Navid Rekabsaz
Scholar

Navid Rekabsaz

Google Scholar ID: lZjyLyEAAAAJ
Thomson Reuters Labs
Deep LearningNatural Language ProcessingInformation Retrieval
Citations & Impact
All-time
Citations
1,618
 
H-index
24
 
i10-index
36
 
Publications
20
 
Co-authors
18
list available
Resume (English only)
Academic Achievements
  • Batched Self-Consistency Improves LLM Relevance Assessment and Ranking (2025)
  • Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization (2024)
  • ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale (2024)
  • Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters (2024)
  • What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition (2024)
  • Measuring Bias in Search Results Through Retrieval List Comparison (2024)
  • Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors (2023)
  • Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks (2023)
  • Parameter-efficient Modularised Bias Mitigation via AdapterFusion (2023)
  • Leveraging Domain Knowledge for Inclusive and Bias-aware Humanitarian Response Entry Classification (2023)
  • Show me a 'Male Nurse'! How Gender Bias is Reflected in the Query Formulation of Search Engine Users (2023)
  • Computational Versus Perceived Popularity Miscalibration in Recommender Systems (2023)
  • Natural Language Processing for humanitarian action: opportunities, challenges, and the path towards humanitarian NLP (2023)
  • Fairness of Recommender Systems in the Recruitment Domain: An Analysis from Technical and Legal Perspectives (2023)
Research Experience
  • Lead AI Scientist @ Thomson Reuters
Background
  • Lead AI Scientist @ Thomson Reuters