Masahiko Osawa
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
Masahiko Osawa has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Kohei Okuoka
Nihon University, Tokyo, Japan
7 shared publications - Ayu Iida
Nihon University, Tokyo, Japan
5 shared publications Michita Imai
Faculty of Science and Technology, Keio University, Kanagawa, Japan
5 shared publications- Ryoichi Nakashima
Kyoto University, Kyoto, Japan
4 shared publications - Honoka Tsunomori
Nihon University, Tokyo, Japan
3 shared publications - Michita Imai
Keio University
3 shared publications
Latest Publications
- Open Access
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 496-498
Rethinking Imitation: Familiar-Other Framing Shapes the Perceived Authenticity of an Agent as a Particular Person
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 496-498
Open AccessRethinking Imitation: Familiar-Other Framing Shapes the Perceived Authenticity of an Agent as a Particular Person
- Open Access
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 605-607
The Effects of Conscious User Involvement in the Creation of Conversational Self-Clones for Digital Mental Health: A Preliminary Study
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 605-607
Open AccessThe Effects of Conscious User Involvement in the Creation of Conversational Self-Clones for Digital Mental Health: A Preliminary Study
- Open Access
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 723-725
Familiar-Other Framing: Can Framing Project Pre-Existing Relationships with Familiar Others onto Dialogue Systems?
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 723-725
Open AccessFamiliar-Other Framing: Can Framing Project Pre-Existing Relationships with Familiar Others onto Dialogue Systems?
- Open Access
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 656-658
Human-Side Adaptation in Circle-Drawing Feedback Interaction: Adjusting Expression to an Agent's Response Tendencies
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 656-658
Open AccessHuman-Side Adaptation in Circle-Drawing Feedback Interaction: Adjusting Expression to an Agent's Response Tendencies
- Open Access
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 556-558
In-Vehicle Dialogue Information Management System for Contextual Disclosure Control and Driver Intent Understanding
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 556-558
Open AccessIn-Vehicle Dialogue Information Management System for Contextual Disclosure Control and Driver Intent Understanding
- Open Access
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 759-761
Dynamic Shading Alters Perception of Minimal-Design Robots
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 759-761
Open AccessDynamic Shading Alters Perception of Minimal-Design Robots
- Open Access
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 638-640
A Concept of a Dialogue System Using a Stereotypical Mental Model of Others
- 15 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 638-640
Open AccessA Concept of a Dialogue System Using a Stereotypical Mental Model of Others
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 424-426
From Doubt to Action
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 424-426
Open AccessFrom Doubt to Action
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 485-487
LLM-Based Evaluation of Utterances with Implicature Understanding
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 485-487
Open AccessLLM-Based Evaluation of Utterances with Implicature Understanding
- Open Access
- 24 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 260-269
Integrating Large Language Model and Mental Model of Others: Studies on Dialogue Communication Based on Implicature
Despite the significant development of Large Language Models (LLMs), they struggle with “dialogue communication based on implicature,” which humans handle easily. In this study, we aim to improve the performance of LLMs in this type of dialogue tasks by integrating LLMs with a cognitive model of dialogue. The cognitive model of dialogue comprises beliefs, desires, and intentions, which is defined as the Mental Model of Others (MMO) for predicting or estimating other’s mental states and behaviors. We propose two integration methods: the LLM Embedded in Cognitive Model (LEC) and the Cognitive Model Embedded in LLM (CEL). We examined the performances of our proposed method using the dialogue task, showing that the LEC can respond appropriately in the dialogues with implicatures, which cannot be achieved by conventional LLMs.
- 24 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 260-269
Open AccessIntegrating Large Language Model and Mental Model of Others: Studies on Dialogue Communication Based on Implicature
Despite the significant development of Large Language Models (LLMs), they struggle with “dialogue communication based on implicature,” which humans handle easily. In this study, we aim to improve the performance of LLMs in this type of dialogue tasks by integrating LLMs with a cognitive model of dialogue. The cognitive model of dialogue comprises beliefs, desires, and intentions, which is defined as the Mental Model of Others (MMO) for predicting or estimating other’s mental states and behaviors. We propose two integration methods: the LLM Embedded in Cognitive Model (LEC) and the Cognitive Model Embedded in LLM (CEL). We examined the performances of our proposed method using the dialogue task, showing that the LEC can respond appropriately in the dialogues with implicatures, which cannot be achieved by conventional LLMs.