Causal Methods for LLM Development and Evaluation
Authors:
- Dennis FrauenDFDennis Frauen
- Marie BrockschmidtMBMarie Brockschmidt
- Konstantin HessKHKonstantin Hess
- Haorui MaHMHaorui Ma
- Yuchen MaYMYuchen Ma
- Abdurahman MaaroufAMAbdurahman Maarouf
- Maresa SchröderMSMaresa Schröder
- Jonas SchweisthalJSJonas Schweisthal
- Yuxin WangYWYuxin Wang
- Athiya DeviyaniADAthiya Deviyani
- Sonali ParbhooSPSonali Parbhoo
- Rahul G. KrishnanRKRahul G. Krishnan
Open Access
- 8 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 13170-13177
Abstract
No abstract availableAll Related Versions
This publication has 30 references indexed in Scilit:
- Holistic evaluation of large language models for medical tasks with MedHELMNature Medicine, 2026
- Algorithms for reliable decision-making need causal reasoningNature Computational Science, 2025
- Doubly-Valid/Doubly-Sharp Sensitivity Analysis for Causal Inference with Unmeasured ConfoundingJournal of the American Statistical Association, 2024
- On the Dangers of Stochastic Parrots2021
- Shortcut learning in deep neural networksNature Machine Intelligence, 2020
- Measuring and Mitigating Unintended Bias in Text Classification2018
- Double/debiased machine learning for treatment and structural parametersThe Econometrics Journal, 2018
- Non-parametric Methods for Doubly Robust Estimation of Continuous Treatment EffectsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2016
- Estimation of Regression Coefficients When Some Regressors are not Always ObservedJournal of the American Statistical Association, 1994
- Estimating causal effects of treatments in randomized and nonrandomized studies.Journal of Educational Psychology, 1974