James Zou

How much does your data exploration overfit? Controlling bias via information usage

2015 · arXiv (Cornell University)

Modern data is messy and high-dimensional, and it is often not clear a priori what are the right questions to ask. Instead, the analyst typically needs to use the data to search for interesting analyses …

Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials

2022 · Research Square

<title>Abstract</title> Prostate cancer is the most frequent cancer in men and a leading cause of cancer death. Determining a patient’s optimal therapy is a challenge, where oncologists must select a therapy with the highest likelihood …

New Evaluation Metrics Capture Quality Degradation due to LLM Watermarking

2023 · arXiv (Cornell University)

With the increasing use of large-language models (LLMs) like ChatGPT, watermarking has emerged as a promising approach for tracing machine-generated content. However, research on LLM watermarking often relies on simple perplexity or diversity-based measures to …

Mapping the Increasing Use of LLMs in Scientific Papers

2024 · arXiv (Cornell University)

Scientific publishing lays the foundation of science by disseminating research findings, fostering collaboration, encouraging reproducibility, and ensuring that scientific knowledge is accessible, verifiable, and built upon over time. Recently, there has been immense speculation about …

Mixture-of-Agents Enhances Large Language Model Capabilities

2024 · arXiv (Cornell University)

Recent advances in large language models (LLMs) demonstrate substantial capabilities in natural language understanding and generation tasks. With the growing number of LLMs, how to harness the collective expertise of multiple LLMs is an exciting …

RAPID: Reliable and efficient Automatic generation of submission rePorting checklists with Large language moDels

2025 · bioRxiv (Cold Spring Harbor Laboratory)

Abstract Importance Medical reporting guidelines are significant in improving the transparency, quality, and integrity of medical research, particularly in randomized clinical trials; adherence to these guidelines supports research interpretability and has direct implications for downstream …

Persistent Anti-Muslim Bias in Large Language Models

2021

It has been observed that large-scale language models capture undesirable societal biases, e.g. relating to race and gender; yet religious bias has been relatively unexplored. We demonstrate that GPT-3, a state-of-the-art contextual language model, captures …