COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Natural Experiments in NLP and Where to Find Them
Natural Experiments in NLP and Where to Find ThemAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Mateja Jamnik. In training language models, training choices—such as the random seed for data ordering or the token vocabulary size—significantly influence model behaviour. Answering counterfactual questions like “How would the model perform if this instance were excluded from training?” is computationally expensive, as it requires re-training the model. Once these training configurations are set, they become fixed, creating a “natural experiment” where modifying the experimental conditions incurs high computational costs. Using econometric techniques to estimate causal effects from observational studies enables us to analyse the impact of these choices without requiring full experimental control or repeated model training. In this talk, I will present our paper, Causal Estimation of Memorisation Profiles (Best Paper Award at ACL 2024 ), which introduces a novel method based on the difference-in-differences technique from econometrics to estimate memorisation without requiring model re-training. This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsPostgraduate Travel Group IoT Political Thought Postdoctoral ForumOther talksConservation Evidence Predicting recurrence of prostate cancer: a Bayesian approach Q&A Session A bound on the quantum value of all compiled nonlocal games Biosynthesis Of Anti-Inflammatory Triterpene Fatty Acid Esters In Calendula Officinalis Roundtable on 'Hegel and Italian Political Thought: The Practice of Ideas, 1832-1900' |