Oct 22, 2023 @ Birmingham, UK
Personalized Generative AI
Held in conjunction with CIKM 2023
Contact: cikm2023-ws-pgai@amazon.com
Welcome To The Personalized Generative AI Workshop 2023!
The growing significance of personalization in AI systems necessitates the use of user-specific data like profiles, historical behaviors, and persona descriptions. Integration of this data into generation-based models has been a key focus in Information Retrieval (IR) and Natural Language Processing (NLP) communities, benefiting recommendation systems, search engines, and conversational AI. Generative models offer inductive learning from diverse user signals, enabling cross-domain knowledge transfer and tailored results that enhance user engagement and trust. Recent advancements, particularly Large Language Models (LLMs), revolutionize NLP and IR with reasoning abilities, complex task handling, and context learning. However, utilizing generative models for personalization presents challenges in bridging knowledge gaps, mitigating trust-eroding hallucinatory results, and overcoming input size limitations. This workshop aims to address these challenges and explore personalized applications, fostering discussions and unlocking the full potential of personalized generative models for more accurate and user-centric AI systems.
Thank You!
Thank you all the organizers, authors, speakers, panelists, and attendees for the success of our workshop! See you next year.
Important Notice
Virtual Attendance
A Zoom link will be sent to all authors, speakers, and panelists soon. Anyone interested in our workshop can reach out to cikm2023-ws-pgai@amazon.com to obtain the Zoom link and password in advance.
Panel Discussion
All participants are welcome to send your questions to the panelists ahead to cikm2023-ws-pgai@amazon.com.
Call for Papers
The primary theme of the inaugural PGAI workshop is “Personalization meets Large Language Models”. The main objective of the workshop is to foster a platform where researchers and practitioners from academia and industry can discuss novel ideas, techniques, and methodologies for integrating personalization into LLMs and a broader family of generative models more effectively and efficiently. The relevant topics include, but are not limited to, the following:
Investigating novel techniques for efficient and effective fine-tuning of LLMs on user data
AI agents that leverage user preferences, behaviors, and contextual information to deliver personalized experiences
Addressing ethical concerns and privacy risks associated with LLMs
Interpretable and explainable personalized AI
Evaluating the performance, fairness, robustness, and overall impact of personalized LLM-based systems
Data resources comprising a task with personalized information
Applications of personalization-aware LLMs in Natural Language Processing/Information Retrieval (e.g., personalized search and recommendation, personalized text generation) and in other fields (e.g., finance, healthcare, social media, climate, etc.)
Personalization for multi-modal (e.g., text-to-image) generative models
Submission Link: https://easychair.org/conferences/?conf=pgaicikm2023
Important Dates
September 10, 2023: Deadline for paper submission
September 25, 2023: Paper acceptance notification
October 22, 2023: Workshop date
Submission Guidelines
All submissions will be peer reviewed (double-blind) by the program committee and judged by their relevance to the workshop, especially to the main themes identified above, and their potential to generate discussion. All submission must be written in English and formatted according to the latest ACM SIG proceedings template available at http://www.acm.org/publications/proceedings-template. ("sigconf" proceedings template)
The workshop proceedings will be purely digital and non-archival.
The workshop follows a double-blind reviewing process.
We invite research contributions, position, demo and opinion papers. Submissions must either be short (at most 4 pages) or full papers (at most 9 pages). References do not count against the page limit. We also allow for an unlimited number of pages for appendices in the same PDF.
We encourage but do not require authors to release any code and/or datasets associated with their paper.
Invited Speakers
Heng Ji is a professor at Computer Science Department, and an affiliated faculty member at Electrical and Computer Engineering Department and Coordinated Science Laboratory of University of Illinois Urbana-Champaign. She is an Amazon Scholar, and the Founding Director of Amazon-Illinois Center on AI for Interactive Conversational Experiences (AICE). She received her B.A. and M. A. in Computational Linguistics from Tsinghua University, and her M.S. and Ph.D. in Computer Science from New York University. Her research interests focus on Natural Language Processing, especially on Multimedia Multilingual Information Extraction, Knowledge-enhanced Large Language Models, Knowledge-driven Generation and Conversational AI. She was selected as "Young Scientist" and a member of the Global Future Council on the Future of Computing by the World Economic Forum in 2016 and 2017. She was named as part of Women Leaders of Conversational AI (Class of 2023) by Project Voice. The awards she received include "AI's 10 to Watch" Award by IEEE Intelligent Systems in 2013, NSF CAREER award in 2009, Best Paper awards at ICDM2013 and SDM2013, Best Demo Paper Awards at ACL2020 and NAACL 2021, Google Research Award in 2009 and 2014, IBM Watson Faculty Award in 2012 and 2014 and Bosch Research Award in 2014-2018.
Chenlei (Edward) Guo is a Director at Amazon, where he serves as the head of the Self-learning and End-to-End Routing (SEER) division within the Artificial General Intelligence (AGI) org. In his role, Edward and his team are at the forefront of pioneering self-learning technologies, a critical component in empowering Amazon’s conversational agent, Alexa, to continuously evolve. Their mission includes learning from customer feedback, correcting defects, and tailoring customer experiences through personalization techniques. Before his tenure at Amazon, Edward is a Principal Manager at Microsoft, where he led a team focused on crafting ranking solutions for diverse platforms, including web search (Bing), entity graph (Satori), and O365 applications (People Relevance). Edward received the B.S. degree and M.S. degree in electronic engineering from Fudan University, Shanghai, China, in 2005 and 2008. He also received the M.S degree in computer engineering from Carnegie Mellon University, Pittsburgh, PA, in 2009. He has published 35 technical papers in refereed journal and conference proceedings and is the inventor of over 30 issued/pending patents.
