Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.12445 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912160633847808 |
|---|---|
| author | Lin, Zihao Wang, Zichao Pan, Yuanting Manjunatha, Varun Rossi, Ryan Lau, Angela Huang, Lifu Sun, Tong |
| author_facet | Lin, Zihao Wang, Zichao Pan, Yuanting Manjunatha, Varun Rossi, Ryan Lau, Angela Huang, Lifu Sun, Tong |
| contents | Suggested questions (SQs) provide an effective initial interface for users to engage with their documents in AI-powered reading applications. In practical reading sessions, users have diverse backgrounds and reading goals, yet current SQ features typically ignore such user information, resulting in homogeneous or ineffective questions. We introduce a pipeline that generates personalized SQs by incorporating reader profiles (professions and reading goals) and demonstrate its utility in two ways: 1) as an improved SQ generation pipeline that produces higher quality and more diverse questions compared to current baselines, and 2) as a data generator to fine-tune extremely small models that perform competitively with much larger models on SQ generation. Our approach can not only serve as a drop-in replacement in current SQ systems to immediately improve their performance but also help develop on-device SQ models that can run locally to deliver fast and private SQ experience. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12445 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Persona-SQ: A Personalized Suggested Question Generation Framework For Real-world Documents Lin, Zihao Wang, Zichao Pan, Yuanting Manjunatha, Varun Rossi, Ryan Lau, Angela Huang, Lifu Sun, Tong Computation and Language Suggested questions (SQs) provide an effective initial interface for users to engage with their documents in AI-powered reading applications. In practical reading sessions, users have diverse backgrounds and reading goals, yet current SQ features typically ignore such user information, resulting in homogeneous or ineffective questions. We introduce a pipeline that generates personalized SQs by incorporating reader profiles (professions and reading goals) and demonstrate its utility in two ways: 1) as an improved SQ generation pipeline that produces higher quality and more diverse questions compared to current baselines, and 2) as a data generator to fine-tune extremely small models that perform competitively with much larger models on SQ generation. Our approach can not only serve as a drop-in replacement in current SQ systems to immediately improve their performance but also help develop on-device SQ models that can run locally to deliver fast and private SQ experience. |
| title | Persona-SQ: A Personalized Suggested Question Generation Framework For Real-world Documents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.12445 |