David Heineman

Hey! I'm David πŸ‘‹

I'm a pre-doctoral young investigator at the Allen Institute for AI, working to improve language model pre-training and evaluation.


Research interests

I'm interested in understanding language model behavior. This includes fine-grained evaluation of LLM generation [1, 2], using measures of behavior to improve text generation [3], and interpreting language model behavior with existing theories of human cognition [4].

Previously, I completed my undergrad at Georgia Tech 🐝, where I was fortunate to be advised by Prof. Wei Xu and work with Yao Dou and Dr. Mounica Maddela. I've also spent a few summers as an intern at AWS and Patientco, a healthcare / fintech startup. I enjoy reading, hiking, and making homebrew nitrogen cold brew. β˜•οΈ ⛰️


Publications & Preprints βœ’οΈ

Improving Minimum Bayes Risk Decoding with Multi-Prompt [code]

David Heineman, Yao Dou, Wei Xu
EMNLP, 2024

Towards a Path Dependent Account of Category Fluency [code]

David Heineman, Reba Koenen, Sashank Varma
CogSci, 2024

Thresh 🌾: Unified, Customizable and Deployable Fine-Grained Text Evaluation [thresh.tools]

David Heineman, Yao Dou, Wei Xu
EMNLP Demo, 2023

Edit-level Simplification Evaluation using SALSA πŸ’ƒ [code/data, metric]

David Heineman, Yao Dou, Mounica Maddela, Wei Xu
EMNLP, 2023

LENS πŸ”Ž: A Learnable Evaluation Metric for Text Simplification

Mounica Maddela*, Yao Dou*, David Heineman, Wei Xu
ACL, 2023

* = equal contribution


What I've been building πŸ‘·

My past work 🌳

Recommendations

A few interesting corners of the internet I find worth checking out!

... to flip through


Games, Puzzles, and Computation by Erik Demaine

The Age of Surveillance Capitalism by Shoshana Zuboff

Society Must be Defended by Michel Foucault

GΓΆdel, Escher, Bach by Douglas Hofstadter


I also enjoy trying new coffee shops. Here's 50+ recommendations across Atlanta, that I visited during my undergrad.