pith. sign in

arxiv: 2606.31692 · v1 · pith:UZ5HP3UVnew · submitted 2026-06-30 · 💻 cs.CL

Overview of the TalentCLEF 2026: Skill and Job Title Intelligence for Human Capital Management

Luis Gasco , Hermenegildo Fabregat , Laura Garc\'ia-Sardi\~na , Paula Estrella , Warre Veys , Casimiro P\'io Carrino , Matthias De Lange , Daniel Deniz Cerpa
show 3 more authors
\'Alvaro Rodrigo Jens-Joris Decorte Rabih Zbib
This is my paper

Pith reviewed 2026-07-01 05:22 UTC · model grok-4.3

classification 💻 cs.CL
keywords TalentCLEFNatural Language ProcessingHuman Capital ManagementJob MatchingSkill ClassificationShared TaskCLEF 2026
0
0 comments X

The pith

TalentCLEF 2026 defined two NLP tasks for job matching and skill classification that drew 113 registered teams and over 400 submissions.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents the second edition of the TalentCLEF challenge as a shared evaluation lab at CLEF 2026 focused on natural language processing for human capital management. It specifies Task A as identifying and ranking suitable resume candidates for job vacancies in English and Spanish, and Task B as retrieving relevant skills for a job title while separating core from contextual skills. The overview reports the motivation, datasets, evaluation protocols, and participation figures. A reader would care because the tasks supply concrete benchmarks that allow direct comparison of systems on practical HCM problems.

Core claim

TalentCLEF 2026 consisted of Task A on contextualized job-person matching and Task B on job-skill matching with skill type classification. The challenge received registrations from 113 teams and more than 400 submissions across the tasks. The paper treats these numbers as direct evidence of growing community interest in shared evaluation benchmarks for Human Capital Management and summarizes the datasets, evaluation settings, and main results obtained by participating teams.

What carries the argument

Two evaluation tasks—contextualized job-person matching across English and Spanish, and job-skill matching that distinguishes core from contextual skills—supply the shared benchmarks used to organize submissions and compare systems.

If this is right

  • The bilingual job-person matching task supplies a direct protocol for comparing systems on cross-language resume ranking.
  • The core-versus-contextual skill distinction in Task B gives a measurable way to evaluate precision in skill retrieval for job titles.
  • The reported participation and submission counts establish a baseline level of community activity against which future editions can be measured.
  • The released datasets and evaluation scripts become reusable resources for training and testing new models in the same domain.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Widespread adoption of these tasks could standardize how research groups measure progress on HCM applications, making incremental improvements easier to track.
  • The language coverage in Task A points toward a need for models that handle multilingual resume data without separate pipelines.
  • If the distinction between core and contextual skills proves stable across industries, it could be extended to other job-related text classification problems.

Load-bearing premise

The tasks and evaluation settings defined for the challenge accurately capture real-world complexities in human capital management and provide a fair basis for comparing NLP systems.

What would settle it

A follow-up test in which the top-ranked systems from the challenge produce rankings or skill lists that diverge substantially from expert human judgments on fresh, real-company job postings and resumes not drawn from the provided datasets.

Figures

Figures reproduced from arXiv: 2606.31692 by \'Alvaro Rodrigo, Casimiro P\'io Carrino, Daniel Deniz Cerpa, Hermenegildo Fabregat, Jens-Joris Decorte, Laura Garc\'ia-Sardi\~na, Luis Gasco, Matthias De Lange, Paula Estrella, Rabih Zbib, Warre Veys.

Figure 2
Figure 2. Figure 2: Overview of Task B: Job-Skill Matching with Skill Type Classification [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
read the original abstract

This paper presents an overview of the second edition of the TalentCLEF challenge, organized as a Lab at the Conference and Labs of the Evaluation Forum (CLEF) 2026. TalentCLEF is an initiative aimed at advancing Natural Language Processing research in Human Capital Management. The second edition of the challenge consisted of two tasks: Task A, contextualized job-person matching, focuses on identifying and ranking the most suitable candidates represented by their resumes for a given job vacancy in English and Spanish. Task B, job-skill matching with skill type classification, addresses retrieving the most relevant skills for a given job title in English and distinguishing between core and contextual skills. TalentCLEF attracted 113 registered teams and received more than 400 submissions in the two tasks, reflecting the growing interest of the research community in shared evaluation benchmarks for Human Capital Management. This paper describes the motivation and organization of the challenge, summarizes the datasets and evaluation settings, and reports the main results obtained by the participating teams.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 0 minor

Summary. The manuscript presents an overview of the second edition of the TalentCLEF challenge organized as a CLEF 2026 lab. It defines two tasks—Task A on contextualized job-person matching (ranking resumes for job vacancies in English and Spanish) and Task B on job-skill matching with core vs. contextual skill classification (in English)—and reports that 113 teams registered with more than 400 submissions received across the tasks. The paper describes the motivation and organization, summarizes the datasets and evaluation settings, and reports the main results obtained by participating teams.

