# Can Unconfident LLM Annotations Be Used for Confident Conclusions?

arXiv: https://arxiv.org/abs/2408.15204 · HTML: https://mlsanity.com/paper/2408.15204/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 65 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [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)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [Show Your Work: Improved Reporting of Experimental Results](https://mlsanity.com/paper/1909.03004/) (2019)
- [Active Learning by Acquiring Contrastive Examples](https://mlsanity.com/paper/2109.03764/) (2021)
- [With Little Power Comes Great Responsibility](https://mlsanity.com/paper/2010.06595/) (2020)
- [A Computational Approach to Politeness with Application to Social Factors](https://mlsanity.com/paper/1306.6078/) (2013)
- [Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty](https://mlsanity.com/paper/2401.06730/) (2024)
- [Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks](https://mlsanity.com/paper/2306.07899/) (2023)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation](https://mlsanity.com/paper/2310.15638/) (2023)
- [We Can Detect Your Bias: Predicting the Political Ideology of News Articles](https://mlsanity.com/paper/2010.05338/) (2020)
- [When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks](https://mlsanity.com/paper/2305.06626/) (2023)
- [Testing of Detection Tools for AI-Generated Text](https://mlsanity.com/paper/2306.15666/) (2023)
- [LLMaAA: Making Large Language Models as Active Annotators](https://mlsanity.com/paper/2310.19596/) (2023)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)

## Built on by (most cited first, 30 of 49)

- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs](https://mlsanity.com/paper/2501.10970/) (2025)
- [Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI](https://mlsanity.com/paper/2501.09731/) (2025)
- [This human study did not involve human subjects: Validating LLM simulations as behavioral evidence](https://mlsanity.com/paper/2602.15785/) (2026)
- [Cost-Optimal Active AI Model Evaluation](https://mlsanity.com/paper/2506.07949/) (2025)
- [Efficient Evaluation of LLM Performance with Statistical Guarantees](https://mlsanity.com/paper/2601.20251/) (2026)
- [SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation](https://mlsanity.com/paper/2507.09108/) (2025)
- [Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey](https://mlsanity.com/paper/2503.01513/) (2025)
- [Always Tell Me The Odds: Fine-grained Conditional Probability Estimation](https://mlsanity.com/paper/2505.01595/) (2025)
- [No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference](https://mlsanity.com/paper/2505.20178/) (2025)
- [Probably Approximately Correct Labels](https://mlsanity.com/paper/2506.10908/) (2025)
- [Another look at statistical inference with machine learning-imputed data](https://mlsanity.com/paper/2411.19908/) (2024)
- [Valid Inference with Imperfect Synthetic Data](https://mlsanity.com/paper/2508.06635/) (2025)
- [Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking](https://mlsanity.com/paper/2605.05973/) (2026)
- [Robust Sampling for Active Statistical Inference](https://mlsanity.com/paper/2511.08991/) (2025)
- [Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring](https://mlsanity.com/paper/2503.17569/) (2025)
- [ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking](https://mlsanity.com/paper/2511.09833/) (2025)
- [Revisiting Active Sequential Prediction-Powered Mean Estimation](https://mlsanity.com/paper/2604.18569/) (2026)
- [Model-in-the-Loop (MILO): Accelerating Multimodal AI Data Annotation with LLMs](https://mlsanity.com/paper/2409.10702/) (2024)
- [The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum](https://mlsanity.com/paper/2508.17164/) (2025)
- [Model-agnostic Selective Labeling with Provable Statistical Guarantees](https://mlsanity.com/paper/2510.14581/) (2025)
- [Next Generation Active Learning: Mixture of LLMs in the Loop](https://mlsanity.com/paper/2601.15773/) (2026)
- [CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion](https://mlsanity.com/paper/2607.05046/) (2026)
- [ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis](https://mlsanity.com/paper/2508.04915/) (2025)
- [What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification](https://mlsanity.com/paper/2510.03541/) (2025)
- [Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer](https://mlsanity.com/paper/2606.11018/) (2026)
- [Mitigating LLM-based p-Hacking by Preregistering for the Next LLM](https://mlsanity.com/paper/2606.27687/) (2026)
- [Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models](https://mlsanity.com/paper/2506.08593/) (2025)
- [Towards a rigorous evaluation of RAG systems: the challenge of due diligence](https://mlsanity.com/paper/2507.21753/) (2025)
- [Enhancing LLM-Based Data Annotation with Error Decomposition](https://mlsanity.com/paper/2601.11920/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have shown high agreement with human raters across a variety of tasks, demonstrating potential to ease the challenges of human data collection. In computational social science (CSS), researchers are increasingly leveraging LLM annotations to complement slow and expensive human annotations. Still, guidelines for collecting and using LLM annotations, without compromising the validity of downstream conclusions, remain limited. We introduce Confidence-Driven Inference: a method that combines LLM annotations and LLM confidence indicators to strategically select which human annotations should be collected, with the goal of producing accurate statistical estimates and provably valid confidence intervals while reducing the number of human annotations needed. Our approach comes with safeguards against LLM annotations of poor quality, guaranteeing that the conclusions will be both valid and no less accurate than if we only relied on human annotations. We demonstrate the effectiveness of Confidence-Driven Inference over baselines in statistical estimation tasks across three CSS settings--text politeness, stance, and bias--reducing the needed number of human annotations by over 25% in each. Although we use CSS settings for demonstration, Confidence-Driven Inference can be used to estimate most standard quantities across a broad range of NLP problems.