Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: De Lange, Matthias, Decorte, Jens-Joris, Van Hautte, Jeroen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908943378284544
author De Lange, Matthias
Decorte, Jens-Joris
Van Hautte, Jeroen
author_facet De Lange, Matthias
Decorte, Jens-Joris
Van Hautte, Jeroen
contents Applications in labor market intelligence demand specialized NLP systems for a wide range of tasks, characterized by extreme multi-label target spaces, strict latency constraints, and multiple text modalities such as skills and job titles. These constraints have led to isolated, task-specific developments in the field, with models and benchmarks focused on single prediction tasks. Exploiting the shared structure of work-related data, we propose a unifying framework, combining a wide range of tasks in a multi-task ranking benchmark, and a flexible architecture tackling text-driven work tasks with a single model. The benchmark, WorkBench, is the first unified evaluation suite spanning six work-related tasks formulated explicitly as ranking problems, curated from real-world ontologies and human-annotated resources. WorkBench enables cross-task analysis, where we find significant positive cross-task transfer. This insight leads to Unified Work Embeddings (UWE), a task-agnostic bi-encoder that exploits our training-data structure with a many-to-many InfoNCE objective, and leverages token-level embeddings with task-agnostic soft late interaction. UWE demonstrates zero-shot ranking performance on unseen target spaces in the work domain, and enables low-latency inference with two orders of magnitude fewer parameters than best-performing generalist models (Qwen3-8B), with +4.4 MAP improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07969
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker
De Lange, Matthias
Decorte, Jens-Joris
Van Hautte, Jeroen
Computation and Language
Applications in labor market intelligence demand specialized NLP systems for a wide range of tasks, characterized by extreme multi-label target spaces, strict latency constraints, and multiple text modalities such as skills and job titles. These constraints have led to isolated, task-specific developments in the field, with models and benchmarks focused on single prediction tasks. Exploiting the shared structure of work-related data, we propose a unifying framework, combining a wide range of tasks in a multi-task ranking benchmark, and a flexible architecture tackling text-driven work tasks with a single model. The benchmark, WorkBench, is the first unified evaluation suite spanning six work-related tasks formulated explicitly as ranking problems, curated from real-world ontologies and human-annotated resources. WorkBench enables cross-task analysis, where we find significant positive cross-task transfer. This insight leads to Unified Work Embeddings (UWE), a task-agnostic bi-encoder that exploits our training-data structure with a many-to-many InfoNCE objective, and leverages token-level embeddings with task-agnostic soft late interaction. UWE demonstrates zero-shot ranking performance on unseen target spaces in the work domain, and enables low-latency inference with two orders of magnitude fewer parameters than best-performing generalist models (Qwen3-8B), with +4.4 MAP improvement.
title Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker
topic Computation and Language
url https://arxiv.org/abs/2511.07969