Alvin Chen 陳柏駿

Salvete omnes!

I’m a second year Master’s student at CU Boulder in the CLASIC program; most of my research is done with the BLAST Group where I’ve been working on developing tools to support qualitative research.

I’m primarily interested in the intersection of NLP and HCI, specifically in terms of (1) researching human-in-the-loop methods that reliably incorporate expert knowledge, (2) developing interactive systems that facilitate human-AI teaming, and (3) evaluating the impact of these tools in tasks where ground truth is inaccessible. While I’m interested in exploring these interests across a broad range of qualitative data, my previous research has focused on social media datasets used in Computational Social Science.

Previously, I was an Associate Manager at Johnson & Johnson in the Data Intelligence team. Extracting insights from messy sales data and designing dashboards to streamline communication informed my decision to pivot towards a data and engineering-centric career. Combined with my passion for linguistics (fluent in English, Mandarin, and French), designing NLP systems comes naturally to me.

Here you’ll find my publications as well as my projects which I use to familiarize myself with existing machine learning methods.

Thanks for visiting my page, feel free to contact me via email, valete!

news

Jan 15, 2024	I built a Convolutional Neural Network in NumPy that performs at TensorFlow levels!
Dec 11, 2023	I implemented an Irony Detector for tweets that outperforms SOTA!

selected publications

Studying the Effects of Collaboration in Interactive Theme Discovery Systems

Alvin Po-Chun Chen, Dananjay Srinivas, Alexandra Barry , and 2 more authors

2024

Abs HTML

NLP-assisted solutions have gained considerable traction to support qualitative data analysis. However, there does not exist a unified evaluation framework that can account for the many different settings in which qualitative researchers may employ them. In this paper, we take a first step in this direction by proposing an evaluation framework to study the way in which different tools may result in different outcomes depending on the collaboration strategy employed. Specifically, we study the impact of synchronous vs. asynchronous collaboration using two different NLP-assisted qualitative research tools and present a comprehensive analysis of significant differences in the consistency, cohesiveness, and correctness of their outputs.
Mothman at SemEval-2024 Task 9: An Iterative System for Chain-of-Thought Prompt Optimization

Alvin Po-Chun Chen, Ray Groshan, and Sean Von Bayern

In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024) , Jun 2024

Abs HTML

Extensive research exists on the performance of large language models on logic-based tasks, whereas relatively little has been done on their ability to generate creative solutions on lateral thinking tasks. The BrainTeaser shared task tests lateral thinking and uses adversarial datasets to prevent memorization, resulting in poor performance for out-of-the-box models. We propose a system for iterative, chain-of-thought prompt engineering which optimizes prompts using human evaluation. Using this shared task, we demonstrate our system’s ability to significantly improve model performance by optimizing prompts and evaluate the input dataset.