Significance. If the reported participation figures hold, the paper establishes a documented record of community engagement with shared benchmarks for NLP in Human Capital Management, with the explicit count of 113 registered teams and >400 submissions serving as direct evidence of interest. A strength is the straightforward factual reporting of registration and submission numbers without derivations or fitted parameters, together with the bilingual scope of Task A.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive review and recommendation to accept the manuscript. The assessment correctly highlights the value of the documented participation numbers and the bilingual aspect of Task A as evidence of community interest in NLP for Human Capital Management.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper is a purely descriptive overview of a shared-task lab (TalentCLEF 2026) with no derivations, equations, models, predictions, or first-principles results. Its central factual claim (113 teams, >400 submissions) is a direct report of observed events and does not reduce to any fitted parameter, self-definition, or self-citation chain. Task descriptions and motivation statements are conventional for evaluation campaigns and carry no load-bearing uniqueness theorems or ansatzes. The paper is therefore self-contained against external benchmarks with no circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a descriptive overview with no mathematical content, free parameters, axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5759 in / 1195 out tokens · 33033 ms · 2026-07-01T05:22:03.746351+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

72 extracted references · 21 canonical work pages · 5 internal anchors

  1. [1]

    CoRR abs/2212.08553(2022)

    Anand, S., Decorte, J., Lowie, N.: Is it required? ranking the skills required for a job-title. CoRR abs/2212.08553(2022). https://doi.org/10.48550/ARXIV.2212.08553, https://doi.org/10.48550/arXiv.2212.08553

    work page doi:10.48550/arxiv.2212.08553 2022

  2. [2]

    Gasco et al

    Arafan, A.M., Graus, D., Santos, F.P., Beauxis-Aussalet, E.: End-to-end bias miti- gationincandidaterecommendersystemswithfairnessgates.In:Kaya,M.,Bogers, 18 L. Gasco et al. T., Graus, D., Mesbah, S., Johnson, C., Gutiérrez, F. (eds.) Proceedings of the 2nd Workshop on Recommender Systems for Human Resources (RecSys-in-HR 2022) co-located with the 16th AC...

    2022

  3. [3]

    In: CLEF (Working Notes) (2026)

    Bao, P.D., Duy, T.N.H.: In-Domain Contrastive Fine-tuning of Sentence-BERT for ESCO-based Job–Skill Retrieval and Classification. In: CLEF (Working Notes) (2026)

    2026

  4. [4]

    In: Proceedings of the 18th ACM Conference on Recom- mender Systems

    Bogers, T., Graus, D., Kaya, M., Johnson, C., Decorte, J.J., De Bie, T.: Fourth workshop on recommender systems for human resources (rec- sys in hr 2024). In: Proceedings of the 18th ACM Conference on Recom- mender Systems. p. 1222–1226. RecSys ’24, Association for Computing Ma- chinery, New York, NY, USA (2024). https://doi.org/10.1145/3640457.3687109, h...

    work page doi:10.1145/3640457.3687109 2024

  5. [5]

    arXiv preprint arXiv:2601.23183 (2026)

    Carrino, C.P., Estrella, P., Zbib, R., Escolano, C., Fonollosa, J.A.: Jobresqa: A benchmark for llm machine reading comprehension on multilingual r\’esum\’es and jds. arXiv preprint arXiv:2601.23183 (2026)

    work page arXiv 2026

  6. [6]

    In: CLEF (Working Notes) (2026)

    Castañeira Rodríguez, A.J.: Semantic Reranking for Zero-Shot Occupation-Skill Linking. In: CLEF (Working Notes) (2026)

    2026

  7. [7]

    M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

    Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self- knowledge distillation. arXiv preprint arXiv:2402.032164(5) (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  8. [8]

