mlsanityData to 14 Oct 2026

ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining

arXiv 2502.12361 ↗First posted 17 Feb 2025cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

A reliable resume-job matching system helps a company recommend suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a list of job posts. However, since job seekers apply only to a few jobs, interaction labels in resume-job datasets are sparse. We introduce ConFit v2, an improvement over ConFit to tackle this sparsity problem. We propose two techniques to enhance the encoder's contrastive training process: augmenting job data with hypothetical reference resume generated by a large language model; and creating high-quality hard negatives from unlabeled resume/job pairs using a novel hard-negative mining strategy. We evaluate ConFit v2 on two real-world datasets and demonstrate that it outperforms ConFit and prior methods (including BM25 and OpenAI text-embedding-003), achieving an average absolute improvement of 13.8% in recall and 17.5% in nDCG across job-ranking and resume-ranking tasks.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 38 of its 60 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

38 of 60 references.

References · 38

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2017Billion-scale similarity search with GPUscited by 2,497
  8. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  9. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  10. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  11. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  12. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
26 more
  1. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  2. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  3. 2022Large Language Models Can Self-Improvecited by 664
  4. 2020Contrastive Learning with Hard Negative Samplescited by 628
  5. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  6. 2015An Introduction to Convolutional Neural Networkscited by 514
  7. 2019On Measuring Social Biases in Sentence Encoderscited by 398
  8. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 337
  9. 2021Optimizing Dense Retrieval Model Training with Hard Negativescited by 155
  10. 2022Dense Text Retrieval based on Pretrained Language Models: A Surveycited by 136
  11. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 104
  12. 2019Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networkscited by 103
  13. 2018Understanding the Origins of Bias in Word Embeddingscited by 91
  14. 2024NV-Retriever: Improving text embedding models with effective hard-negative miningcited by 84
  15. 2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoderscited by 75
  16. 2018Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approachcited by 39
  17. 2023Teaching Language Models to Self-Improve through Interactive Demonstrationscited by 26
  18. 2020Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Networkcited by 25
  19. 2022SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrievalcited by 21
  20. 2023Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Taskcited by 21
  21. 2024Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddingscited by 21
  22. 2022Modeling Two-Way Selection Preference for Person-Job Fitcited by 18
  23. 2020Learning Effective Representations for Person-Job Fit by Feature Fusioncited by 16
  24. 2023Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboardcited by 15
  25. 2024SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrievalcited by 14
  26. 2024HyQE: Ranking Contexts with Hypothetical Query Embeddingscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026JobResQA: A Benchmark for LLM Machine Reading Comprehension on Multilingual R'esum'es and JDscited by 2
  2. 2026ConFit v3: Improving Resume-Job Matching with LLM-based Re-Rankingcited by 2
  3. 2026An Efficient Long-Context Ranking Architecture With Calibrated LLM Distillation: Application to Person-Job Fitcited by 1
  4. 2025MSLEF: Multi-Segment LLM Ensemble Finetuning in Recruitmentcited by 0
  5. 2026EHR-Bench: A Chinese Multi-Task Benchmark for Recruitment AIcited by 0