Kathryn Ricci — accepted AI-conference papers

2026

Seq vs Seq: An Open Suite of Paired Encoders and Decoders

Orion Weller, Kathryn Ricci, Marc Marone, Antoine Chaffin, Dawn Lawrie, Benjamin Van Durme

ICLR 2026poster

The large language model (LLM) community focuses almost exclusively on decoder-only language models, since they are easier to use for text generation. However, a large subset of the community still uses encoder-only models for tasks such as classification or retrieval. Previous work has attempted to…

Cited by 0 Source ↗code ↗Scholar ↗

2023

Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling

Haw-Shiuan Chang, Ruei-Yao Sun, Kathryn Ricci, Andrew McCallum

ACL 2023long

Ensembling BERT models often significantly improves accuracy, but at the cost of significantly more computation and memory footprint. In this work, we propose Multi-CLS BERT, a novel ensembling method for CLS-based prediction tasks that is almost as efficient as a single BERT model. Multi-CLS BERT u…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