Mi-Young Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mi-Young Kim has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Randy Goebel
University of Alberta
18 shared publications - Juliano Rabelo
University of Alberta
11 shared publications - Ken Satoh
Center for Juris-Informatics, ROIS-DS, Tokyo, Japan
6 shared publications - Masaharu Yoshioka
Hokkaido University, Sapporo, Hokkaido, Japan
6 shared publications Randy Goebel
Department of Computing Science and Alberta Machine Intelligence Institute (Amii), University of Alberta, Edmonton, Canada
6 shared publications- Yoshinobu Kano
Faculty of Informatics, Shizuoka University, Hamamatsu, Japan
6 shared publications
Latest Publications
- 8 September 2026
- Published by Springer Nature
- p. 380-396
Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?
- 8 September 2026
- Published by Springer Nature
- p. 380-396
Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?
- 8 September 2026
- Published by Springer Nature
- p. 415-431
Layer-Wise Suppressors for ViT Interpretation
- 3 August 2026
- Published by Springer Nature
- p. 32-46
Feature-Level Interaction Explanations in Multimodal Transformers
- 3 August 2026
- Published by Springer Nature
- p. 32-46
Feature-Level Interaction Explanations in Multimodal Transformers
- Open Access
Reason2Decide-C: Adaptive Cycle-Consistent Training for Clinical Rationales
Large Language Models (LLMs) used for clinical decision support must not only make accurate predictions but also generate rationales that are consistent with, and sufficient for, those predictions. Building on Reason2Decide, a two-stage rationale-driven multi-task framework, we propose Reason2Decide-C (R2D-C, where C denotes cycle consistency), which augments Reason2Decide’s stage 2 training with confidence-adaptive scheduled sampling and cycle-consistent rationale-to-label training. In stage 1, we pretrain our model on rationale generation. In stage 2, we jointlytrain on label prediction and rationale generation, gradually replacing gold labels with model-predicted labels based on confidence. Simultaneously, we feed the rationale logits back into the model to recover the label, thus enforcing explanation sufficiency. We evaluate R2D-C on one proprietary triage dataset, as well as public biomedical QA and reasoning datasets. Across model sizes, R2D-C substantially improves rationale–prediction consistency (where stage 1 and stage 2 predictions agree) and sufficiency (where the rationale alone recovers the ground-truth label) over other baselines while matching or modestly improving predictive performance (F1); in several settings R2D-C surpasses larger foundation models. Ablations confirm that the full combination is optimal, maximizing alignment and LLM-as-a-Judge rationale quality. These results demonstrate that confidence-adaptive scheduled sampling and cycle-consistent rationale-to-label training substantially enhance explanation alignment without sacrificing accuracy.Open AccessReason2Decide-C: Adaptive Cycle-Consistent Training for Clinical Rationales
Large Language Models (LLMs) used for clinical decision support must not only make accurate predictions but also generate rationales that are consistent with, and sufficient for, those predictions. Building on Reason2Decide, a two-stage rationale-driven multi-task framework, we propose Reason2Decide-C (R2D-C, where C denotes cycle consistency), which augments Reason2Decide’s stage 2 training with confidence-adaptive scheduled sampling and cycle-consistent rationale-to-label training. In stage 1, we pretrain our model on rationale generation. In stage 2, we jointlytrain on label prediction and rationale generation, gradually replacing gold labels with model-predicted labels based on confidence. Simultaneously, we feed the rationale logits back into the model to recover the label, thus enforcing explanation sufficiency. We evaluate R2D-C on one proprietary triage dataset, as well as public biomedical QA and reasoning datasets. Across model sizes, R2D-C substantially improves rationale–prediction consistency (where stage 1 and stage 2 predictions agree) and sufficiency (where the rationale alone recovers the ground-truth label) over other baselines while matching or modestly improving predictive performance (F1); in several settings R2D-C surpasses larger foundation models. Ablations confirm that the full combination is optimal, maximizing alignment and LLM-as-a-Judge rationale quality. These results demonstrate that confidence-adaptive scheduled sampling and cycle-consistent rationale-to-label training substantially enhance explanation alignment without sacrificing accuracy. - Open Access
- 20 February 2026
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 20 (1) , 183-213
The COLIEE 2025 Competition on Legal Information Extraction and Entailment: Overview, Discussion, and Dataset Expansion
