Papers by Danielle Cohen
Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition (2025.emnlp-main)
Copied to clipboard
Danielle Cohen, Yoni Halpern, Noam Kahlon, Joel Oren, Omri Berkovitch, Sapir Caduri, Ido Dagan, Anatoly Efros
| Challenge: | Large multi-modal large language models are good at extracting user intents from UI sequences, but smaller models struggle with accurate intent inference. |
| Approach: | They propose a decomposed approach for extracting user intent from small models . they perform structured interaction summarization and intent extraction using a fine-tuned model . |
| Outcome: | The proposed method surpasses the performance of large MLLMs in the intent extraction task. |