“Large language models for enabling constructive online conversations” with Dr. Kristina Gligorić

“Large language models for enabling constructive online conversations” with Dr. Kristina Gligorić

2024-05-09T01:30:00+00:00

2024-05-09T03:30:00+00:00

https://epflalumni.ch//medias/image/thumbnail_11770725036630c0d501980.jpg

Dear EPFL alumni and alumnae,Please join us as we welcome, Dr. Kristina Gligorić (EPFL alumna PhD IN'22), Stanford University, on Wednesday, May 8, 2024, 6:30PM-8:30PM, at Swissnex in San Francisco, Pier 17.BioDr. Kristina Gligorić is a Postdoctoral Scholar at Stanford University Computer Science Department, advised by Dan Jurafsky at the NLP group. Previously she obtained her Ph.D. in Computer Science at EPFL, where she was advised by Robert West. Her research focuses on developing computational approaches to address societal issues, understand and improve human well-being, and promote social good. She leverages large-scale textual data and digital behavioral traces and tailors computational methods drawn from NLP and causal inference. Her work has been published in top computer science conferences focused on computational social science and social media (CSCW, ICWSM, TheWebConf) and natural language processing (EACL, NAACL, EMNLP), and broad audience journals (Nature Communications and Nature Medicine). She is a Swiss National Science Foundation Fellow and University of Chicago Rising star in Data Science. She received awards for her work, including EPFL Thesis Distinction and CSCW 2021 Best Paper Honorable Mention Award.Connect on LinkedIn with Dr. Kristina GligorićPresentation AbstractNLP systems promise to disrupt society through applications in high-stakes social domains. However, current evaluation and development focus on tasks that are not grounded in specific societal implications, which can lead to societal harm. There is a need to evaluate and mitigate the societal harms and, in doing so, bridge the gap between the realities of application and how models are currently developed.In this talk, I will present recent work addressing these issues in the domain of online content moderation. In the first part, I will discuss online content moderation to enable constructive conversations about race. Content moderation practices on social media risk silencing the voices of historically marginalized groups. We find that both the most recent models and humans disproportionately flag posts in which users share personal experiences of racism. Not only does this censorship hinder the potential of social media to give voice to marginalized communities, but we also find that witnessing such censorship exacerbates feelings of isolation. We offer a path to reduce censorship through a psychologically informed reframing of moderation guidelines. These findings reveal how automated content moderation practices can help or hinder this effort in an increasingly diverse nation where online interactions are commonplace.In the second part, I will discuss how identified biases in models can be traced to the use-mention distinction, which is the difference between the use of words to convey a speaker's intent and mention of words for quoting what someone said or pointing out properties of a word. Computationally modeling the use-mention distinction is crucial for enabling counterspeech to hate and misinformation. Counterspeech that refutes problematic content mentions harmful language but is not harmful itself. We show that even recent language models fail at distinguishing use from mention and that this failure propagates to downstream tasks. We introduce prompting mitigations that teach the use-mention distinction and show that they reduce these errors.Finally, I will discuss the big picture and other recent efforts to address these issues in different domains beyond content moderation, including education, emotional support, and public discourse about AI. I will reflect on how, by doing so, we can minimize the harms and develop and apply NLP systems for social good.Program 6:30pm — Doors open7:00pm — Opening remarks – Swissnex in San Francisco & EPFL Alumni U.S. West Coast Chapter7:05pm — Presentation by Dr. Kristina Gligorić7:45pm — Q&A8:00pm — Networking & aperitif 8:30pm — Doors closeTo attend this presentation, please use password “EPFL_Alumni_NPL” to register.If you have any questions about this event, please contact Azadeh Mohebbi We look forward to seeing you there!EPFL Alumni U.S. West Coast Chapter

https://epflalumni.ch/en/event/-large-language-models-for-enabling-constructive-online-conversations-with-dr-kristina-gligoric/2024/05/09/678