Abstract

While large language models have advanced the state-of-the-art in natural language processing, these models are trained on large-scale datasets, which may include harmful information. Studies have shown that as a result, the models exhibit social biases and generate misinformation after training. In this talk, I will discuss my work on analyzing and interpreting the risks of large language models across the areas of fairness, trustworthiness, and safety. I will first describe my research in the detection of dialect bias between African American English (AAE) vs. Standard American English (SAE). The second part investigates the trustworthiness of models through the memorization and subsequent generation of conspiracy theories. I will end my talk with recent work in AI safety regarding text that may lead to physical harm.

Biography

Sharon is a 5th-year Ph.D. candidate at the University of California, Santa Barbara, where she is advised by Professor William Wang. Her research interests lie in natural language processing, with a focus on Responsible AI. Sharon’s research spans the subareas of fairness, trustworthiness, and safety, with publications in ACL, EMNLP, WWW, and LREC. She has spent summers interning at AWS, Meta, and Pinterest. Sharon is a 2022 EECS Rising Star and a current recipient of the Amazon Alexa AI Fellowship for Responsible AI.

Abstract

Understanding the implications underlying a text is critical to assessing its impact, in particular the social dynamics that may result from a reading of the text. This requires endowing artificial intelligence (AI) systems with pragmatic reasoning, for example to correctly conclude that the statement “Epidemics and cases of disease in the 21st century are “staged”” relates to unfounded conspiracy theories. In this talk, I discuss how shortcomings in the ability of current AI systems to reason about pragmatics present challenges to equitable detection of false or harmful language. I demonstrate how these shortcomings can be addressed by imposing human-interpretable structure on deep learning architectures using insights from linguistics.

In the first part of the talk, I describe how adversarial text generation algorithms can be used to improve robustness of content moderation systems. I then introduce a pragmatic formalism for reasoning about harmful implications conveyed by social media text. I show how this pragmatic approach can be combined with generative neural language models to uncover implications of news headlines. I also address the bottleneck to progress in text generation posed by gaps in evaluation of factuality. I conclude by showing how context-aware content moderation can be used to ensure safe interactions with conversational agents.

Biography

Saadia Gabriel is a PhD candidate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Prof. Yejin Choi and Prof. Franziska Roesner. Her research
revolves around natural language processing and machine learning, with a particular focus on building systems for understanding how social commonsense manifests in text (i.e. how do people typically behave in social scenarios), as well as mitigating spread of false or harmful text (e.g. Covid-19 misinformation). Her work has been covered by a wide range of media outlets like Forbes and TechCrunch. It has also received a 2019 ACL best short paper nomination, a 2019 IROS RoboCup best paper nomination and won a best paper award at the 2020 WeCNLP summit. Prior to her PhD, Saadia received a BA summa cum laude from Mount Holyoke College in Computer Science and Mathematics.

Abstract

Large language models (LLMs) have demonstrated incredible power, but they also possess vulnerabilities that can lead to misuse and potential attacks. In this presentation, we will address two fundamental questions regarding the responsible utilization of LLMs: (1) How can we accurately identify AI-generated text? (2) What measures can safeguard the intellectual property of LLMs? We will introduce two recent watermarking techniques designed for text and models, respectively. Our discussion will encompass the theoretical underpinnings that ensure the correctness of watermark detection, along with robustness against evasion attacks. Furthermore, we will showcase empirical evidence validating their effectiveness. These findings establish a solid technical groundwork for policymakers, legal professionals, and generative AI practitioners alike.

Biography

Lei Li is an Assistant Professor in Language Technology Institute at Carnegie Mellon University. He received Ph.D. from Carnegie Mellon University School of Computer Science. He is a recipient of ACL 2021 Best Paper Award, CCF Young Elite Award in 2019, CCF distinguished speaker in 2017, Wu Wen-tsün AI prize in 2017, and 2012 ACM SIGKDD dissertation award (runner-up), and is recognized as Notable Area Chair of ICLR 2023. Previously, he was a faculty member at UC Santa Barbara. Prior to that,  he founded ByteDance AI Lab in 2016 and led its research in NLP, ML, Robotics, and Drug Discovery. He launched ByteDance’s machine translation system VolcTrans and AI writing system Xiaomingbot, serving one billion users.