    In: Proceedings of the ACM on Web Conference

    Chen, Y., Liu, Q., Zhang, Y., Sun, W., Ma, X., Yang, W., Shi, D., Mao, J., Yin, D.: Tourrank: Utilizing large language models for documents ranking with a tournament-inspired strategy. In: Proceedings of the ACM on Web Conference

  9. [9]

    1638–1652 (2025)

    pp. 1638–1652 (2025)

    2025

  10. [10]

    WorkRB: A Community-Driven Evaluation Framework for AI in the Work Domain

    DeLange,M.,Veys,W.,Retyk,F.,Deniz,D.,Jouanneau,W.,Zhang,M.,Bielinski, A., Jouffroy, E., Clobes, N., Baranowska, N., et al.: Workrb: A community-driven evaluation framework for ai in the work domain. arXiv preprint arXiv:2604.13055 (2026)

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  11. [11]

    In: Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)

    De Santo, A., Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N.: Skillens: recognising and mapping novel skills from millions of job ads across europe using language models. In: Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track). pp. 877–885 (2026)

    2026

  12. [12]

    arXiv preprint arXiv:2507.21609 (2025)

    Decorte, J.J., De Lange, M., Van Hautte, J.: Multilingual jobbert for cross-lingual job title matching. arXiv preprint arXiv:2507.21609 (2025)

    work page arXiv 2025

  13. [13]

    In: Kaya, M., Bogers, T., Graus, D., Johnson, C., Decorte, J

    Decorte, J., Hautte, J.V., Deleu, J., Develder, C., Demeester, T.: Career path prediction using resume representation learning and skill-based matching. In: Kaya, M., Bogers, T., Graus, D., Johnson, C., Decorte, J. (eds.) Proceedings of the 3rd Workshop on Recommender Systems for Human Resources (RecSys in HR 2023) co-located with the 17th ACM Conference ...

    2023

  14. [14]

    CoRRabs/2109.09605(2021), https://arxiv.org/abs/2109.09605

    Decorte, J., Hautte, J.V., Demeester, T., Develder, C.: Jobbert: Un- derstanding job titles through skills. CoRRabs/2109.09605(2021), https://arxiv.org/abs/2109.09605

    work page arXiv 2021

  15. [15]

    arXiv preprint arXiv:2410.05006 (2024) TalentCLEF at CLEF2026 19

    Decorte, J.J., Van Hautte, J., Demeester, T., Develder, C.: Skillmatch: Evaluating self-supervised learning of skill relatedness. arXiv preprint arXiv:2410.05006 (2024) TalentCLEF at CLEF2026 19

    work page arXiv 2024

  16. [16]

    In: Kaya, M., Bogers, T., Graus, D., Johnson, C., Decorte, J., Bie, T.D

    Deniz, D., Retyk, F., García-Sardiña, L., Fabregat, H., Gascó, L., Zbib, R.: Com- bined unsupervised and contrastive learning for multilingual job recommenda- tion. In: Kaya, M., Bogers, T., Graus, D., Johnson, C., Decorte, J., Bie, T.D. (eds.) Proceedings of the 4th Workshop on Recommender Systems for Human Re- sources (RecSys-in-HR 2024) co-located with...

    2024

  17. [17]

    In: CLEF (Working Notes) (2026)

    Dumitru, D.A.: Ranking job-resume similarity using cross-lingual bi-encoding. In: CLEF (Working Notes) (2026)

    2026

  18. [18]

    In: CLEF (Working Notes) (2026)

    Fabregat, H., García-Sardiña, L., Estrella, P., Gasco, L., Carrino, C.P., Deniz Cerpa, D., Rodrigo, A., Zbib, R.: Overview of talentclef 2026: Task a — contextualized job-person matching. In: CLEF (Working Notes) (2026)

    2026

  19. [19]

    Procesamiento del Lenguaje Natural73, 83–94 (2024), http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6602

    Fabregat, H., Poves, R., Alvarez, L.L., Retyk, F., García-Sardiña, L., Zbib, R.: Inductive graph neural network for job-skill frame- work analysis. Procesamiento del Lenguaje Natural73, 83–94 (2024), http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6602

    2024

  20. [20]

    arXiv preprint arXiv:2509.13803 (2025)

    García-Sardiña, L., Fabregat, H., Deniz, D., Zbib, R.: Measuring gender bias in job title matching for grammatical gender languages. arXiv preprint arXiv:2509.13803 (2025)

    work page arXiv 2025

  21. [21]

    Procesamiento del Lenguaje Natural71, 63–73 (2023)

