mlsanityData to 14 Oct 2026

RankPO: Preference Optimization for Job-Talent Matching

arXiv 2503.10723 ↗First posted 13 Mar 2025cs.CL cs.AI cs.IRcited by 0

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

Matching job descriptions (JDs) with suitable talent requires models capable of understanding not only textual similarities between JDs and candidate resumes but also contextual factors such as geographical location and academic seniority. To address this challenge, we propose a two-stage training framework for large language models (LLMs). In the first stage, a contrastive learning approach is used to train the model on a dataset constructed from real-world matching rules, such as geographical alignment and research area overlap. While effective, this model primarily learns patterns that defined by the matching rules. In the second stage, we introduce a novel preference-based fine-tuning method inspired by Direct Preference Optimization (DPO), termed Rank Preference Optimization (RankPO), to align the model with AI-curated pairwise preferences emphasizing textual understanding. Our experiments show that while the first-stage model achieves strong performance on rule-based data (nDCG@20 = 0.706), it lacks robust textual understanding (alignment with AI annotations = 0.46). By fine-tuning with RankPO, we achieve a balanced model that retains relatively good performance in the original tasks while significantly improving the alignment with AI preferences. The code and data are available at https://github.com/yflyzhang/RankPO.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 25 of its 31 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

25 of 31 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024SimPO: Simple Preference Optimization with a Reference-Free Reward23 May
  2. 2024Direct Preference Optimization with an Offset16 Feb
  3. 2023Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints28 Sep
  4. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 21

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2017Deep reinforcement learning from human preferencescited by 3,912
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  7. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  8. 2020Learning to summarize from human feedbackcited by 2,588
  9. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  10. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  11. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  12. 2020Contrastive Learning with Hard Negative Samplescited by 628
9 more
  1. 2023A Survey on Large Language Models for Recommendationcited by 379
  2. 2023Secrets of RLHF in Large Language Models Part I: PPOcited by 229
  3. 2024Secrets of RLHF in Large Language Models Part II: Reward Modelingcited by 171
  4. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  5. 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 132
  6. 2023Large Language Models for Generative Recommendation: A Survey and Visionary Discussionscited by 73
  7. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
  8. 2024The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarizationcited by 50
  9. 2020Revisiting Design Choices in Proximal Policy Optimizationcited by 38

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models
  2. 2024Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts
  3. 2025Beyond Pairwise: Empowering LLM Alignment With Ranked Choice Modeling
  4. 2024Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization
  5. 2025MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
  6. 2025Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions
  7. 2024Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
  8. 2025InfoPO: On Mutual Information Maximization for Large Language Model Alignment