JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning

Chang Gao, Wenxuan Zhang, Guizhen Chen, Wai Lam

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: instruction tuning, generalization, robustness, controllability

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Instruction tuning has emerged as a crucial process for harnessing the capabilities of large language models (LLMs) by providing explicit task instructions, leading to improved performance in various tasks. However, prevalent text-to-text instruction tuning (TextTuning) methods suffer from limitations in generalization, robustness, and controllability due to the ambiguity and lack of explicit structure in tasks. In this paper, we propose JsonTuning, a novel structure-to-structure approach for instruction tuning. By leveraging the versatility and structured nature of JSON to represent tasks, JsonTuning enhances generalization by helping the model understand essential task elements and their relations, improves robustness by minimizing ambiguity, and increases controllability by providing explicit control over the output. We conduct a comprehensive comparative study with diverse language models and evaluation benchmarks. Experimental results show that JsonTuning outperforms TextTuning in various applications, showcasing improved performance, adaptability, robustness, and controllability. By overcoming the limitations of TextTuning, JsonTuning demonstrates significant potential for more effective and reliable LLMs capable of handling diverse scenarios

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 7027