GUI-ReRank: Enhancing GUI Retrieval with Multi-Modal LLM-based Reranking

TL;DR

GUI-ReRank introduces a multi-modal LLM-based reranking framework that significantly improves GUI retrieval accuracy and generalizability, enabling customizable, efficient GUI repository searches for interactive system development.

Contribution

The paper presents GUI-ReRank, a novel framework combining embedding retrieval with MLLM reranking, and offers a customizable pipeline for GUI repository annotation and embedding.

Findings

Outperforms state-of-the-art LTR models in retrieval accuracy

Demonstrates improved generalizability across GUI datasets

Provides a cost and efficiency analysis of MLLM reranking

Abstract

GUI prototyping is a fundamental component in the development of modern interactive systems, which are now ubiquitous across diverse application domains. GUI prototypes play a critical role in requirements elicitation by enabling stakeholders to visualize, assess, and refine system concepts collaboratively. Moreover, prototypes serve as effective tools for early testing, iterative evaluation, and validation of design ideas with both end users and development teams. Despite these advantages, the process of constructing GUI prototypes remains resource-intensive and time-consuming, frequently demanding substantial effort and expertise. Recent research has sought to alleviate this burden through NL-based GUI retrieval approaches, which typically rely on embedding-based retrieval or tailored ranking models for specific GUI repositories. However, these methods often suffer from limited retrieval performance and struggle to generalize across arbitrary GUI datasets. In this work, we present GUI-ReRank, a novel framework that integrates rapid embedding-based constrained retrieval models with highly effective MLLM-based reranking techniques. GUI-ReRank further introduces a fully customizable GUI repository annotation and embedding pipeline, enabling users to effortlessly make their own GUI repositories searchable, which allows for rapid discovery of relevant GUIs for inspiration or seamless integration into customized LLM-based RAG workflows. We evaluated our approach on an established NL-based GUI retrieval benchmark, demonstrating that GUI-ReRank significantly outperforms SOTA tailored LTR models in both retrieval accuracy and generalizability. Additionally, we conducted a comprehensive cost and efficiency analysis of employing MLLMs for reranking, providing valuable insights regarding the trade-offs between retrieval effectiveness and computational resources. Video: https://youtu.be/_7x9UCh82ug