102 citations · 609 across the 64 of their papers we have counts for
7 papers · 1 filter
When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
Hyeong Kyu Choi, Xiaojin Zhu, Sharon Li
Multi-agent debate (MAD) aims to improve large language model (LLM) reasoning by letting multiple agents exchange answers and then aggregate their opinions. Yet recent studies reve…
CHARTOM: A Visual Theory-of-Mind Benchmark for LLMs on Misleading Charts
Shubham Bharti, Shiyun Cheng, Jihyun Rho +5
We introduce CHARTOM, a visual theory-of-mind benchmark designed to evaluate multimodal large language models' capability to understand and reason about misleading data visualizati…
The Delusional Hedge Algorithm as a Model of Human Learning from Diverse Opinions
Yun-Shiuan Chuang, Jerry Zhu, Timothy T. Rogers
Whereas cognitive models of learning often assume direct experience with both the features of an event and with a true label or outcome, much of everyday learning arises from heari…
Learning interactions to boost human creativity with bandits and GPT-4
Ara Vartanian, Xiaoxi Sun, Yun-Shiuan Chuang +3
This paper considers how interactions with AI algorithms can boost human creative thought. We employ a psychological task that demonstrates limits on human creativity, namely seman…
Program Synthesis from Visual Specification
Evan Hernandez, Ara Vartanian, Xiaojin Zhu
Program synthesis is the process of automatically translating a specification into computer code. Traditional synthesis settings require a formal, precise specification. Motivated…
Analysis of a Design Pattern for Teaching with Features and Labels
Christopher Meek, Patrice Simard, Xiaojin Zhu
We study the task of teaching a machine to classify objects using features and labels. We introduce the Error-Driven-Featuring design pattern for teaching using features and labels…
Robust Spatio-Temporal Signal Recovery from Noisy Counts in Social Media
Jun-Ming Xu, Aniruddha Bhargava, Robert Nowak +1
Many real-world phenomena can be represented by a spatio-temporal signal: where, when, and how much. Social media is a tantalizing data source for those who wish to monitor such si…