Hiroaki Yamada
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Hiroaki Yamada has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Takenobu Tokunaga
Institute of Science Tokyo Institute of Science Tokyo University of Cambridge Institute of Science Tokyo
8 shared publications - Kazumoto Iguchi
70-3 Shinhari, Hari, Anan, Tokushima 774-0003, Japan
5 shared publications - Kensuke S. Ikeda
College of Science and Engineering, Ritsumeikan University, Noji-higashi 1-1-1, Kusatsu 525-8577, Japan
4 shared publications - Shu-Ichi Kinoshita
Graduate School of Science and Technology, Niigata University, Nishi-ku Ikarashi 2-Nochou 8050, Niigata 950-2181, Japan
4 shared publications - Akira Igarashi
Graduate School of Science and Technology, Niigata University, Ikarashi 2-Nochou 8050, Niigata 950-2181, Japan
3 shared publications - Fumihiro Matsui
Department of Physics, College of Science and Engineering, Ritsumeikan University - Noji-higashi 1-1-1, Kusatsu 525-8577, Japan
3 shared publications
Latest Publications
- Open Access
- 20 July 2025
- Published by SAGE Publications in Language Testing
- Vol. 42 (4) , 447-475
Examining the consistency of instructor versus large language model ratings on summary content: Toward checklist-based feedback provision with second language writers
This study examined the consistency between instructor ratings of learner-generated summaries and those estimated by a large language model (LLM) on summary content checklist items designed for undergraduate second language (L2) writing instruction in Japan. The effects of the LLM prompt design on the consistency between the two were also explored by comparing six types of prompts obtained by altering the amount of information included in the prompt and the direction concerning the order in which different parts of the LLM output (a checklist-based rating and its rationale) are generated. Ninety-seven summaries written by Japanese undergraduate students were analyzed by employing three checklist items on the use of topic sentences included in the source text. Satisfactory agreement between instructor and LLM ratings for low-stakes use was obtained for certain checklist item-by-prompt type combinations. When discrepancies between the two were observed, LLM ratings tended to be harsher than instructor ratings in general. Furthermore, the amount of information included in the LLM prompt affected the instructor-LLM rating agreement more than the order of generating a rating and its rationale in the output. The results offered initial empirical support for employing LLM-generated formative feedback on summary content in L2 writing classrooms.
- 20 July 2025
- Published by SAGE Publications in Language Testing
- Vol. 42 (4) , 447-475
Open AccessExamining the consistency of instructor versus large language model ratings on summary content: Toward checklist-based feedback provision with second language writers
This study examined the consistency between instructor ratings of learner-generated summaries and those estimated by a large language model (LLM) on summary content checklist items designed for undergraduate second language (L2) writing instruction in Japan. The effects of the LLM prompt design on the consistency between the two were also explored by comparing six types of prompts obtained by altering the amount of information included in the prompt and the direction concerning the order in which different parts of the LLM output (a checklist-based rating and its rationale) are generated. Ninety-seven summaries written by Japanese undergraduate students were analyzed by employing three checklist items on the use of topic sentences included in the source text. Satisfactory agreement between instructor and LLM ratings for low-stakes use was obtained for certain checklist item-by-prompt type combinations. When discrepancies between the two were observed, LLM ratings tended to be harsher than instructor ratings in general. Furthermore, the amount of information included in the LLM prompt affected the instructor-LLM rating agreement more than the order of generating a rating and its rationale in the output. The results offered initial empirical support for employing LLM-generated formative feedback on summary content in L2 writing classrooms.
- Open Access
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 506-515
An Overview of the COLIEE 2025 Competition: Legal Case Law and Statute Law Information Retrieval and Entailment
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 506-515
Open AccessAn Overview of the COLIEE 2025 Competition: Legal Case Law and Statute Law Information Retrieval and Entailment
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Springer Nature in Artificial Intelligence and Law
- p. 1-25
Japanese tort-case dataset for rationale-supported legal judgment prediction
This paper presents the first dataset for Japanese Legal Judgment Prediction (LJP), the Japanese Tort-case Dataset (JTD), which features two tasks: tort prediction and its rationale extraction. The rationale extraction task identifies the court’s accepting arguments from alleged arguments by plaintiffs and defendants, which is a novel task in the field. JTD is constructed based on annotated 3477 Japanese Civil Code judgments by 41 legal experts, resulting in 7978 instances with 59,697 of their alleged arguments from the involved parties. Our baseline experiments show the feasibility of the proposed two tasks, and our error analysis by legal experts identifies sources of errors and suggests future directions of the LJP research.
- 11 May 2024
- Published by Springer Nature in Artificial Intelligence and Law
- p. 1-25
Top Cited PapersOpen AccessJapanese tort-case dataset for rationale-supported legal judgment prediction
This paper presents the first dataset for Japanese Legal Judgment Prediction (LJP), the Japanese Tort-case Dataset (JTD), which features two tasks: tort prediction and its rationale extraction. The rationale extraction task identifies the court’s accepting arguments from alleged arguments by plaintiffs and defendants, which is a novel task in the field. JTD is constructed based on annotated 3477 Japanese Civil Code judgments by 41 legal experts, resulting in 7978 instances with 59,697 of their alleged arguments from the involved parties. Our baseline experiments show the feasibility of the proposed two tasks, and our error analysis by legal experts identifies sources of errors and suggests future directions of the LJP research.
