Record
- Authors
- Bowyer, S.; Aitchison, L.; Ivanova, D. R.
- Year
- 2025
- Title
- Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
- Published in
- Proceedings of the 42nd International Conference on Machine Learning
- Type
- Conference paper
- DOI
- 10.48550/arxiv.2503.01747
- arXiv
- arXiv:2503.01747
- Our note
- none yet
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4416045832 · DOI 10.48550/arxiv.2503.01747 · arXiv:2503.01747 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
bowyer-2025-position-don-t-use-clt-llm
Cited on
- Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations read status: not stated
As cited
The pages cite this work in one form.
-
Bowyer, S., Aitchison, L., and Ivanova, D. R. (2025). Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints. Proceedings of the 42nd International Conference on Machine Learning, PMLR 267. arXiv:2503.01747v3. (Later work; main text read, appendices skimmed.)
BibLaTeX
@inproceedings{bowyer-2025-position-don-t-use-clt-llm,
author = {Bowyer, S. and Aitchison, L. and Ivanova, D. R.},
title = {{Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints}},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
date = {2025},
doi = {10.48550/arxiv.2503.01747},
eprint = {2503.01747},
eprinttype = {arxiv}
}