Seuraa
Mengsay Loem
Mengsay Loem
Sansan, Inc.
Vahvistettu sähköpostiosoite verkkotunnuksessa sansan.com - Kotisivu
Nimike
Viittaukset
Viittaukset
Vuosi
Exploring effectiveness of GPT-3 in grammatical error correction: A study on performance and controllability in prompt-based methods
M Loem, M Kaneko, S Takase, N Okazaki
arXiv preprint arXiv:2305.18156, 2023
312023
Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities
K Fujii, T Nakamura, M Loem, H Iida, M Ohi, K Hattori, H Shota, S Mizuki, ...
arXiv preprint arXiv:2404.17790, 2024
152024
Extraphrase: Efficient data augmentation for abstractive summarization
M Loem, S Takase, M Kaneko, N Okazaki
arXiv preprint arXiv:2201.05313, 2022
92022
Building a Large Japanese Web Corpus for Large Language Models
N Okazaki, K Hattori, H Shota, H Iida, M Ohi, K Fujii, T Nakamura, M Loem, ...
arXiv preprint arXiv:2404.17733, 2024
22024
Saie framework: Support alone isn’t enough-advancing llm training with adversarial remarks
M Loem, M Kaneko, N Okazaki
ECAI 2024, 3717-3724, 2024
22024
Likelihood-based Mitigation of Evaluation Bias in Large Language Models
M Ohi, M Kaneko, R Koike, M Loem, N Okazaki
arXiv preprint arXiv:2402.15987, 2024
12024
Are Neighbors Enough? Multi-Head Neural n-gram can be Alternative to Self-attention
M Loem, S Takase, M Kaneko, N Okazaki
arXiv preprint arXiv:2207.13354, 2022
12022
Järjestelmä ei voi suorittaa toimenpidettä nyt. Yritä myöhemmin uudelleen.
Artikkelit 1–7