David A. Smith — accepted AI-conference papers

2025

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training

Jaydeep Borkar, Matthew Jagielski, Katherine Lee, Niloofar Mireshghallah, David A. Smith, Christopher A. Choquette-Choo

ACL 2025finding

Due to the sensitive nature of personally identifiable information (PII), its owners may have the authority to control its inclusion or request its removal from large-language model (LLM) training. Beyond this, PII may be added or removed from training datasets due to evolving dataset curation techn…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Through the Lens of History: Methods for Analyzing Temporal Variation in Content and Framing of State-run Chinese Newspapers

Shijia Liu, David A. Smith

NAACL 2025long

State-run Chinese newspapers are believed to strategically select and frame news articles to align with the shifting political tides of the country. This paper describes methods to quantify these changes in content and framing over time. Looking at more than 50 years of articles from the People’s Da…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Detecting Syntactic Change with Pre-trained Transformer Models

Liwen Hou, David A. Smith

EMNLP 2023long findings

We investigate the ability of Transformer-based language models to find syntactic differences between the English of the early 1800s and that of the late 1900s. First, we show that a fine-tuned BERT model can distinguish between text from these two periods using syntactic information only; to show t…

Cited by 0 Source ↗Scholar ↗