Pith. sign in

REVIEW 14 cited by

Efficient Intent Detection with Dual Sentence Encoders

Not yet reviewed by Pith; the record is open.

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 2003.04807 v1 pith:MVBOOAS2 submitted 2020-03-10 cs.CL

classification cs.CL
keywords intentdetectiondetectorsannotateddualencodersexamplesfew-shot
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Building conversational systems in new domains and with added functionality requires resource-efficient models that work under low-data regimes (i.e., in few-shot setups). Motivated by these requirements, we introduce intent detection methods backed by pretrained dual sentence encoders such as USE and ConveRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that: 1) they outperform intent detectors based on fine-tuning the full BERT-Large model or using BERT as a fixed black-box encoder on three diverse intent detection data sets; 2) the gains are especially pronounced in few-shot setups (i.e., with only 10 or 30 annotated examples per intent); 3) our intent detectors can be trained in a matter of minutes on a single CPU; and 4) they are stable across different hyperparameter settings. In hope of facilitating and democratizing research focused on intention detection, we release our code, as well as a new challenging single-domain intent detection dataset comprising 13,083 annotated examples over 77 intents.

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 Pith papers

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

  1. BitNet Text Embeddings

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    BITEMBED trains 1.58-bit ternary-weight LLM embedders with contrastive pre-training, supervised distillation, and multi-precision output training, matching FP16 teachers within ~0.6 MMTEB points at ~2x CPU speed.

  2. Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Prompting LLMs for candidate labels and distilling them into a small model improves annotation accuracy and noise tolerance over single-label annotation.

  3. Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs

    cs.CL 2025-05 conditional novelty 6.0 of 10

    PaMA uses LLM-generated event patterns to align clusters with classes, improving H-score by up to 12.58% on event-centric GCD benchmarks while staying competitive on standard GCD datasets.

  4. Large Language Models in the Task of Automatic Validation of Text Classifier Predictions

    cs.CL 2025-05 conditional novelty 6.0 of 10

    LLM-based annotators using token-probability thresholds, RAG, and reasoning fine-tuning matched or exceeded human annotator quality on a proprietary 250-class intent-validation task.

  5. Next Token Perception Score: Analytical Assessment of your LLM Perception Skills

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A subspace-overlap score computed from frozen LLM representations and labels is proposed, with a bounding theorem in a linear setting and empirical correlations with linear probe accuracy and LoRA gains.

  6. Communication-Aware Knowledge Distillation for Federated LLM Fine-Tuning over Wireless Networks

    cs.LG 2025-09 conditional novelty 5.0 of 10

    A federated distillation scheme combining channel-aware Top-k logit sparsification, sparsity-aware aggregation, and LoRA projection alignment cuts communication by about 50% while improving fine-tuning accuracy in a G...

  7. Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Using BERT probabilities to shrink the label list in LLM prompts improves intent recognition in multi-party dialogues and cuts latency, though gains vary by model and dataset.

  8. Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework

    cs.CL 2025-06 conditional novelty 5.0 of 10

    CPP improves generalized intent discovery by using LLM-generated prototypes and verbalizers plus consistency and cross-prediction losses, reporting SOTA on Banking and CLINC without statistical validation.

  9. MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

    cs.AI 2025-05 conditional novelty 5.0 of 10

    MAPLE uses graph-influence scores to select and pseudo-label the most useful unlabeled examples, then adaptively chooses demonstrations per query, improving many-shot in-context learning with few human labels.

  10. 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.

  11. Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals

    cs.CL 2025-09 conditional novelty 4.0 of 10

    The ratio of agreement to disagreement between a small student model and an LLM correlates with the LLM's annotation accuracy across ten datasets and can heuristically select better models.

  12. Deep Learning Approaches for Multimodal Intent Recognition: A Survey

    cs.CL 2025-07 conditional novelty 4.0 of 10

    A survey of deep learning methods for intent recognition, tracing the field from unimodal text, audio, vision, and EEG approaches to multimodal fusion, alignment, knowledge-augmented, and multi-task models.

  13. LGAI-EMBEDDING-Preview Technical Report

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A Mistral-7B embedding model trained with in-context instructions, soft labels from an in-house retrieval pipeline, and margin-based hard-negative mining reports top-tier MTEB English v2 scores.

  14. Can Post-Training Quantization Benefit from an Additional QLoRA Integration?

    cs.CL 2025-02 conditional novelty 4.0 of 10

    Adding QLoRA on top of a 4-bit post-training quantized LLM improves task accuracy over quantization alone, and can match or beat full 16-bit fine-tuning on some tasks.

Pith tools