We summarize the 12th Competition on Legal Information Extraction and Entailment. In this edition, the competition included two tasks on case law, two tasks on statute law, plus a new pilot task on Tort law. The two case law components include an information retrieval task (Task 1), and the confirmation of an entailment relation between an existing case and an unseen case (Task 2). The statute law components include an information retrieval task (Task 3), and an entailment/question-answering task based on retrieved civil code statutes (Task 4). The new pilot task involves tort prediction and rationale extraction. Participation was open to any group using any approach. Eight teams submitted a total of 21 runs for Task 1, achieving a top F1 score of 0.3604, with dominant approaches featuring multi-stage retrieval pipelines combining traditional IR with neural re-ranking methods. We summarize the variety of approaches, provide our official evaluation, and give a summary analysis of our data and submission results. In Task 2, the NOWJ team, which used BM25 for retrieval and DeepSeek-V3 and Qwen/QwQ-32B for reranking, achieved the best score of 0.3195. Eight teams submitted a total of 22 runs for Task 3. The best-performing system employs a multi-stage retrieval approach: it first retrieves a limited number of candidate articles in the initial stage, then applies an LLM-based cross-encoder for re-ranking, and finally determines the relevant articles using multiple LLMs. This system achieves nearly perfect retrieval performance for questions with a single relevant article; however, it still faces challenges in retrieving all relevant articles for questions that have multiple relevant answers. 11 teams submitted a total of 29 runs for Task 4, achieving a top accuracy score of 0.9041, where the solution uses an LLM coupled with a prompt engineering approach. Most teams used LLMs but their approaches and the models used were quite different. The new pilot task received 10 runs from four teams. All the teams employed LLMs. The best performing runs are JAIST-LJPJT25 (acc.=0.765) by the CAPTAIN team for the tort prediction task and KIS5 (F1=0.712) by the KIS team for the rationale extraction task. Finally, based on the strong performance observed in Tasks 3 and 4 this year, we propose introducing a new task for the next COLIEE, focusing on statute retrieval.
- 20 February 2026
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 20 (1) , 183-213
Open AccessThe COLIEE 2025 Competition on Legal Information Extraction and Entailment: Overview, Discussion, and Dataset Expansion
We summarize the 12th Competition on Legal Information Extraction and Entailment. In this edition, the competition included two tasks on case law, two tasks on statute law, plus a new pilot task on Tort law. The two case law components include an information retrieval task (Task 1), and the confirmation of an entailment relation between an existing case and an unseen case (Task 2). The statute law components include an information retrieval task (Task 3), and an entailment/question-answering task based on retrieved civil code statutes (Task 4). The new pilot task involves tort prediction and rationale extraction. Participation was open to any group using any approach. Eight teams submitted a total of 21 runs for Task 1, achieving a top F1 score of 0.3604, with dominant approaches featuring multi-stage retrieval pipelines combining traditional IR with neural re-ranking methods. We summarize the variety of approaches, provide our official evaluation, and give a summary analysis of our data and submission results. In Task 2, the NOWJ team, which used BM25 for retrieval and DeepSeek-V3 and Qwen/QwQ-32B for reranking, achieved the best score of 0.3195. Eight teams submitted a total of 22 runs for Task 3. The best-performing system employs a multi-stage retrieval approach: it first retrieves a limited number of candidate articles in the initial stage, then applies an LLM-based cross-encoder for re-ranking, and finally determines the relevant articles using multiple LLMs. This system achieves nearly perfect retrieval performance for questions with a single relevant article; however, it still faces challenges in retrieving all relevant articles for questions that have multiple relevant answers. 11 teams submitted a total of 29 runs for Task 4, achieving a top accuracy score of 0.9041, where the solution uses an LLM coupled with a prompt engineering approach. Most teams used LLMs but their approaches and the models used were quite different. The new pilot task received 10 runs from four teams. All the teams employed LLMs. The best performing runs are JAIST-LJPJT25 (acc.=0.765) by the CAPTAIN team for the tort prediction task and KIS5 (F1=0.712) by the KIS team for the rationale extraction task. Finally, based on the strong performance observed in Tasks 3 and 4 this year, we propose introducing a new task for the next COLIEE, focusing on statute retrieval.
