Skip to content
← Back to explorer

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

Matthias De Lange, Jens-Joris Decorte, Jeroen Van Hautte · Nov 11, 2025 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Apr 7, 2026, 1:05 PM

Recent

Extraction refreshed

Apr 12, 2026, 6:27 PM

Fresh

Extraction source

Persisted extraction

Confidence 0.45

Abstract

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.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.45 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

5/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: 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.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: 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.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: 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.

Benchmarks / Datasets

partial

Workbench

Confidence: Low Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: 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.

Reported Metrics

partial

Latency

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: 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.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: 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.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Ranking
  • Expertise required: General
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.45
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

Workbench

Reported Metrics

latency

Research Brief

Deterministic synthesis

These constraints have led to isolated, task-specific developments in the field, with models and benchmarks focused on single prediction tasks. HFEPX signals include Automatic Metrics with confidence 0.45. Updated from current HFEPX corpus.

Generated Apr 12, 2026, 6:27 PM · Grounded in abstract + metadata only

Key Takeaways

  • 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…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Cross-check benchmark overlap: Workbench.
  • Validate metric comparability (latency).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • 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.

Why It Matters For Eval

  • 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.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: Workbench

  • Pass: Metric reporting is present

    Detected: latency

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote