| Smarter, better, faster, longer: A modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference B Warner, A Chaffin, B Clavié, O Weller, O Hallström, S Taghadouini, ... arXiv preprint arXiv:2412.13663, 2024 | 545 | 2024 |
| Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification B Clavié, A Ciceu, F Naylor, G Soulié, T Brightwell 28TH INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE & INFORMATION SYSTEMS …, 2023 | 130 | 2023 |
| Employing machine learning techniques for detection and classification of phishing emails N Moradpoor, B Clavie, B Buchanan 2017 computing conference, 149-156, 2017 | 93 | 2017 |
| Edubert: Pretrained deep language models for learning analytics B Clavié, K Gal Companion Proceedings of the Tenth International Conference on Learning …, 2020 | 47 | 2020 |
| Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matchers B Clavié, G Soulié RecSys in HR’23: The 3rd Workshop on Recommender Systems for Human Resources …, 2023 | 44 | 2023 |
| The unreasonable effectiveness of the baseline: discussing SVMs in legal text classification B Clavié, M Alphonsus Legal Knowledge and Information Systems: JURIX 2021, 2021 | 21 | 2021 |
| rerankers: A lightweight python library to unify ranking methods B Clavié arXiv preprint arXiv:2408.17344, 2024 | 13* | 2024 |
| JaColBERTv2. 5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources B Clavié Journal of Natural Language Processing 32 (1), 176-218, 2025 | 12 | 2025 |
| Jacolbert and hard negatives, towards better japanese-first embeddings for retrieval: Early technical report B Clavié arXiv preprint arXiv:2312.16144, 2023 | 11* | 2023 |
| Reducing the footprint of multi-vector retrieval with minimal performance impact via token pooling B Clavié, A Chaffin, G Adams arXiv preprint arXiv:2409.14683, 2024 | 8 | 2024 |
| LegaLMFiT: efficient short legal text classification with LSTM language model pre-training B Clavié, A Gheewala, P Briton, M Alphonsus, R Laabiyad, F Piccoli arXiv preprint arXiv:2109.00993, 2021 | 8 | 2021 |
| Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference. CoRR abs/2412.13663 (2024) B Warner, A Chaffin, B Clavié, O Weller, O Hallström, S Taghadouini, ... arXiv preprint ARXIV.2412.13663, 2024 | 7 | 2024 |
| Deep Embeddings of Contextual Assessment Data for Improving Performance Prediction. B Clavié, K Gal International Educational Data Mining Society, 2020 | 5 | 2020 |
| Towards simple hybrid language model reasoning through human explanations enhanced prompts B Clavié, G Soulié, F Naylor, T Brightwell HHAI 2023: Augmenting human intellect, 379-381, 2023 | 4 | 2023 |
| Fantastic (small) retrievers and how to train them: mxbai-edge-colbert-v0 tech report R Takehi, B Clavié, S Lee, A Shakir arXiv preprint arXiv:2510.14880, 2025 | 2 | 2025 |
| It’s all in the [MASK]: Simple instruction-tuning enables BERT-like masked language models as generative classifiers B Clavié, N Cooper, B Warner Natural Language Processing Journal, 100150, 2025 | 2 | 2025 |
| LIR: The First Workshop on Late Interaction and Multi Vector Retrieval@ ECIR 2026 B Clavié, X Li, A Chaffin, O Khattab, T Aarsen, M Faysse, J Li arXiv preprint arXiv:2511.00444, 2025 | | 2025 |
| Simple Projection Variants Improve ColBERT Performance B Clavié, S Lee, R Takehi, A Shakir, MP Kato arXiv preprint arXiv:2510.12327, 2025 | | 2025 |
| ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language Models B Clavié, F Brand arXiv preprint arXiv:2505.19091, 2025 | | 2025 |
Benjamin WarnerSophontVerified email at sophontai.com
