Sun | Mon | Tue | Wed | Thu | Fri | Sat |
---|---|---|---|---|---|---|
Xinyu Crystina Zhang (University of Waterloo) – “Information Seeking Beyond English”
12:00 pm
Xinyu Crystina Zhang (University of Waterloo) – “Information Seeking Beyond English”
@ Hackerman Hall B17
Mar 10 @ 12:00 pm – 1:15 pm
Abstract Pretrained language models have brought revolutionary progress to information-seeking in the English world. While the advance is exciting, how to transfer such progress into non-English, especially lower resource languages, presents new challenges that require[...]
|
Krithika Ramesh (JHU) – “Navigating Privacy in Language Models: A Brief Overview of Challenges and Solutions”
12:00 pm
Krithika Ramesh (JHU) – “Navigating Privacy in Language Models: A Brief Overview of Challenges and Solutions”
@ Hackerman Hall B17
Mar 14 @ 12:00 pm – 1:15 pm
Abstract With language models becoming increasingly embedded in our digital interactions, concerns over data privacy and information leakage are becoming more apparent. The lack of regulation and transparency in how pipelines involving LLMs collect and[...]
Niyati Bafna (JHU) – “Evaluating and Inducing Dialectal Robustness in Large Language Models”
12:00 pm
Niyati Bafna (JHU) – “Evaluating and Inducing Dialectal Robustness in Large Language Models”
@ Hackerman Hall B17
Mar 14 @ 12:00 pm – 1:15 pm
Abstract While state-of-the-art models for machine translation and natural language understanding perform well on high-resource members of (some of) the world’s language families, they degrade on closely-related languages, dialects, and variants of these languages, which[...]
|
|||||
Lisa Li (Stanford University) – “Controlling Language Models”
12:00 pm
Lisa Li (Stanford University) – “Controlling Language Models”
@ Hackerman Hall B17
Mar 24 @ 12:00 pm – 1:15 pm
Abstract Controlling language models is key to unlocking their full potential and making them useful for downstream tasks. Successfully deploying these models often requires both task-specific customization and rigorous auditing of their behavior. In this[...]
|
Aaron Goksalan (Cornell) – “Challenges and Opportunities in Open Generative Models”
12:00 pm
Aaron Goksalan (Cornell) – “Challenges and Opportunities in Open Generative Models”
@ Hackerman Hall B17
Mar 28 @ 12:00 pm – 1:15 pm
Abstract Open source generative models like OpenGPT2, BLOOM, and others have been pivotal in advancing AI technology. These models leverage extensive text data to achieve advanced linguistic capabilities. However, the trend towards proprietary tools and[...]
|
|||||