    García-Sardiña, L., Retyk, F., Fabregat, H., Alvarez Lacasa, L., Poves, R., Zbib, R.: Normalisation of education information in digitalised recruitment processes. Procesamiento del Lenguaje Natural71, 63–73 (2023)

    2023

  22. [22]

    In: European Conference on Information Retrieval

    Gasco, L., Fabregat, H., García-Sardiña, L., Deniz, D., Rodrigo, A., Estrella, P., Zbib, R.: Talentclef at clef2025: skill and job title intelligence for human capi- tal management. In: European Conference on Information Retrieval. pp. 479–486. Springer (2025)

    2025

  23. [23]

    In: European Conference on Information Retrieval

    Gasco, L., Fabregat, H., García-Sardiña, L., Estrella, P., Carrino, C.P., Deniz, D., Rodrigo, A., Zbib, R.: Talentclef at clef2026: Skill and job title intelligence for human capital management. In: European Conference on Information Retrieval. Springer (2026)

    2026

  24. [24]

    In: International Conference of the Cross-Language Evalua- tion Forum for European Languages

    Gasco, L., Fabregat, H., García-Sardiña, L., Estrella, P., Deniz, D., Rodrigo, A., Zbib, R.: Overview of the talentclef 2025: Skill and job title intelligence for human capital management. In: International Conference of the Cross-Language Evalua- tion Forum for European Languages. pp. 464–485. Springer (2025)

    2025

  25. [25]

    arXiv preprint arXiv:2309.11805 (2023)

    Ghosh, P., Sadaphal, V.: Jobrecogpt–explainable job recommendations using llms. arXiv preprint arXiv:2309.11805 (2023)

    work page arXiv 2023

  26. [26]

    Applied Soft Computing 101, 107049 (2021)

    Giabelli, A., Malandri, L., Mercorio, F., Mezzanzanica, M., Seveso, A.: Skills2job: A recommender system that encodes job of- fer embeddings on graph databases. Applied Soft Computing 101, 107049 (2021). https://doi.org/10.1016/J.ASOC.2020.107049, https://doi.org/10.1016/j.asoc.2020.107049

    work page doi:10.1016/j.asoc.2020.107049 2021

  27. [27]

    In: CLEF (Working Notes) (2026)

    Hamza, A.: Multi-Stage CV Retrieval for TalentCLEF 2026 Task A: A Bi-Encoder and Cross-Encoder Pipeline. In: CLEF (Working Notes) (2026)

    2026

  28. [28]

    In: CLEF (Working Notes) (2026)

    Hemamou, L., Dupont, R.: Retrieve, Rerank, Survive: LLM-Listwise Pipelines for Job–Person and Job–Skill Matching at TalentCLEF 2026. In: CLEF (Working Notes) (2026)

    2026

  29. [29]

    Association for Computational Linguistics

    Hruschka, E., Lake, T., Otani, N., Mitchell, T.: Proceedings of the first work- shop on natural language processing for human resources (nlp4hr 2024). In: Pro- ceedings of the First Workshop on Natural Language Processing for Human Re- 20 L. Gasco et al. sources (NLP4HR 2024). "Association for Computational Linguistics" (2024), https://aclanthology.org/20...

    2024

  30. [30]

    Iclr1(2), 3 (2022)

    Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al.: Lora: Low-rank adaptation of large language models. Iclr1(2), 3 (2022)

    2022

  31. [31]

    In: CLEF (Working Notes) (2026)

    Ibrahim,S.,Zaghouani,W.:MARSADatTalentCLEF2026TaskB:HybridESCO- Aware Retrieval for Job–Skill Matching. In: CLEF (Working Notes) (2026)

    2026

  32. [32]

    In: Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval

    Khattab, O., Zaharia, M.: Colbert: Efficient and effective passage search via con- textualized late interaction over bert. In: Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval. pp. 39–48 (2020)

    2020

  33. [33]

    arXiv preprint arXiv:2511.02537 (2025)

    Khelkhal, K., Lanasri, D.: Smart-hiring: An explainable end-to-end pipeline for cv information extraction and job matching. arXiv preprint arXiv:2511.02537 (2025)

    work page arXiv 2025

  34. [34]

    In: CLEF (Working Notes) (2026)

    Kim, S., Choi, M., Lee, S.: Semantic Enrichment for Resume Ranking and Skill Retrieval at TalentCLEF 2026. In: CLEF (Working Notes) (2026)