- 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
- 28 May 2024
- Published by Springer Nature
- p. 109-124
Overview of Benchmark Datasets and Methods for the Legal Information Extraction/Entailment Competition (COLIEE) 2024
- 28 May 2024
- Published by Springer Nature
- p. 109-124
Overview of Benchmark Datasets and Methods for the Legal Information Extraction/Entailment Competition (COLIEE) 2024
- Top Cited PapersOpen Access
- 12 January 2024
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 18 (1) , 27-47
Overview and Discussion of the Competition on Legal Information, Extraction/Entailment (COLIEE) 2023
We summarize the 10th Competition on Legal Information Extraction and Entailment. In this tenth edition, the competition included four tasks on case law and statute law. The case law component includes an information retrieval task (Task 1), and the confirmation of an entailment relation between an existing case and a selected unseen case (Task 2). The statute law component includes an information retrieval task (Task 3), and an entailment/question-answering task based on retrieved civil code statutes (Task 4). Participation was open to any group based on any approach. Ten different teams participated in the case law competition tasks, most of them in more than one task. We received results from 8 teams for Task 1 (22 runs) and seven teams for Task 2 (18 runs). On the statute law task, there were 9 different teams participating, most in more than one task. 6 teams submitted a total of 16 runs for Task 3, and 9 teams submitted a total of 26 runs for Task 4. We describe the variety of approaches, our official evaluation, and analysis of our data and submission results.
- 12 January 2024
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 18 (1) , 27-47
Top Cited PapersOpen AccessOverview and Discussion of the Competition on Legal Information, Extraction/Entailment (COLIEE) 2023
We summarize the 10th Competition on Legal Information Extraction and Entailment. In this tenth edition, the competition included four tasks on case law and statute law. The case law component includes an information retrieval task (Task 1), and the confirmation of an entailment relation between an existing case and a selected unseen case (Task 2). The statute law component includes an information retrieval task (Task 3), and an entailment/question-answering task based on retrieved civil code statutes (Task 4). Participation was open to any group based on any approach. Ten different teams participated in the case law competition tasks, most of them in more than one task. We received results from 8 teams for Task 1 (22 runs) and seven teams for Task 2 (18 runs). On the statute law task, there were 9 different teams participating, most in more than one task. 6 teams submitted a total of 16 runs for Task 3, and 9 teams submitted a total of 26 runs for Task 4. We describe the variety of approaches, our official evaluation, and analysis of our data and submission results.
- Open Access
- 11 January 2024
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 18 (1) , 101-121
Legal Information Retrieval and Entailment Using Transformer-based Approaches
The challenge of information overload in the legal domain increases every day. The COLIEE competition has created four challenge tasks that are intended to encourage the development of systems and methods to alleviate some of that pressure: a case law retrieval (Task 1) and entailment (Task 2), and a statute law retrieval (Task 3) and entailment (Task 4). Here we describe our methods for Task 1 and Task 4. In Task 1, we used a sentence-transformer model to create a numeric representation for each case paragraph. We then created a histogram of the similarities between a query case and a candidate case. The histogram is used to build a binary classifier that decides whether a candidate case should be noticed or not. In Task 4, our approach relies on fine-tuning a pre-trained DeBERTa large language model (LLM) trained on SNLI and MultiNLI datasets. Our method for Task 4 was ranked third among eight participating teams in the COLIEE 2023 competition. For Task 4, We also compared the performance of the DeBERTa model with those of a knowledge distillation model and ensemble methods including Random Forest and Voting.
- 11 January 2024
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 18 (1) , 101-121
Open AccessLegal Information Retrieval and Entailment Using Transformer-based Approaches
The challenge of information overload in the legal domain increases every day. The COLIEE competition has created four challenge tasks that are intended to encourage the development of systems and methods to alleviate some of that pressure: a case law retrieval (Task 1) and entailment (Task 2), and a statute law retrieval (Task 3) and entailment (Task 4). Here we describe our methods for Task 1 and Task 4. In Task 1, we used a sentence-transformer model to create a numeric representation for each case paragraph. We then created a histogram of the similarities between a query case and a candidate case. The histogram is used to build a binary classifier that decides whether a candidate case should be noticed or not. In Task 4, our approach relies on fine-tuning a pre-trained DeBERTa large language model (LLM) trained on SNLI and MultiNLI datasets. Our method for Task 4 was ranked third among eight participating teams in the COLIEE 2023 competition. For Task 4, We also compared the performance of the DeBERTa model with those of a knowledge distillation model and ensemble methods including Random Forest and Voting.
- Top Cited PapersOpen Access
- 19 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 472-480
Summary of the Competition on Legal Information, Extraction/Entailment (COLIEE) 2023
- 19 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 472-480
Top Cited PapersOpen AccessSummary of the Competition on Legal Information, Extraction/Entailment (COLIEE) 2023