Pith. sign in

REVIEW 5 cited by

Exploring Zero and Few-shot Techniques for Intent Classification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.07157 v1 pith:M5GUS5UI submitted 2023-05-11 cs.CL cs.AI

Soham Parikh , Quaizar Vohra , Prashil Tumbade , Mitul Tiwari This is my paper · ORCID
classification cs.CLcs.AI
keywords intentclassificationmodelsapproachesconstraintcustomersdescriptionsdifferent
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Conversational NLU providers often need to scale to thousands of intent-classification models where new customers often face the cold-start problem. Scaling to so many customers puts a constraint on storage space as well. In this paper, we explore four different zero and few-shot intent classification approaches with this low-resource constraint: 1) domain adaptation, 2) data augmentation, 3) zero-shot intent classification using descriptions large language models (LLMs), and 4) parameter-efficient fine-tuning of instruction-finetuned language models. Our results show that all these approaches are effective to different degrees in low-resource settings. Parameter-efficient fine-tuning using T-few recipe (Liu et al., 2022) on Flan-T5 (Chang et al., 2022) yields the best performance even with just one sample per intent. We also show that the zero-shot method of prompting LLMs using intent descriptions

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling

    cs.CL 2025-04 conditional novelty 6.0 of 10

    GRPO reinforcement learning with reward-based curriculum sampling improves generalization to unseen intents in task-oriented dialogue, outperforming supervised fine-tuning on two datasets.

  2. Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification

    cs.CL 2024-12 conditional novelty 6.0 of 10

    Dynamic, per-query rewriting of intent labels by an LLM improves few-shot dialogue intent classification accuracy compared to retrieval ICL with original labels.

  3. GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets

    cs.CL 2025-04 conditional novelty 5.0 of 10

    SFT plus RL with post-hoc selection of the best training and inference prompts improves generative text classification accuracy by about 3.5% relative to a naive SFT baseline.

  4. Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes

    cs.CL 2026-08 conditional novelty 4.0 of 10

    Statistical classifiers built on LLM activation norms and coordinates match or beat trained MLP heads on coarse intent routing and resist camouflage better, while MLPs win on fine-grained subfield distinctions.

  5. Comprehensive Audio Query Handling System with Integrated Expert Models and Contextual Understanding

    eess.AS 2024-12 reject novelty 4.0 of 10

    A modular audio chatbot using a BERT intent router, expert audio models, and a 3.8B LLM over audio-event metadata matches 7B-8B audio-language models on MMAU sound and beats several of them on custom temporal QA.

Pith tools