    2026

  35. [35]

    Kusupati, A., Bhatt, G., Rege, A., Wallingford, M., Sinha, A., Ramanujan, V., Howard-Snyder, W., Chen, K., Kakade, S., Jain, P., et al.: Matryoshka representa- tionlearning.AdvancesinNeuralInformationProcessingSystems35,30233–30249 (2022)

    2022

  36. [36]

    arXiv preprint arXiv:2403.06789 (2024)

    Lassance, C., Déjean, H., Formal, T., Clinchant, S.: Splade-v3: New baselines for splade. arXiv preprint arXiv:2403.06789 (2024)

    work page arXiv 2024

  37. [37]

    Lavi, D., Medentsiy, V., Graus, D.: consultantbert: Fine-tuned siamese sentence- bertformatchingjobsandjobseekers.In:Kaya,M.,Bogers,T.,Graus,D.,Verbert, K., Gutiérrez, F. (eds.) Proceedings of the Workshop on Recommender Systems for Human Resources (RecSys in HR 2021) co-located with the 15th ACM Confer- ence on Recommender Systems (RecSys 2021), Amsterda...

    2021

  38. [38]

    ACM Transactions on Information Systems (2025)

    Li, M., Lv, X., Zou, J., Chen, T., Zhang, C., An, S., Nie, E., Zhou, G.: Query expansion in the age of pre-trained and large language models: A comprehensive survey. ACM Transactions on Information Systems (2025)

    2025

  39. [39]

    LinkedIn: The Skills signal: Unlocking the opportunity in a changing labor market (June 2025), https://economicgraph.linkedin.com/content/dam/me/business/en- us/talent-solutions/resources/pdfs/the-skills-signal-report-2025.pdf, Accessed: 2026-06-03

    2025

  40. [40]

    In: CLEF (Working Notes) (2026)

    Liu, Y., Niu, Z., Li, C., Fan, Z.: Pointwise and Pairwise LLM-as-a-Reranker for Job-Title to ESCO Skill Retrieval over GIST-Fine-Tuned JobBERT. In: CLEF (Working Notes) (2026)

    2026

  41. [41]

    In: Proceedings of the computer vision and pattern recognition conference

    Lo, F.P.W., Qiu, J., Wang, Z., Yu, H., Chen, Y., Zhang, G., Lo, B.: Ai hiring with llms: A context-aware and explainable multi-agent framework for resume screening. In: Proceedings of the computer vision and pattern recognition conference. pp. 4184–4193 (2025)

    2025

  42. [42]

    In: CLEF (Working Notes) (2026)

    Luthfiyyah, I.Q., Yudhoatmojo, S., Budi, I.: ui-nlp at TalentCLEF 2026: Multilin- gual Bi-Encoder Retrieval with Ensemble Strategy for Job-Person and Job-Skill Matching. In: CLEF (Working Notes) (2026)

    2026

  43. [43]

    In: CLEF (Working Notes) (2026)

    Moreno, M., Martinez-Santos, J.C., Puertas, E.: VerbaNex at TalentCLEF 2026: A HybridMultilingualRetrievalandApproachforContextualizedJob-PersonMatch- ing. In: CLEF (Working Notes) (2026)

    2026

  44. [44]

    In: European Conference on Information Retrieval

    Nentidis, A., Krithara, A., Paliouras, G., Krallinger, M., Sanchez, L.G., Lima, S., Farre, E., Loukachevitch, N., Davydova, V., Tutubalina, E.: Bioasq at clef2024: the twelfth edition of the large-scale biomedical semantic indexing and question TalentCLEF at CLEF2026 21 answering challenge. In: European Conference on Information Retrieval. pp. 490–

  45. [45]

    In: Proceedings of the First Workshop on Natural Language Processing for Human Resources (NLP4HR 2024)

    Nguyen, K., Zhang, M., Montariol, S., Bosselut, A.: Rethinking skill extraction in the job market domain using large language models. In: Proceedings of the First Workshop on Natural Language Processing for Human Resources (NLP4HR 2024). pp. 27–42 (2024)

    2024

  46. [46]

    Representation Learning with Contrastive Predictive Coding

    Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predic- tive coding. arXiv preprint arXiv:1807.03748 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  47. [47]

    In: CLEF (Working Notes) (2026)

    Palomino, A.: Hybrid Dense-Sparse Retrieval and Re-Ranking for Multilingual Resume Retrieval from Job Descriptions. In: CLEF (Working Notes) (2026)

