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

arXiv: https://arxiv.org/abs/2406.06577 · HTML: https://mlsanity.com/paper/2406.06577/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 66 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models](https://mlsanity.com/paper/2309.10062/) (2023)
- [Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction](https://mlsanity.com/paper/2106.09232/) (2021)
- [Supporting Clustering with Contrastive Learning](https://mlsanity.com/paper/2103.12953/) (2021)
- [Exploring the Feasibility of ChatGPT for Event Extraction](https://mlsanity.com/paper/2303.03836/) (2023)
- [Zero-Shot Transfer Learning for Event Extraction](https://mlsanity.com/paper/1707.01066/) (2017)
- [TACO: Learning Task Decomposition via Temporal Alignment for Control](https://mlsanity.com/paper/1803.01840/) (2018)
- [Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection](https://mlsanity.com/paper/1910.11621/) (2019)
- [Zero-shot Temporal Relation Extraction with ChatGPT](https://mlsanity.com/paper/2304.05454/) (2023)
- [Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions](https://mlsanity.com/paper/2009.14259/) (2020)
- [Dynamic Prefix-Tuning for Generative Template-based Event Extraction](https://mlsanity.com/paper/2205.06166/) (2022)
- [Unsupervised Label-aware Event Trigger and Argument Classification](https://mlsanity.com/paper/2012.15243/) (2020)
- [proScript: Partially Ordered Scripts Generation via Pre-trained Language Models](https://mlsanity.com/paper/2104.08251/) (2021)
- [Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation](https://mlsanity.com/paper/1808.09006/) (2018)
- [A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, Fake News](https://mlsanity.com/paper/2306.10702/) (2023)
- [GLEN: General-Purpose Event Detection for Thousands of Types](https://mlsanity.com/paper/2303.09093/) (2023)
- [The Survey on Multi-Source Data Fusion in Cyber-Physical-Social Systems:Foundational Infrastructure for Industrial Metaverses and Industries 5.0](https://mlsanity.com/paper/2404.07476/) (2024)

## Built on by (most cited first, 2 of 2)

- [Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches](https://mlsanity.com/paper/2507.14633/) (2025)
- [TemPrompt: Multi-Task Prompt Learning for Temporal Relation Extraction in RAG-based Crowdsourcing Systems](https://mlsanity.com/paper/2406.14825/) (2024)

## Abstract (arXiv)

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.