Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Chang, Zhang, Wenxuan, Chen, Guizhen, Lam, Wai
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2310.02953
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913883501887488
author Gao, Chang
Zhang, Wenxuan
Chen, Guizhen
Lam, Wai
author_facet Gao, Chang
Zhang, Wenxuan
Chen, Guizhen
Lam, Wai
contents Instruction tuning is vital for enhancing the performance of large language models (LLMs), but existing text-to-text methods, referred to as TextTuning, struggle with issues such as generalization, robustness, and controllability due to their lack of explicit task structures. We introduce JsonTuning, a structure-to-structure approach that uses JSON structures to represent tasks. This method improves generalization by clarifying task elements and their relations, boosts robustness by minimizing ambiguity, and enhances controllability by allowing precise control over outputs. We conduct an extensive comparative analysis between JsonTuning and TextTuning using various language models and benchmarks. Our findings reveal that JsonTuning consistently surpasses TextTuning in terms of performance, robustness, and controllability across different scenarios. By overcoming the limitations of TextTuning, JsonTuning demonstrates significant potential for developing more effective and reliable LLMs capable of handling diverse scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2310_02953
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning
Gao, Chang
Zhang, Wenxuan
Chen, Guizhen
Lam, Wai
Computation and Language
Instruction tuning is vital for enhancing the performance of large language models (LLMs), but existing text-to-text methods, referred to as TextTuning, struggle with issues such as generalization, robustness, and controllability due to their lack of explicit task structures. We introduce JsonTuning, a structure-to-structure approach that uses JSON structures to represent tasks. This method improves generalization by clarifying task elements and their relations, boosts robustness by minimizing ambiguity, and enhances controllability by allowing precise control over outputs. We conduct an extensive comparative analysis between JsonTuning and TextTuning using various language models and benchmarks. Our findings reveal that JsonTuning consistently surpasses TextTuning in terms of performance, robustness, and controllability across different scenarios. By overcoming the limitations of TextTuning, JsonTuning demonstrates significant potential for developing more effective and reliable LLMs capable of handling diverse scenarios.
title JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning
topic Computation and Language
url https://arxiv.org/abs/2310.02953