{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/how-emotionally-stable-is-albert-testing-1","title":"How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task","arxiv_id":"2111.09612","date":"2021-11-18","proceeding":"EMNLP (Eval4NLP) 2021 11","authors":["Urja Khurana","Eric Nalisnick","Antske Fokkens"],"abstract":"Despite their success, modern language models are fragile. Even small changes in their training pipeline can lead to unexpected results. We study this phenomenon by examining the robustness of ALBERT (arXiv:1909.11942) in combination with Stochastic Weight Averaging (SWA) (arXiv:1803.05407) -- a cheap way of ensembling -- on a sentiment analysis task (SST-2). In particular, we analyze SWA's stability via CheckList criteria (arXiv:2005.04118), examining the agreement on errors made by models differing only in their random seed. We hypothesize that SWA is more stable because it ensembles model snapshots taken along the gradient descent trajectory. We quantify stability by comparing the models' mistakes with Fleiss' Kappa (Fleiss, 1971) and overlap ratio scores. We find that SWA reduces error rates in general; yet the models still suffer from their own distinct biases (according to CheckList).","url_abs":"https://arxiv.org/abs/2111.09612v1","url_pdf":"https://arxiv.org/pdf/2111.09612v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"how-emotionally-stable-is-albert-testing-1","repo_url":"https://github.com/cltl/robustness-albert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"SST-2"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"albert","method_name":"ALBERT"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"lamb","method_name":"LAMB"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"stochastic-weight-averaging","method_name":"Stochastic Weight Averaging"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2111.09612","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}