Papers › Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Sungjin Lee, Devamanyu Hazarika, Mahdi Namazifar, Di Jin, Yang Liu, Dilek Hakkani-Tur
This work focuses on in-context data augmentation for intent detection. Having found that augmentation via in-context prompting of large pre-trained language models (PLMs) alone does not improve performance, we introduce a novel approach based on PLMs and pointwise V-information (PVI), a metric that can measure the usefulness of a datapoint for training a model. Our method first fine-tunes a PLM on a small seed of training data and then synthesizes new datapoints - utterances that correspond to given intents. It then employs intent-aware filtering, based on PVI, to remove datapoints that are not helpful to the downstream intent classifier. Our method is thus able to leverage the expressive power of large language models to produce diverse training data. Empirical results demonstrate that our method can produce synthetic training data that achieve state-of-the-art performance on three challenging intent detection datasets under few-shot settings (1.28% absolute improvement in 5-shot and 1.18% absolute in 10-shot, on average) and perform on par with the state-of-the-art in full-shot settings (within 0.01% absolute, on average).
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Intent Detection | BANKING77 | RoBERTa-Large + ICDA | Accuracy (%) | 94.42 | #1 of 2 | Archive leaderboard | report |
| Intent Detection | BANKING77 10-shot | RoBERTa-Large + ICDA | Accuracy (%) | 89.79 | #1 of 1 | Archive leaderboard | report |
| Intent Detection | BANKING77 5-shot | RoBERTa-Large + ICDA | Accuracy (%) | 84.01 | #1 of 1 | Archive leaderboard | report |
| Intent Detection | CLINC150 | RoBERTa-Large + ICDA | Accuracy (%) | 97.12 | #1 of 1 | Archive leaderboard | report |
| Intent Detection | CLINC150 10-shot | RoBERTa-Large + ICDA | Accuracy (%) | 94.84 | #1 of 1 | Archive leaderboard | report |
| Intent Detection | CLINC150 5-shot | RoBERTa-Large + ICDA | Accuracy (%) | 92.62 | #1 of 1 | Archive leaderboard | report |
| Intent Detection | HWU64 | RoBERTa-Large + ICDA | Accuracy (%) | 92.57 | #1 of 1 | Archive leaderboard | report |
| Intent Detection | HWU64 10-shot | RoBERTa-Large + ICDA | Accuracy (%) | 87.41 | #1 of 1 | Archive leaderboard | report |
| Intent Detection | HWU64 5-shot | RoBERTa-Large + ICDA | Accuracy (%) | 82.45 | #1 of 1 | Archive leaderboard | report |
| Text Classification | BANKING77 | RoBERTa-Large + ICDA | Accuracy | 94.42 | #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