Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition

ACL ARR 2025 May Submission6521 Authors

Abstract:

Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development.
While massive, datacenter-based, multi-modal large language models (MLLMs) possess greater capacity to handle the complexities of such sequences, smaller models which can run on-device to provide a privacy-preserving, low-cost, and low-latency user experience, struggle with accurate intent inference.
We address these limitations by introducing a novel decomposed approach: first, we perform structured interaction summarization, capturing key information from each user action. Second, we perform intent extraction using a fine-tuned model operating on the aggregated summaries.
This method improves intent understanding in resource-constrained models, even surpassing the base performance of large MLLMs.

Paper Type: Long

Research Area: Generation

Research Area Keywords: efficient models, model architectures, inference methods, UI-to-text generation

Contribution Types: Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 6521