    2026

  48. [48]

    In: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society

    Peña, A., Fierrez, J., Morales, A., Mancera, G., Lopez-Duran, M., Tolosana, R.: Addressing bias in llms: Strategies and application to fair ai-based recruitment. In: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society. vol. 8, pp. 1976–1987 (2025)

    1976

  49. [49]

    arXiv preprint arXiv:2509.12541 (2025)

    Pipitone, N., Alami, G.H., Avadhanam, A., Kaminskyi, A., Khoo, A.: zelo: Elo- inspired training method for rerankers and embedding models. arXiv preprint arXiv:2509.12541 (2025)

    work page arXiv 2025

  50. [50]

    In: CLEF (Working Notes) (2026)

    Poerwanto, J., Wu, S.H.: CYUT at TalentCLEF 2026: Zero-Shot Multi-View Re- trieval for Job-Person Matching. In: CLEF (Working Notes) (2026)

    2026

  51. [51]

    In: CLEF (Working Notes) (2026)

    Ranjan, D., S, A., Harrison, V.S.K.R.R., Rao, L.P.S.: Fine-tuned Bi-Encoder for Job-Skill Matching: Exploring Curriculum Learning, Hard Negative Mining, and Hybrid Retrieval. In: CLEF (Working Notes) (2026)

    2026

  52. [52]

    In: Kaya, M., Bogers, T., Graus, D., Johnson, C., Decorte, J., Bie, T.D

    Retyk, F., Gascó, L., Carrino, C.P., Deniz, D., Zbib, R.: MELO: an evaluation benchmark for multilingual entity linking of occupations. In: Kaya, M., Bogers, T., Graus, D., Johnson, C., Decorte, J., Bie, T.D. (eds.) Proceedings of the 4th Work- shop on Recommender Systems for Human Resources (RecSys-in-HR 2024) co- located with the 18th ACM Conference on ...

    2024

  53. [53]

    In: CLEF (Working Notes) (2026)

    Riabi, A., Essayeh, M.: Taxonomy-Aware Hybrid Retrieval with Bounded LLM Reranking for TalentCLEF 2026 Task A. In: CLEF (Working Notes) (2026)

    2026

  54. [54]

    In: AI-Oriented Competency Framework for Talent Management in the Digital Economy, pp

    Sathish, A., Rajkumar, V.S., Vijay, V., Kathiravan, C.: The significance of artificial intelligence in career progression and career pathway development. In: AI-Oriented Competency Framework for Talent Management in the Digital Economy, pp. 28–

  55. [55]

    In: European semantic web conference

    Schlichtkrull, M., Kipf, T.N., Bloem, P., Van Den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: European semantic web conference. pp. 593–607. Springer (2018)

    2018

  56. [56]

    AI & SOCIETY41(4), 2841–2861 (2026)

    Sivakaminathan, S.S., Musi, E.: Chatgpt is a gender bias echo-chamber in hr re- cruitment: an nlp analysis and framework to uncover the language roots of bias. AI & SOCIETY41(4), 2841–2861 (2026)

    2026

  57. [57]

    arXiv preprint arXiv:2402.16829 (2024)

    Solatorio, A.V.: Gistembed: Guided in-sample selection of training negatives for text embedding fine-tuning. arXiv preprint arXiv:2402.16829 (2024)

    work page arXiv 2024

  58. [58]

    In: CLEF (Working Notes) (2026)

    Thuma, E., Anderson, G.: A Union Fusion of PyTerrier, Doc2Query, BM25 and Multilingual Embeddings for Job Title Matching. In: CLEF (Working Notes) (2026)

    2026

  59. [59]

    In: CLEF (Working Notes) (2026) 22 L

    Tran, H.H.H.: QTPride @TalentCLEF 2026: Towards Multi-View Job-Person Matching with LLM Parsing and Knowledge Graph-Enhanced Retrieval. In: CLEF (Working Notes) (2026) 22 L. Gasco et al

    2026

  60. [60]

    In: Findings of the Association for Computational Linguistics: NAACL 2025

    Vaishampayan, S., Leary, H., Alebachew, Y.B., Hickman, L., Stevenor, B., Beck, W., Brown, C.: Human and llm-based resume matching: An observational study. In: Findings of the Association for Computational Linguistics: NAACL 2025. pp. 4823–4838 (2025)

    2025

  61. [61]

