REVIEW 6 cited by
IntentGPT: Few-shot Intent Discovery with Large Language Models
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
In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants. In these dialogues, it is important to identify user's goals automatically to resolve their needs promptly. This has necessitated the integration of models that perform Intent Detection. However, users' intents are diverse and dynamic, making it challenging to maintain a fixed set of predefined intents. As a result, a more practical approach is to develop a model capable of identifying new intents as they emerge. We address the challenge of Intent Discovery, an area that has drawn significant attention in recent research efforts. Existing methods need to train on a substantial amount of data for correctly identifying new intents, demanding significant human effort. To overcome this, we introduce IntentGPT, a novel training-free method that effectively prompts Large Language Models (LLMs) such as GPT-4 to discover new intents with minimal labeled data. IntentGPT comprises an \textit{In-Context Prompt Generator}, which generates informative prompts for In-Context Learning, an \textit{Intent Predictor} for classifying and discovering user intents from utterances, and a \textit{Semantic Few-Shot Sampler} that selects relevant few-shot examples and a set of known intents to be injected into the prompt. Our experiments show that IntentGPT outperforms previous methods that require extensive domain-specific data and fine-tuning, in popular benchmarks, including CLINC and BANKING, among others.
Forward citations
Cited by 6 Pith papers
-
OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis
OralAgent, a ReAct-style dental agent with 22 vision tools and a 134.8M-token textbook RAG corpus, reaches SOTA on MMOral-Uni, MMOral-OPG, and OralQA-ZH.
-
NILC: Discovering New Intents with LLM-assisted Clustering
NILC combines LLM-generated semantic centroids with hard-sample rewriting to improve new-intent clustering, but its 'consistent' superiority claim is contradicted on DBPedia.
-
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
An automated two-stage rewriting framework, IntentPrompt, bypasses LLM content guardrails with 80-98% success by turning harmful asks into declarative outlines.
-
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.
-
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.
-
A Computational Approach to Modeling Conversational Systems: Analyzing Large-Scale Quasi-Patterned Dialogue Flows
A dialogue-flow pipeline that embeds, clusters, labels, and prunes conversations into trees, evaluated with a semantic metric that largely reflects its own clustering choices.
Discussion (0). Continue with ORCID to comment.