A training-free LLM prompting pipeline with semantic few-shot retrieval and feedback of discovered intents outperforms trained baselines on few-shot intent discovery benchmarks.
IDAS: Intent Discovery with Abstractive Summarization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Intent discovery is the task of inferring latent intents from a set of unlabeled utterances, and is a useful step towards the efficient creation of new conversational agents. We show that recent competitive methods in intent discovery can be outperformed by clustering utterances based on abstractive summaries, i.e., "labels", that retain the core elements while removing non-essential information. We contribute the IDAS approach, which collects a set of descriptive utterance labels by prompting a Large Language Model, starting from a well-chosen seed set of prototypical utterances, to bootstrap an In-Context Learning procedure to generate labels for non-prototypical utterances. The utterances and their resulting noisy labels are then encoded by a frozen pre-trained encoder, and subsequently clustered to recover the latent intents. For the unsupervised task (without any intent labels) IDAS outperforms the state-of-the-art by up to +7.42% in standard cluster metrics for the Banking, StackOverflow, and Transport datasets. For the semi-supervised task (with labels for a subset of intents) IDAS surpasses 2 recent methods on the CLINC benchmark without even using labeled data.
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
IntentGPT: Few-shot Intent Discovery with Large Language Models
A training-free LLM prompting pipeline with semantic few-shot retrieval and feedback of discovered intents outperforms trained baselines on few-shot intent discovery benchmarks.