    Compjobs’ 22: Computational Jobs Marketplace1(1), 2–6 (2022)

    Vermeer, N., Provatorova, V., Graus, D., Rajapakse, T., Mesbah, S.: Using robbert and extreme multi-label classification to extract implicit and explicit skills from dutch job descriptions. Compjobs’ 22: Computational Jobs Marketplace1(1), 2–6 (2022)

    2022

  62. [62]

    In: CLEF (Working Notes) (2026)

    Veys, W., Gasco, L., De Lange, M., Decorte, J.J.: Overview of talentclef 2026: Task b — job-skill matching with skill type classification. In: CLEF (Working Notes) (2026)

    2026

  63. [63]

    In: CLEF (Working Notes) (2026)

    Vielvoye, M.: Skillberg at TalentCLEF 2026: Cross-Framework Knowledge-Graph Grounded Multilingual Encoders for Job–Person and Job–Skill Matching. In: CLEF (Working Notes) (2026)

    2026

  64. [64]

    In: 2024 First International Conference on Innovations in Communications, Electrical and Computer Engineer- ing (ICICEC)

    Vijayalakshmi, V., Ananya, A., Sharanya Avadhani, M.: Optimization of hr re- cruitment process using large language model (llm). In: 2024 First International Conference on Innovations in Communications, Electrical and Computer Engineer- ing (ICICEC). pp. 1–5. IEEE (2024)

    2024

  65. [65]

    Computer47(10), 57–64 (2014)

    le Vrang, M., Papantoniou, A., Pauwels, E., Fannes, P., Vandensteen, D., Smedt, J.D.: ESCO: boosting job matching in europe with semantic interop- erability. Computer47(10), 57–64 (2014). https://doi.org/10.1109/MC.2014.283, https://doi.org/10.1109/MC.2014.283

    work page doi:10.1109/mc.2014.283 2014

  66. [66]

    Multilingual E5 Text Embeddings: A Technical Report

    Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., Wei, F.: Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672 (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  67. [67]

    IEEE transactions on pattern analysis and machine intelligence44(9), 4555–4576 (2021)

    Wang, X., Chen, Y., Zhu, W.: A survey on curriculum learning. IEEE transactions on pattern analysis and machine intelligence44(9), 4555–4576 (2021)

    2021

  68. [68]

    ACM Transactions on Information Systems (TOIS)28(4), 1–38 (2010)

    Webber, W., Moffat, A., Zobel, J.: A similarity measure for indefinite rankings. ACM Transactions on Information Systems (TOIS)28(4), 1–38 (2010)

    2010

  69. [69]

    CoRRabs/2207.00494(2022)

    Zbib, R., Alvarez, L.L., Retyk, F., Poves, R., Aizpuru, J., Fabregat, H., Simkus, V., Casademont, E.G.: Learning job titles similarity from noisy skill labels. CoRRabs/2207.00494(2022). https://doi.org/10.48550/ARXIV.2207.00494, https://doi.org/10.48550/arXiv.2207.00494

    work page doi:10.48550/arxiv.2207.00494 2022

  70. [70]

    In: Kaya, M., Bogers, T., Graus, D., Mesbah, S., Johnson, C., Gutiérrez, F

    Zhang, M., Jensen, K.N., van der Goot, R., Plank, B.: Skill extraction from job postings using weak supervision. In: Kaya, M., Bogers, T., Graus, D., Mesbah, S., Johnson, C., Gutiérrez, F. (eds.) Proceedings of the 2nd Workshop on Rec- ommender Systems for Human Resources (RecSys-in-HR 2022) co-located with the 16th ACM Conference on Recommender Systems (...

    2022

  71. [71]

    In: Carpuat, M., de Marneffe, M., Ruíz, I.V.M

    Zhang, M., Jensen, K.N., Sonniks, S.D., Plank, B.: Skillspan: Hard and soft skill extraction from english job postings. In: Carpuat, M., de Marneffe, M., Ruíz, I.V.M. (eds.) Proceedings of the 2022 Confer- ence of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United Sta...

    work page doi:10.18653/v1/2022.naacl-main.366 2022

  72. [72]

    Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

    Zhang, Y., Li, M., Long, D., Zhang, X., Lin, H., Yang, B., Xie, P., Yang, A., Liu, D., Lin, J., et al.: Qwen3 embedding: Advancing text embedding and reranking through foundation models. arXiv preprint arXiv:2506.05176 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025