A primer on the inner workings of transformer-based language models J Ferrando, G Sarti, A Bisazza, M Costa-jussà | 65 | 2024 |
Measuring the Mixing of Contextual Information in the Transformer J Ferrando, GI Gállego, MR Costa-jussà EMNLP 2022, 2022 | 52 | 2022 |
Improving accuracy and speeding up document image classification through parallel systems J Ferrando, JL Domínguez, J Torres, R García, D García, D Garrido, ... Computational Science–ICCS 2020: 20th International Conference, Amsterdam …, 2020 | 49 | 2020 |
Towards opening the black box of neural machine translation: Source and target interpretations of the transformer J Ferrando, GI Gállego, B Alastruey, C Escolano, MR Costa-jussà EMNLP 2022, 2022 | 47 | 2022 |
Neurons in large language models: Dead, n-gram, positional E Voita, J Ferrando, C Nalmpantis ACL 2024 (Findings), 2023 | 46 | 2023 |
Explaining How Transformers Use Context to Build Predictions J Ferrando, GI Gállego, I Tsiamas, MR Costa-jussà ACL 2023, 2023 | 32 | 2023 |
Information flow routes: Automatically interpreting language models at scale J Ferrando, E Voita EMNLP 2024, 2024 | 26 | 2024 |
Interpreting gender bias in neural machine translation: Multilingual architecture matters MR Costa-jussà, C Escolano, C Basta, J Ferrando, R Batlle, ... Proceedings of the AAAI Conference on Artificial Intelligence 36 (11), 11855 …, 2022 | 25 | 2022 |
Toxicity in multilingual machine translation at scale MR Costa-jussà, E Smith, C Ropers, D Licht, J Maillard, J Ferrando, ... EMNLP 2023 (Findings), 2022 | 23 | 2022 |
Interpreting gender bias in neural machine translation: Multilingual architecture matters MR Costa-jussà, C Escolano, C Basta, J Ferrando, R Batlle, ... AAAI 2022, 2022 | 23* | 2022 |
Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions J Ferrando, MR Costa-jussà EMNLP 2021 (Findings), 2021 | 21 | 2021 |
Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models J Ferrando*, O Obeso*, S Rajamanoharan, N Nanda ICLR 2025 (Oral), 2025 | 8 | 2025 |
Lm transparency tool: Interactive tool for analyzing transformer language models I Tufanov, K Hambardzumyan, J Ferrando, E Voita ACL 2024 (Demo), 2024 | 8 | 2024 |
On the Locality of Attention in Direct Speech Translation B Alastruey*, J Ferrando*, GI Gállego, MR Costa-jussà ACL SRW 2022, 2022 | 8 | 2022 |
On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task J Ferrando, MR Costa-jussà EMNLP 2024 (Findings), 2024 | 5 | 2024 |
The TALP-UPC Participation in WMT21 News Translation Task: an mBART-based NMT Approach C Escolano, I Tsiamas, C Basta, J Ferrando, MR Costa-jussà, ... WMT 2021, 2021 | 4 | 2021 |
Automating Behavioral Testing in Machine Translation J Ferrando, M Sperber, H Setiawan, D Telaar, S Hasan WMT 2023, 2023 | 3 | 2023 |