Papers by Soma Sato
Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples (2024.acl-srw)
Copied to clipboard
| Challenge: | Decoder-based large language models (LLMs) have shown high performance on many tasks in natural language processing. |
| Approach: | They propose to automatically generate an NLI dataset with an LLM and use it for fine-tuning of PromptEOL. |
| Outcome: | The proposed model outperforms existing models on STS tasks without large manually annotated datasets. |
How Do Language Models Acquire Character-Level Information? (2026.eacl-long)
Copied to clipboard
| Challenge: | Language models (LMs) implicitly encode character-level information, despite not being explicitly provided during training. |
| Approach: | They analyze how language models acquire character-level knowledge by comparing them to standard settings. |
| Outcome: | The results show that LMs do not treat words as opaque tokens, but instead treat them as tokens. |