Publications (14)
When Bad Data Leads to Good Models
Kenneth Li, Yida Chen, Fernanda Viégas +1
In large language model (LLM) pretraining, data quality is believed to determine model quality. In this paper, we re-examine the notion of "quality" from the perspective of pre- an…
An AI-Resilient Text Rendering Technique for Reading and Skimming Documents
Ziwei Gu, Ian Arawjo, Kenneth Li +2
Readers find text difficult to consume for many reasons. Summarization can address some of these difficulties, but introduce others, such as omitting, misrepresenting, or hallucina…
Designing a Dashboard for Transparency and Control of Conversational AI
Yida Chen, Aoyu Wu, Trevor DePodesta +9
Conversational LLMs function as black box systems, leaving users guessing about why they see the output they do. This lack of transparency is potentially problematic, especially gi…
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Kenneth Li, Aspen K. Hopkins, David Bau +3
Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics,…
Towards Tokenized Human Dynamics Representation
Kenneth Li, Xiao Sun, Zhirong Wu +2
For human action understanding, a popular research direction is to analyze short video clips with unambiguous semantic content, such as jumping and drinking. However, methods for u…
Do Time Constraints Re-Prioritize Attention to Shapes During Visual Photo Inspection?
Yiyuan Yang, Kenneth Li, Fernanda Eliott +1
People's visual experiences of the world are easy to carve up and examine along natural language boundaries, e.g., by category labels, attribute labels, etc. However, it is more di…