- Open Access
- 15 June 2023
- Published by American Physical Society (APS) in Physical Review E
- Vol. 107 (6) , L062201
Localized-diffusive and ballistic-diffusive transitions in kicked incommensurate lattices
By using the kicked Harper model, the effect of dynamical perturbations to the localized and ballistic phases in quasiperiodic lattice systems is investigated. The transition from the localized phase to diffusive phase via a critical subdiffusion ( is time) with is observed. In addition, we confirm the existence of the transition from the ballistic phase to the diffusive phase via a critical superdiffusion with .- 15 June 2023
- Published by American Physical Society (APS) in Physical Review E
- Vol. 107 (6) , L062201
Open AccessLocalized-diffusive and ballistic-diffusive transitions in kicked incommensurate lattices
By using the kicked Harper model, the effect of dynamical perturbations to the localized and ballistic phases in quasiperiodic lattice systems is investigated. The transition from the localized phase to diffusive phase via a critical subdiffusion ( is time) with is observed. In addition, we confirm the existence of the transition from the ballistic phase to the diffusive phase via a critical superdiffusion with . - Open Access
- 9 December 2022
- Published by Elsevier in Information Processing & Management
- Vol. 60 (2)
Looking deep in the eyes: Investigating interpretation methods for neural models on reading tasks using human eye-movement behaviour
- 9 December 2022
- Published by Elsevier in Information Processing & Management
- Vol. 60 (2)
Open AccessLooking deep in the eyes: Investigating interpretation methods for neural models on reading tasks using human eye-movement behaviour
- Open Access
- 13 March 2020
- Published by American Physical Society (APS) in Physical Review E
- Vol. 101 (3) , 032210
Critical phenomena of dynamical delocalization in quantum maps: Standard map and Anderson map
Following the paper exploring the Anderson localization of monochromatically perturbed kicked quantum maps [ Phys. Rev. E 97, 012210 (2018)], the delocalization-localization transition phenomena in polychromatically perturbed quantum maps (QM) is investigated focusing particularly on the dependency of critical phenomena on the number of the harmonic perturbations, where corresponds to the spatial dimension of the ordinary disordered lattice. The standard map and the Anderson map are treated and compared. As the basis of analysis, we apply the self-consistent theory (SCT) of the localization for our systems, taking a plausible hypothesis on the mean-free-path parameter which worked successfully in the analyses of the monochromatically perturbed QMs. We compare in detail the numerical results with the predictions of the SCT by largely increasing . The numerically obtained index of critical subdiffusion (:time) agrees well with the prediction of one-parameter scaling theory , but the numerically obtained critical exponent of localization length significantly deviates from the SCT prediction. Deviation from the SCT prediction is drastic for the critical perturbation strength of the transition: If is fixed, then the SCT presents plausible prediction for the parameter dependence of the critical value, but its value is times smaller than the SCT prediction, which implies existence of a strong cooperativity of the harmonic perturbations with the main mode.- 13 March 2020
- Published by American Physical Society (APS) in Physical Review E
- Vol. 101 (3) , 032210
Open AccessCritical phenomena of dynamical delocalization in quantum maps: Standard map and Anderson map
Following the paper exploring the Anderson localization of monochromatically perturbed kicked quantum maps [ Phys. Rev. E 97, 012210 (2018)], the delocalization-localization transition phenomena in polychromatically perturbed quantum maps (QM) is investigated focusing particularly on the dependency of critical phenomena on the number of the harmonic perturbations, where corresponds to the spatial dimension of the ordinary disordered lattice. The standard map and the Anderson map are treated and compared. As the basis of analysis, we apply the self-consistent theory (SCT) of the localization for our systems, taking a plausible hypothesis on the mean-free-path parameter which worked successfully in the analyses of the monochromatically perturbed QMs. We compare in detail the numerical results with the predictions of the SCT by largely increasing . The numerically obtained index of critical subdiffusion (:time) agrees well with the prediction of one-parameter scaling theory , but the numerically obtained critical exponent of localization length significantly deviates from the SCT prediction. Deviation from the SCT prediction is drastic for the critical perturbation strength of the transition: If is fixed, then the SCT presents plausible prediction for the parameter dependence of the critical value, but its value is times smaller than the SCT prediction, which implies existence of a strong cooperativity of the harmonic perturbations with the main mode. - Open Access
- 15 February 2019
- Published by Springer Nature in Artificial Intelligence and Law
- Vol. 27 (2) , 141-170
Building a corpus of legal argumentation in Japanese judgement documents: towards structure-based summarisation
- 15 February 2019
- Published by Springer Nature in Artificial Intelligence and Law
- Vol. 27 (2) , 141-170
Open AccessBuilding a corpus of legal argumentation in Japanese judgement documents: towards structure-based summarisation
- Open Access
- 1 January 2019
- Published by IOS Press
- p. 133-142
Neural Network Based Rhetorical Status Classification for Japanese Judgment Documents
- 1 January 2019
- Published by IOS Press
- p. 133-142
Open AccessNeural Network Based Rhetorical Status Classification for Japanese Judgment Documents
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 343-348
Supporting content evaluation of student summaries by Idea Unit embedding
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 343-348
Open AccessSupporting content evaluation of student summaries by Idea Unit embedding
- Open Access
- 1 August 2018
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 113, 178-185
Localization of disordered harmonic chain with long-range correlation
- 1 August 2018
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 113, 178-185
Open AccessLocalization of disordered harmonic chain with long-range correlation