mlsanityData to 14 Oct 2026

Enabling Fine-Grained Operating Points for Black-Box LLMs

arXiv 2510.17727 ↗First posted 20 Oct 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Black-box Large Language Models (LLMs) provide practical and accessible alternatives to other machine learning methods, as they require minimal labeled data and machine learning expertise to develop solutions for various decision making problems. However, for applications that need operating with constraints on specific metrics (e.g., precision ≥ 95%), decision making with black-box LLMs remains unfavorable, due to their low numerical output cardinalities. This results in limited control over their operating points, preventing fine-grained adjustment of their decision making behavior. In this paper, we study using black-box LLMs as classifiers, focusing on efficiently improving their operational granularity without performance loss. Specifically, we first investigate the reasons behind their low-cardinality numerical outputs and show that they are biased towards generating rounded but informative verbalized probabilities. Then, we experiment with standard prompt engineering, uncertainty estimation and confidence elicitation techniques, and observe that they do not effectively improve operational granularity without sacrificing performance or increasing inference cost. Finally, we propose efficient approaches to significantly increase the number and diversity of available operating points. Our proposed approaches provide finer-grained operating points and achieve comparable to or better performance than the benchmark methods across 11 datasets and 3 LLMs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

29 of 42 references.

References · 29

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  4. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  5. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  6. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  7. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  8. 2021Revisiting the Calibration of Modern Neural Networkscited by 390
  9. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 293
  10. 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 277
  11. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  12. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 210
17 more
  1. 2019Deep ReLU Networks Have Surprisingly Few Activation Patternscited by 161
  2. 2020Improving model calibration with accuracy versus uncertainty optimizationcited by 123
  3. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 94
  4. 2023Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Modelscited by 91
  5. 2021Classifier Calibration: A survey on how to assess and improve predicted class probabilitiescited by 73
  6. 2024Calibrating Large Language Models Using Their Generations Onlycited by 65
  7. 2024Calibrating Language Models with Adaptive Temperature Scalingcited by 58
  8. 2024Multicalibration for Confidence Scoring in LLMscited by 46
  9. 2024Large Language Models Are Neurosymbolic Reasonerscited by 31
  10. 2024What Are the Odds? Language Models Are Capable of Probabilistic Reasoningcited by 26
  11. 2024LLM-Generated Black-box Explanations Can Be Adversarially Helpfulcited by 21
  12. 2024Black-box Uncertainty Quantification Method for LLM-as-a-Judgecited by 18
  13. 2023Enabling Calibration In The Zero-Shot Inference of Large Vision-Language Modelscited by 17
  14. 2024Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planningcited by 16
  15. 2024DALD: Improving Logits-based Detector without Logits from Black-box LLMscited by 13
  16. 2024Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Modelscited by 8
  17. 2019Cost-Sensitive Feature Selection by Optimizing F-Measurescited by 7

Built on by

Not cited yet.