Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.04392 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911982258487296 |
|---|---|
| author | Yao, Yiqun Ma, Wenjia Fang, Xuezhi Jiang, Xin Li, Xiang Meng, Xuying Han, Peng Li, Jing Sun, Aixin Wang, Yequan |
| author_facet | Yao, Yiqun Ma, Wenjia Fang, Xuezhi Jiang, Xin Li, Xiang Meng, Xuying Han, Peng Li, Jing Sun, Aixin Wang, Yequan |
| contents | Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications. Current methods typically employ constrained decoding with rule-based automata or fine-tuning with manually crafted format instructions, both of which struggle with open-domain format requirements. To address this limitation, we introduce a novel framework for controlled generation in LLMs, leveraging user-provided, one-shot QA pairs. This study investigates LLMs' capabilities to follow open-domain, one-shot constraints and replicate the format of the example answers. We observe that this is a non-trivial problem for current LLMs. We also develop a dataset collection methodology for supervised fine-tuning that enhances the open-domain format control of LLMs without degrading output quality, as well as a benchmark on which we evaluate both the helpfulness and format correctness of LLM outputs. The resulting datasets, named OIFC-SFT, along with the related code, will be made publicly available at https://github.com/cofe-ai/OIFC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04392 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Open-domain Implicit Format Control for Large Language Model Generation Yao, Yiqun Ma, Wenjia Fang, Xuezhi Jiang, Xin Li, Xiang Meng, Xuying Han, Peng Li, Jing Sun, Aixin Wang, Yequan Computation and Language Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications. Current methods typically employ constrained decoding with rule-based automata or fine-tuning with manually crafted format instructions, both of which struggle with open-domain format requirements. To address this limitation, we introduce a novel framework for controlled generation in LLMs, leveraging user-provided, one-shot QA pairs. This study investigates LLMs' capabilities to follow open-domain, one-shot constraints and replicate the format of the example answers. We observe that this is a non-trivial problem for current LLMs. We also develop a dataset collection methodology for supervised fine-tuning that enhances the open-domain format control of LLMs without degrading output quality, as well as a benchmark on which we evaluate both the helpfulness and format correctness of LLM outputs. The resulting datasets, named OIFC-SFT, along with the related code, will be made publicly available at https://github.com/cofe-ai/OIFC. |
| title | Open-domain Implicit Format Control for Large Language Model Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.04392 |