no code implementations • 30 Oct 2023 • Noah Ziems, Gang Liu, John Flanagan, Meng Jiang
Finally, we show LLM generated decision tree explanations correlate highly with human ratings of readability, quality, and use of background knowledge while simultaneously providing better understanding of decision boundaries.
no code implementations • 8 Jul 2023 • Hy Dang, Bang Nguyen, Noah Ziems, Meng Jiang
Our paper investigates the use of discourse embedding techniques to develop a community recommendation system that focuses on mental health support groups on social media.
1 code implementation • 16 May 2023 • Noah Ziems, Wenhao Yu, Zhihan Zhang, Meng Jiang
To overcome this limitation, recent autoregressive search engines replace the dual-encoder architecture by directly generating identifiers for relevant documents in the candidate pool.
no code implementations • 1 Oct 2022 • Usama Nadeem, Noah Ziems, Shaoen Wu
In an effort to improve the performance of code search, we have investigated docid representation strategies, impact of tokenization on docid structure, and dataset sizes on overall code search performance.
no code implementations • 6 May 2021 • Noah Ziems, Shaoen Wu
Detecting security vulnerabilities in software before they are exploited has been a challenging problem for decades.
no code implementations • 6 May 2021 • Noah Ziems, Shaoen Wu, Jim Norman
Primary Hyperparathyroidism(PHPT) is a relatively common disease, affecting about one in every 1, 000 adults.