← Search

Ahmed Elshabrawy

2 accepted papers

2025

Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning

NAACL 2025findings

While Large Language Models (LLMs) exhibit remarkable capabilities in zero-shot and few-shot scenarios, they often require computationally prohibitive sizes. Conversely, smaller Masked Language Models (MLMs) like BERT and RoBERTa achieve state-of-the-art results through fine-tuning but struggle with…

Cited by 1SourcePDFScholar
2025

Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models

ACL 2025finding

Large Language Models (LLMs) excel in zero-shot and few-shot tasks, but achieving similar performance with encoder-only models like BERT and RoBERTa has been challenging due to their architecture. However, encoders offer advantages such as lower computational and memory costs. Recent work adapts the…