Selected work

Representative Papers

Schema-Guided Response Generation using Multi-Frame Dialogue State for Motivational Interviewing Systems

Aug 28, 2025

This study addresses the challenge of ensuring adherence to Motivational Interviewing (MI) principles in large language model (LLM)-driven counseling dialogue systems. Methodologically, we propose a framework integrating multi-turn dialogue state modeling with dynamic response focus control. It features a fine-grained, MI-principle-guided dialogue state update mechanism, pattern-informed dialogue management, strategy-controllable LLM response generation, and principle-constrained dynamic focus modulation. Our key contribution is the first explicit computational encoding of MI’s clinical logic—formalizing state transitions and strategy selection rules to precisely guide autonomy support, empathic responding, and evocative questioning. A user study demonstrates that our system significantly improves MI fidelity (+32.7%) and enhances users’ depth of self-reflection and readiness for behavior change (p < 0.01).

0 citationsRead paper

Computational Complexity and Integer Programming Formulation of the Oredango Puzzle

Mar 13, 2025

This study presents the first systematic computational complexity analysis of the Oredango puzzle. We establish that its decision problem is NP-complete via a polynomial-time reduction from 1-in-3SAT, and its counting/constructive variant is ASP-complete. Methodologically, we propose the first exact and complete 0–1 integer programming (IP) formulation, encoding all puzzle constraints as linear inequalities. The model is empirically validated using commercial solvers—including Gurobi and CPLEX—successfully solving multiple standard instances published by Nikoli and Puzzle Square JP, while ensuring correctness and demonstrating strong scalability. Our principal contributions are threefold: (i) the formal classification of Oredango’s computational complexity; (ii) the development of the first directly solvable, constraint-accurate IP model; and (iii) the introduction of a novel paradigm for automated solving and complexity-theoretic analysis of logic puzzles.

0 citationsRead paper

Recent publications

Latest Papers

Schema-Guided Response Generation using Multi-Frame Dialogue State for Motivational Interviewing Systems

Aug 28, 2025

This study addresses the challenge of ensuring adherence to Motivational Interviewing (MI) principles in large language model (LLM)-driven counseling dialogue systems. Methodologically, we propose a framework integrating multi-turn dialogue state modeling with dynamic response focus control. It features a fine-grained, MI-principle-guided dialogue state update mechanism, pattern-informed dialogue management, strategy-controllable LLM response generation, and principle-constrained dynamic focus modulation. Our key contribution is the first explicit computational encoding of MI’s clinical logic—formalizing state transitions and strategy selection rules to precisely guide autonomy support, empathic responding, and evocative questioning. A user study demonstrates that our system significantly improves MI fidelity (+32.7%) and enhances users’ depth of self-reflection and readiness for behavior change (p < 0.01).

0 citationsRead paper

Computational Complexity and Integer Programming Formulation of the Oredango Puzzle

Mar 13, 2025

This study presents the first systematic computational complexity analysis of the Oredango puzzle. We establish that its decision problem is NP-complete via a polynomial-time reduction from 1-in-3SAT, and its counting/constructive variant is ASP-complete. Methodologically, we propose the first exact and complete 0–1 integer programming (IP) formulation, encoding all puzzle constraints as linear inequalities. The model is empirically validated using commercial solvers—including Gurobi and CPLEX—successfully solving multiple standard instances published by Nikoli and Puzzle Square JP, while ensuring correctness and demonstrating strong scalability. Our principal contributions are threefold: (i) the formal classification of Oredango’s computational complexity; (ii) the development of the first directly solvable, constraint-accurate IP model; and (iii) the introduction of a novel paradigm for automated solving and complexity-theoretic analysis of logic puzzles.

0 citationsRead paper