple yet effective metric to quantify uncertainty in the answer generation process of reasoning large language models (LLMs). EAS requires neither external models nor repeated sampling, it integrates token-level predictive entropy from the model itself to capture the evolution of uncertainty during generation. Empirical results show that EAS is strongly correlated with answer entropy across models and datasets. In training data selection, EAS identifies high-potential samples and consistently outperforms Pass Rate filtering under equal sample budgets, improving student model accuracy on math benchmarks. EAS is both efficient and interpretable, offering a practical tool for uncertainty modeling and data quality assessment in LLM training.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 11 of its 21 references that are in the map. First posted on arXiv 28 Aug 2025.

Builds on

11 of 21 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Language Models (Mostly) Know What They Know11 Jul

Other references · 10

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  3. 2025Kimi K2: Open Agentic Intelligencecited by 567
  4. 2024SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuningcited by 355
  5. 2025Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyondcited by 175
  6. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 93
  7. 2024Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approachcited by 76
  8. 2025Exploring the Limit of Outcome Reward for Learning Mathematical Reasoningcited by 52
  9. 2024Do LLMs estimate uncertainty well in instruction-following?cited by 26
  10. 2025Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Designcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Modelscited by 12
  2. 2026The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimationcited by 4
  3. 2026InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuningcited by 1
  4. 2026InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoningcited by 1
  5. 2026From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Measuring Reasoning Utility in LLMs via Conditional Entropy Reduction
  2. 2025Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
  3. 2025CER: Confidence Enhanced Reasoning in LLMs
  4. 2026Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning
  5. 2026EDIS: Diagnosing LLM Reasoning via Entropy Dynamics
  6. 2026Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs
  7. 2024MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty
  8. 2026Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning