# LLM Confidence Evaluation Measures in Zero-Shot CSS Classification

arXiv: https://arxiv.org/abs/2410.13047 · HTML: https://mlsanity.com/paper/2410.13047/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Builds on (most cited first, 7 of 7)

- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Conformal Prediction with Large Language Models for Multi-Choice Question Answering](https://mlsanity.com/paper/2305.18404/) (2023)
- [Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach](https://mlsanity.com/paper/2404.15993/) (2024)
- [Uncertainty Quantification for In-Context Learning of Large Language Models](https://mlsanity.com/paper/2402.10189/) (2024)
- [An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project](https://mlsanity.com/paper/2401.16186/) (2024)

## Built on by (most cited first, 6 of 6)

- [MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform](https://mlsanity.com/paper/2506.00308/) (2025)
- [Cautious Next Token Prediction](https://mlsanity.com/paper/2507.03038/) (2025)
- [ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis](https://mlsanity.com/paper/2508.04915/) (2025)
- [FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI](https://mlsanity.com/paper/2510.02185/) (2025)
- [Self-Anchored Attention Model for Sample-Efficient Classification of Prosocial Text Chat](https://mlsanity.com/paper/2506.09259/) (2025)
- [Prosocial Behavior Detection in Player Game Chat: From Aligning Human-AI Definitions to Efficient Annotation at Scale](https://mlsanity.com/paper/2508.05938/) (2025)

## Abstract (arXiv)

Assessing classification confidence is critical for leveraging large language models (LLMs) in automated labeling tasks, especially in the sensitive domains presented by Computational Social Science (CSS) tasks. In this paper, we make three key contributions: (1) we propose an uncertainty quantification (UQ) performance measure tailored for data annotation tasks, (2) we compare, for the first time, five different UQ strategies across three distinct LLMs and CSS data annotation tasks, (3) we introduce a novel UQ aggregation strategy that effectively identifies low-confidence LLM annotations and disproportionately uncovers data incorrectly labeled by the LLMs. Our results demonstrate that our proposed UQ aggregation strategy improves upon existing methods andcan be used to significantly improve human-in-the-loop data annotation processes.