Misha Sra is the John and Eileen Gerngross Assistant Professor of Computer Science at the University of California, Santa Barbara where she directs the Human-AI Integration Lab in the Computer Science department at UCSB. Misha received her PhD from the MIT Media Lab in 2018, advised by Prof. Pattie Maes in the Fluid Interfaces Group. She has published at the most selective HCI, VR, and machine learning venues such as CHI, UIST, VRST, AAAI, and CVPR where she received four best paper awards and honorable mentions. From 2014-2015, she was a Robert Wood Johnson Foundation wellbeing research fellow at the Media Lab. In spring 2016, she received the Silver Award in the annual Edison Awards Global Competition that honors excellence in human-centered design and innovation. MIT selected her as an EECS Rising Star in 2018. In 2023 she was awarded an NSF CAREER Award for her work in Human-AI Interaction Design. Her research has received extensive media coverage from leading media outlets (e.g., from Engadget, UploadVR, MIT Tech Review) and has drawn the attention of industry research, such as Toyota Research, Samsung Research, and Unity 3D.
Jianmo Ni is a senior software engineer at Google DeepMind, where he worked on the intersection of natural language understanding and recommender systems. He has developed Sentence T5, Promptagator and Differentiable Search Index to improve retrieval systems by bridging embedding models with large language models (LLMs). Prior to Google, he obtained his Ph.D. from University of California San Diego, where his research focused on personalized machine learning.
Industry Panel
Michelle Zhou is a co-founder and CEO of Juji, Inc., an Artificial Intelligence (AI) company that powers Cognitive AI Assistants in the form of chatbots. She is an expert in the field of Human-Centered AI, an interdisciplinary area that intersects AI and Human-Computer Interaction (HCI). Zhou has authored more than 100 publications and 45 patent applications on subjects including conversational AI, personality analytics, and interactive visual analytics of big data. Earlier in her career, she spent 15 years at IBM Research and the IBM Watson Group, where she managed the research and development of Human-Centered AI technologies and solutions, including IBM Watson Personality Insights. Zhou serves as Editor-in-Chief of ACM Transactions on Interactive Intelligent Systems (TiiS) and an Associate Editor of ACM Transactions on Intelligent Systems and Technology (TIST), and was formerly the Steering Committee Chair for the ACM International Conference Series on Intelligent User Interfaces. She received a Ph.D. in Computer Science from Columbia University and is an ACM Distinguished Member.
Yinglong Xia is an applied research scientist and an uber technical lead in Meta AI, collaborating with multiple teams on personalized recommendation systems, developing cutting edge ML techniques to connect people to who and what matter most. Prior to that, he was the Chief Architect of AI and a manager in Futurewei Technologies, leading a large global team on building a Cloud AI platform. Before that, he was a technical lead in IBM T.J. Watson Research Center. He is active in professional communities, served as a director on the Board of the Linked Data Benchmark Council (LDBC), a member of the Standardization committee of the IEEE Big Data Initiative, a representative in Linux Foundation, an associate Editor for IEEE TKDE and TBD, and a CRA/NSF Computing Innovation Fellow (CIFellow). He was a general co-chair of IEEE HiPC’18, a co-founder of Deep Learning on Graph (DLG) in KDD’23/AAAI’23, a Senior PC for KDD’23 and CIKM’23, etc. He publishes extensively with 90+ technical papers and 30+ patents.
Ruhi Sarikaya is a VP at Amazon. He built and is leading the Intelligence Decisions organization, which is one of the three pillars of Alexa AI. With his team, he has been building core AI capabilities around ranking, relevance, natural language understanding, dialog management, contextual understanding, personalization, self-learning, metrics and analytics for Alexa. Prior to that, he was a principal science manager and the founder of the language understanding and dialog systems group at Microsoft between 2011 and 2016. His group has built the language understanding and dialog management capabilities of Cortana, Xbox One, and the underlying platform. Before Microsoft, he was a research staff member and team lead in the Human Language Technologies Group at the IBM T.J. Watson Research Center for ten years. He received his BS degree from Bilkent University, MS degree from Clemson University, and Ph.D. degree from Duke University, all in electrical and computer engineering. He has published over 130 technical papers in refereed journal and conference proceedings and is the inventor of over 80 issued/pending patents. Dr. Sarikaya has served in the IEEE SLTC, the general co-chair of IEEE SLT'12, publicity chair of IEEE ASRU'05, and associate editor of IEEE Trans. on Audio, Speech and Language Processing and IEEE Signal Processing Letters. He has given keynotes in major AI, Web and language technology conferences. Dr. Sarikaya is an IEEE Fellow.
Organizing Committee
- Zheng Chen (Amazon)
- Ziyan Jiang (Amazon)
- Fan Yang (Amazon)
- Zhankui He (UC San Diego)
- Yupeng Hou (UC San Diego)
- Eunah Cho (Amazon)
- Julian McAuley (UC San Diego)
- Aram Galstyan (Amazon & USC ISI)
- Xiaohua Hu (Drexel University)
- Jie Yang (Delft University of Technology)