--- title: "JobMatchAI - An Intelligent Job Matching Platform Using" description: "The authors also release JobSearch-XS, a benchmark built from NYC civil-service postings. 6 references." authors: ["Mayank Vyas", "Abhijit Chakraborty", "Vivek Gupta"] year: 2026 venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)" source: "https://aclanthology.org/2026.acl-demo.52/" doi: "10.18653/v1/2026.acl-demo.52" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/vyas-2026-jobmatchai-intelligent-job-matching-platform/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/vyas-2026-jobmatchai-intelligent-job-matching-platform/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/14/) / JobMatchAI - An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI # JobMatchAI - An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI **Authors:** Mayank Vyas, Abhijit Chakraborty and [Vivek Gupta](https://md.research.elamur.ai/free/en/authors/vivek-gupta/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.acl-demo.52/) · [PDF](https://aclanthology.org/2026.acl-demo.52.pdf) · [DOI 10.18653/v1/2026.acl-demo.52](https://doi.org/10.18653/v1/2026.acl-demo.52) · [OpenAlex](https://openalex.org/W7166828109) **Citations:** 1 citations (OpenAlex, 2026-10-14) ## Summary Most job search engines filter on keywords. They miss skill synonyms and non-linear career paths, and their match scores cannot be inspected. JobMatchAI is a microservices system that tackles this by combining three retrieval channels: BM25 lexical search in Elasticsearch, approximate nearest-neighbour search over all-MiniLM-L6-v2 embeddings, and multi-hop traversal of a Neo4j skill graph built from ESCO plus a hand-made synonym table. The three result lists are merged with query-adaptive Reciprocal Rank Fusion. Candidates are then reranked by a transparent weighted utility over six factors, and users can change the weights live. An LLM only verbalises these precomputed scores and graph paths. It can therefore explain a ranking but cannot raise one, which keeps decisions auditable for hiring compliance. The authors also release JobSearch-XS, a benchmark built from NYC civil-service postings. On it, the system reaches NDCG@10 of 0.81, roughly 7% better than BM25, with sub-100 ms latency. The work matters as a deployable, open reference design for explainable matching in a legally sensitive domain. ## Key points - **JobSearch-XS benchmark:** - 1,283 NYC Open Data civil-service roles, 30 queries and about 29K silver labels. - Skill-disjoint train/dev/test splits test zero-shot skill generalisation. - Only 40 gold-labelled pairs exist. - Released under CC-BY-4.0; the code is MIT-licensed. - **Retrieval depths and fusion:** - BM25 and semantic search each return k=150 results; the graph channel returns k=75. - RRF uses k=60. - Short queries (≤2 tokens) weight the knowledge graph at 0.7. - Longer queries shift weight to text matching (0.6). - **Default reranking weights:** skill 0.35, experience 0.25, location 0.15, salary 0.10, semantic similarity 0.10, company fit 0.05. - **Evaluation:** - Offline tests report bootstrap confidence intervals, per-query variance, a skill-extractor ablation and a cross-domain spot-check. - A user study with 20 participants was run. - Recall@100 (0.35) falls below the BM25 baseline. - **Interaction modes:** Smart Search starts from an uploaded resume, and Keyword Search applies graph-based skill expansion. A live demo and an installable package are available. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Arizona State University](https://md.research.elamur.ai/free/en/universities/arizona-state-university/) — University, Tempe, United States · 50 works · 2,032 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [💼 Business, Management and Accounting](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/) · 32 works · [💼 Organizational Behavior and Human Resource Management](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/organizational-behavior-and-human-resource-management/) · 12 works 🧭 Topics (3): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works · [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · 192 works · [🔬 Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/) · 130 works ## Cite Cite as: Mayank Vyas, Abhijit Chakraborty and Vivek Gupta. 2026. JobMatchAI - An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{vyas2026jobmatchai, title = {{JobMatchAI - An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI}}, author = {Mayank Vyas, Abhijit Chakraborty and Vivek Gupta}, booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)}, year = {2026}, doi = {10.18653/v1/2026.acl-demo.52}, url = {https://doi.org/10.18653/v1/2026.acl-demo.52} } ``` - [← previous JIA at SemEval-2026 Task 10: A Dual-Track System with BERT-based Encoders and LLMs for Conspiracy Analysis](https://md.research.elamur.ai/free/en/papers/zhu-2026-jia-semeval-2026-task-10/) - [next → JointCoder: Exploring Automated ICD Coding on Real-World Chinese EHRs with a Multi-Agent Framework](https://md.research.elamur.ai/free/en/papers/liu-2026-jointcoder-exploring-automated-icd-coding/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/14/) ## References 6 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://md.research.elamur.ai/free/en/papers/bajaj-2016-ms-marco-human-generated/). arXiv preprint.… 2. Jo Kristian Bergum. 2019. E-Commerce Search and Recommendation with Vespa.ai. [find](https://scholar.google.com/scholar?q=Jo+Kristian+Bergum%2E+2019%2E+E%2DCommerce+Search+and+Recommendation+with+Vespa%2Eai%2E) 3. Finale Doshi-Velez and Been Kim. 2017. [Towards A Rigorous Science of Interpretable Machine Learning](https://md.research.elamur.ai/free/en/papers/doshi-velez-2017-towards-rigorous-science-interpretable-machine/). arXiv preprint. ArXiv:1702.08608 [stat]. 4. Sarthak Jain and Byron C. Wallace. 2019. [Attention is not Explanation](https://md.research.elamur.ai/free/en/papers/jain-2019-attention-is-not-explanation/). arXiv preprint. ArXiv:1902.10186 [cs]. 5. Omar Khattab and Matei Zaharia. 2020. [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://md.research.elamur.ai/free/en/papers/khattab-2020-colbert-efficient-effective-passage/). arXiv preprint. ArXiv:2004.12832 [cs]. 6. Craig Macdonald and Nicola Tonellotto. 2020. Declarative Experimentation in Information Retrieval using [find](https://scholar.google.com/scholar?q=Craig+Macdonald+and+Nicola+Tonellotto%2E+2020%2E+Declarative+Experimentation+in+Information+Retrieval+using) *Updated 31 October 2026*