mlsanityData to 7 Oct 2026

Benchmarking Large Language Model Uncertainty for Prompt Optimization

arXiv 2409.10044 ↗First posted 16 Sep 2024cs.LG cs.CLcited by 2

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

Abstract (arXiv)

Prompt optimization algorithms for Large Language Models (LLMs) excel in multi-step reasoning but still lack effective uncertainty estimation. This paper introduces a benchmark dataset to evaluate uncertainty metrics, focusing on Answer, Correctness, Aleatoric, and Epistemic Uncertainty. Through analysis of models like GPT-3.5-Turbo and Meta-Llama-3.1-8B-Instruct, we show that current metrics align more with Answer Uncertainty, which reflects output confidence and diversity, rather than Correctness Uncertainty, highlighting the need for improved metrics that are optimization-objective-aware to better guide prompt optimization. Our code and dataset are available at https://github.com/0Frett/PO-Uncertainty-Benchmarking.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 15 of its 28 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

15 of 28 references.

References · 15

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  5. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  6. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
  7. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  8. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 91
  9. 2024Calibrating the Confidence of Large Language Models by Eliciting Fidelitycited by 47
  10. 2024Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruningcited by 19
  11. 2024Text-centric Alignment for Multi-Modality Learningcited by 12
  12. 2022Toward More Generalized Malicious URL Detection Modelscited by 9
3 more
  1. 2023AutoML-GPT: Large Language Model for AutoMLcited by 6
  2. 2024Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Promptingcited by 5
  3. 2024Enhance the Robustness of Text-Centric Multimodal Alignmentscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Uncertainty Profiles for LLMs: Uncertainty Source Decomposition and Adaptive Model-Metric Selectioncited by 4
  2. 2025Multimodal Chip Physical Design Engineer Assistantcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions
  2. 2025Revisiting Uncertainty Estimation and Calibration of Large Language Models
  3. 2026How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding
  4. 2024Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
  5. 2025Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages
  6. 2025Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
  7. 2026Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt
  8. 2026Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs