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
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.
Forward citations
Cited by 14 Pith papers
-
BitNet Text Embeddings
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.
-
Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation
Prompting LLMs for candidate labels and distilling them into a small model improves annotation accuracy and noise tolerance over single-label annotation.
-
Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs
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.
-
Large Language Models in the Task of Automatic Validation of Text Classifier Predictions
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.
-
Next Token Perception Score: Analytical Assessment of your LLM Perception Skills
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.
-
Communication-Aware Knowledge Distillation for Federated LLM Fine-Tuning over Wireless Networks
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...
-
Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations
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.
-
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework
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.
-
MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
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.
-
Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
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.
-
Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals
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.
-
Deep Learning Approaches for Multimodal Intent Recognition: A Survey
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.
-
LGAI-EMBEDDING-Preview Technical Report
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.
-
Can Post-Training Quantization Benefit from an Additional QLoRA Integration?
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.
Discussion (0). Sign in to comment.