Takaaki Onaga
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Takaaki Onaga has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Yoshinobu Kano
Faculty of Informatics, Shizuoka University, Hamamatsu, Japan
4 shared publications - Masaki Fujita
Shizuoka University
3 shared publications - Ayaka Ueyama
Shizuoka University
1 shared publication
Latest Publications
- Open Access
- 18 March 2026
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 20 (1) , 341-359
KIS: COLIEE 2025 Task 4 Solver Using Japanese LLM
This paper presents a controlled comparison of prompting strategies for the COLIEE Task 4 legal entailment task under a unified experimental setting. Using a Japanese instruction-following LLM, we compare zero-shot (ZS), zero-shot Chain-of-Thought (ZS-CoT), and structured Chain-of-Thought (Structured-CoT). Across seven test years (2018–2024), the overall (sample-weighted) accuracy improves along the progression ZS $$\rightarrow $$ ZS-CoT $$\rightarrow $$ Structured-CoT under the unified setting, suggesting that prompt structure—rather than model changes—drives the gain in this setting. In addition, we report few-shot prompting with similarity-based retrieval and label balancing as a secondary sensitivity analysis over the number of shots. Few-shot effects vary by year and n , and we do not observe a consistent monotonic improvement as n increases.- 18 March 2026
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 20 (1) , 341-359
Open AccessKIS: COLIEE 2025 Task 4 Solver Using Japanese LLM
This paper presents a controlled comparison of prompting strategies for the COLIEE Task 4 legal entailment task under a unified experimental setting. Using a Japanese instruction-following LLM, we compare zero-shot (ZS), zero-shot Chain-of-Thought (ZS-CoT), and structured Chain-of-Thought (Structured-CoT). Across seven test years (2018–2024), the overall (sample-weighted) accuracy improves along the progression ZS $$\rightarrow $$ ZS-CoT $$\rightarrow $$ Structured-CoT under the unified setting, suggesting that prompt structure—rather than model changes—drives the gain in this setting. In addition, we report few-shot prompting with similarity-based retrieval and label balancing as a secondary sensitivity analysis over the number of shots. Few-shot effects vary by year and n , and we do not observe a consistent monotonic improvement as n increases. - 28 May 2024
- Published by Springer Nature
- p. 140-155
LLM Tuning and Interpretable CoT: KIS Team in COLIEE 2024
- 28 May 2024
- Published by Springer Nature
- p. 140-155
LLM Tuning and Interpretable CoT: KIS Team in COLIEE 2024
- Open Access
- 8 March 2024
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 18 (1) , 123-143
Contribution Analysis of Large Language Models and Data Augmentations for Person Names in Solving Legal Bar Examination at COLIEE 2023
This paper describes our system for COLIEE 2023 Task 4, which automatically answers Japanese legal bar exam problems. We propose an extension to our previous system in COLIEE 2022, which achieved the highest accuracy among all submissions using data augmentation. We focus on problems that include mentions of person names. In this paper, we present two main contributions. First, we incorporate LUKE as our deep learning component, which is a named entity recognition model trained on RoBERTa. Second, we fine-tune the pretrained LUKE model in multiple ways, comparing fine-tuning on training datasets that include alphabetical person names and ensembling different fine-tuning models. We confirmed that LUKE and its fine-tuned model on person type problems improve their accuracies. Our formal run results show that LUKE and our fine-tuning approach using alphabetical person names were effective, achieving an accuracy of 0.69 in the COLIEE 2023 Task 4 formal run.
- 8 March 2024
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 18 (1) , 123-143
Open AccessContribution Analysis of Large Language Models and Data Augmentations for Person Names in Solving Legal Bar Examination at COLIEE 2023
This paper describes our system for COLIEE 2023 Task 4, which automatically answers Japanese legal bar exam problems. We propose an extension to our previous system in COLIEE 2022, which achieved the highest accuracy among all submissions using data augmentation. We focus on problems that include mentions of person names. In this paper, we present two main contributions. First, we incorporate LUKE as our deep learning component, which is a named entity recognition model trained on RoBERTa. Second, we fine-tune the pretrained LUKE model in multiple ways, comparing fine-tuning on training datasets that include alphabetical person names and ensembling different fine-tuning models. We confirmed that LUKE and its fine-tuned model on person type problems improve their accuracies. Our formal run results show that LUKE and our fine-tuning approach using alphabetical person names were effective, achieving an accuracy of 0.69 in the COLIEE 2023 Task 4 formal run.
- Top Cited Papers
- 6 April 2023
- Published by Springer Nature
- p. 138-153
Legal Textual Entailment Using Ensemble of Rule-Based and BERT-Based Method with Data Augmentation by Related Article Generation
- 6 April 2023
- Published by Springer Nature
- p. 138-153
Top Cited PapersLegal Textual Entailment Using Ensemble of Rule-Based and BERT-Based Method with Data Augmentation by Related Article Generation