Symbol tuning improves in-context learning in language models
Jerry Wei, Le Hou, Andrew Lampinen, Xiangning Chen, Da Huang, Yi Tay, Xinyun Chen, Yifeng Lu, Denny Zhou, Tengyu Ma, Quoc Le
Abstract
We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., “positive/negative sentiment”) are replaced with arbitrary symbols (e.g., “foo/bar”). Symbol tuning leverages the intuition that when a model cannot use instructions or natural language labels to figure out a task, it must instead do so by learning the input-label mappings. We experiment with symbol tuning across PaLM models up to 540B parameters and observe benefits across various settings. First, symbol tuning boosts performance on unseen in-context learning tasks and is much more robust to underspecified prompts, such as those without instructions or without natural language labels. Second, symbol-tuned models are much stronger at algorithmic reasoning tasks, with up to 18.2% better performance on the List Functions benchmark and up to 15.3% better performance on the Simple Turing Concepts benchmark. Finally, symbol-tuned models show large improvements in following flipped-labels presented in-context, meaning that they are more capable of using in-context information to override prior knowledge.- Anthology ID:
- 2023.emnlp-main.61
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 968–979
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.61
- DOI:
- 10.18653/v1/2023.emnlp-main.61
- Cite (ACL):
- Jerry Wei, Le Hou, Andrew Lampinen, Xiangning Chen, Da Huang, Yi Tay, Xinyun Chen, Yifeng Lu, Denny Zhou, Tengyu Ma, and Quoc Le. 2023. Symbol tuning improves in-context learning in language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 968–979, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Symbol tuning improves in-context learning in language models (Wei et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2023.emnlp-main.61.pdf