Papers › ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open...

ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection

25 Aug 2023arXiv:2308.13517archive 2025-07-28

Yihao Fang, Xianzhi Li, Stephen W. Thomas, Xiaodan Zhu

Open intent detection, a crucial aspect of natural language understanding, involves the identification of previously unseen intents in user-generated text. Despite the progress made in this field, challenges persist in handling new combinations of language components, which is essential for compositional generalization. In this paper, we present a case study exploring the use of ChatGPT as a data augmentation technique to enhance compositional generalization in open intent detection tasks. We begin by discussing the limitations of existing benchmarks in evaluating this problem, highlighting the need for constructing datasets for addressing compositional generalization in open intent detection tasks. By incorporating synthetic data generated by ChatGPT into the training process, we demonstrate that our approach can effectively improve model performance. Rigorous evaluation of multiple benchmarks reveals that our method outperforms existing techniques and significantly enhances open intent detection capabilities. Our findings underscore the potential of large language models like ChatGPT for data augmentation in natural language understanding tasks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

fangyihao/gptaug officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationIntent DetectionNatural Language UnderstandingOpen Intent Detection

Datasets

Introduced by this paper, per the archive.

Banking_CGOOS_CGStackOverflow_CG

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Intent Detection Banking_CG ADB+GPTAUG-F4 F1 Score 66.45 #1 of 1 Archive leaderboard report
Open Intent Detection OOS_CG ADB+GPTAUG-F4 F1 Score 56.18 #1 of 1 Archive leaderboard report
Open Intent Detection StackOverflow_CG DA-ADB F1 Score 77.77 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections