Скачать или смотреть How to Win LMs and Influence Predictions (Sameer Singh, UCI), Repl4NLP 2021 Invited Talk

How to Win LMs and Influence Predictions: Using Short Phrases to Control NLP Models

Sameer Singh
University of California, Irvine

Current NLP pipelines rely significantly on finetuning large pre-trained language models. Relying on this paradigm makes such pipelines challenging to use in real-world settings since massive task-specific models are neither memory- nor inference-efficient, nor do we understand how they fare in adversarial settings. This talk will describe our attempts to address these seemingly unrelated concerns by investigating how specific short phrases in the input can control model behavior. These short phrases (which we call triggers) will help us identify model vulnerabilities and introduce new paradigms of training models.

In the first part of the talk, I will focus on the adversarial setting. I will show how easy it is for adversaries to craft triggers that cause a target model to misbehave when the trigger appears in the input. I will also introduce a data poisoning technique that enables adversaries to inject arbitrary triggers into the target model. However, in the second part of the talk, I will show how these triggers can also be used to “prompt” language models to act as task-specific models, providing a negligible-memory, no-learning way to create classifiers. I will end with a comprehensive study of the interplay between prompting and finetuning, providing some guidelines for effectively performing few-shot learning with large language models.

Bio: Dr. Sameer Singh is an Associate Professor of Computer Science at the University of California, Irvine (UCI). He is working primarily on robustness and interpretability of machine learning algorithms, along with models that reason with text and structure for natural language processing. Sameer was a postdoctoral researcher at the University of Washington and received his PhD from the University of Massachusetts, Amherst, during which he also worked at Microsoft Research, Google Research, and Yahoo! Labs. He has received the NSF CAREER award, selected as a DARPA Riser, UCI Early Career Distinguished Faculty award, and the Hellman and the Noyce Faculty Fellowships. His group has received funding from Allen Institute for AI, Amazon, NSF, DARPA, Adobe Research, Hasso Plattner Institute, NEC, Base 11, and FICO. Sameer has published extensively at machine learning and natural language processing venues, including conference paper awards at KDD 2016, ACL 2018, EMNLP 2019, AKBC 2020, and ACL 2020. (https://sameersingh.org/)