RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts

TL;DR

This paper introduces PBCT, a novel prompt-based contrastive learning framework for task decomposition in crowdsourcing, addressing limitations of existing PLM-based methods by improving event detection accuracy and domain adaptability.

Contribution

The paper proposes a new retrieval-augmented, prompt-based contrastive learning approach for task decomposition that overcomes existing PLM limitations and enhances domain adaptability.

Findings

Outperforms existing methods in supervised and zero-shot detection.

Demonstrates effectiveness in domain-specific tasks like PCB manufacturing.

Provides a flexible framework adaptable to professional domains.

Abstract

Crowdsourcing is a critical technology in social manufacturing, which leverages an extensive and boundless reservoir of human resources to handle a wide array of complex tasks. The successful execution of these complex tasks relies on task decomposition (TD) and allocation, with the former being a prerequisite for the latter. Recently, pre-trained language models (PLMs)-based methods have garnered significant attention. However, they are constrained to handling straightforward common-sense tasks due to their inherent restrictions involving limited and difficult-to-update knowledge as well as the presence of hallucinations. To address these issues, we propose a retrieval-augmented generation-based crowdsourcing framework that reimagines TD as event detection from the perspective of natural language understanding. However, the existing detection methods fail to distinguish differences between event types and always depend on heuristic rules and external semantic analyzing tools. Therefore, we present a Prompt-Based Contrastive learning framework for TD (PBCT), which incorporates a prompt-based trigger detector to overcome dependence. Additionally, trigger-attentive sentinel and masked contrastive learning are introduced to provide varying attention to trigger and contextual features according to different event types. Experiment results demonstrate the competitiveness of our method in both supervised and zero-shot detection. A case study on printed circuit board manufacturing is showcased to validate its adaptability to unknown professional domains.