SOTAVerified

Intent Detection

Intent Detection is a task of determining the underlying purpose or goal behind a user's search query given a context. The task plays a significant role in search and recommendations. A traditional approach for intent detection implies using an intent detector model to classify user search query into predefined intent categories, given a context. One of the key challenges of the task implies identifying user intents for cold-start sessions, i.e., search sessions initiated by a non-logged-in or unrecognized user.

Source: Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers

Papers

Showing 1–25 of 330 papers

TitleStatusHype
Flippi: End To End GenAI Assistant for E-Commerce—0
An Interdisciplinary Review of Commonsense Reasoning and Intent Detection—0
Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation—0
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting FrameworkCode0
Building a Few-Shot Cross-Domain Multilingual NLU Model for Customer Care—0
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation—0
Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models—0
Learning Multimodal AI Algorithms for Amplifying Limited User Input into High-dimensional Control SpaceCode0
Enhanced Urdu Intent Detection with Large Language Models and Prototype-Informed Predictive Pipelines—0
Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling—0
Fine-Grained Behavior and Lane Constraints Guided Trajectory Prediction Method—0
Intelligent Framework for Human-Robot Collaboration: Dynamic Ergonomics and Adaptive Decision-Making—0
Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings—0
Towards Refining Developer Questions using LLM-Based Named Entity Recognition for Developer Chatroom Conversations—0
Intention Recognition in Real-Time Interactive Navigation MapsCode0
PSCon: Product Search Through ConversationsCode0
On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response Generation—0
Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent DetectionCode0
Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case StudyCode0
Fitting Different Interactive Information: Joint Classification of Emotion and Intention—0
Meta-Reflection: A Feedback-Free Reflection Learning Framework—0
HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation—0
Evaluating Pixel Language Models on Non-Standardized Languages—0
Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning—0
Towards Intention Recognition for Robotic Assistants Through Online POMDP Planning—0
Show:102550
← PrevPage 1 of 14Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Bi-model with decoderAccuracy98.99—Unverified
2Transformer-CapsuleAccuracy98.89—Unverified
3Attention Encoder-Decoder NNAccuracy98.43—Unverified
4Joint model with recurrent slot label contextAccuracy98.4—Unverified
5CTRANAccuracy98.07—Unverified
6Joint BERT + CRFAccuracy97.9—Unverified
7SF-IDAccuracy97.76—Unverified
8SF-ID (BLSTM) networkAccuracy97.76—Unverified
9JointBERT-CAEAccuracy97.5—Unverified
10Joint BERTAccuracy97.5—Unverified
#ModelMetricClaimedVerifiedStatus
1SSRANAccuracy98.4—Unverified
2BiSLUAccuracy97.8—Unverified
3DGIFAccuracy97.8—Unverified
4Co-guiding NetAccuracy97.7—Unverified
5TFMNAccuracy97.7—Unverified
6TFMN (PACL)Accuracy97.4—Unverified
7MISCAAccuracy97.3—Unverified
8Uni-MISAccuracy97.2—Unverified
9SLIMAccuracy97.2—Unverified
10UGENAccuracy96.9—Unverified
#ModelMetricClaimedVerifiedStatus
1DGIFAccuracy83.3—Unverified
2UGENAccuracy83—Unverified
3TFMN (PACL)Accuracy82.9—Unverified
4SLIM (PACL)Accuracy81.9—Unverified
5BiSLUAccuracy81.5—Unverified
6TFMNAccuracy79.8—Unverified
7RoBERTa (PACL)Accuracy79.1—Unverified
8Co-guiding NetAccuracy79.1—Unverified
9Uni-MISAccuracy78.5—Unverified
10SLIMAccuracy78.3—Unverified
#ModelMetricClaimedVerifiedStatus
1CTRANAccuracy99.42—Unverified
2Stack-Propagation (+BERT)Accuracy99—Unverified
3JointBERT-CAEAccuracy98.3—Unverified
4AGIFAccuracy98.1—Unverified
5LIDSNetAccuracy98—Unverified
6Stack-PropagationAccuracy98—Unverified
7SF-IDAccuracy97.43—Unverified
8SF-ID (BLSTM) networkAccuracy97.43—Unverified
9Capsule-NLUAccuracy97.3—Unverified
10Slot-Gated BLSTM with AttensionAccuracy97—Unverified
#ModelMetricClaimedVerifiedStatus
1plain-LSTMF10.89—Unverified
2linear-NgramsF10.87—Unverified
3glove-LSTMF10.86—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)94.42—Unverified
2OCaTS (kNN-GPT-4)Accuracy (%)82.7—Unverified
#ModelMetricClaimedVerifiedStatus
1JointBERT-CAEIntent Accuracy97.7—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)89.79—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)84.01—Unverified
#ModelMetricClaimedVerifiedStatus
1CM-NetAcc94.56—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)97.12—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)94.84—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)92.62—Unverified
#ModelMetricClaimedVerifiedStatus
1MIDASAccuracy94.27—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)92.57—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)87.41—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-Large + ICDAAccuracy (%)82.45—Unverified
#ModelMetricClaimedVerifiedStatus
1MIDASAccuarcy85.02—Unverified
#ModelMetricClaimedVerifiedStatus
1General SLU Model w/ ProfileAccuracy0.85—Unverified