arXiv subjects

Ayuto Tsutsumi

Publications and source records attributed to Ayuto Tsutsumi.

4 recordsLinked to original sources

arXiv2026

TalkMatrix: Generating Character Dialogue that is Both Consistent and Diverse

Candidate-based decoding typically selects a completion for each prompt independently, but many applications require a collection of outputs that satisfies global, non-decomposable requirements. We formulate this setting as structured multi-prompt, multi-completion selection: given a candidate pool for every prompt, select one completion per prompt to optimize a collection-level objective. We instantiate the problem in character dialogue, where each character should remain consistent across situations, each line should fit its situation, and characters and situations should remain distinguishable. Our method, TalkMatrix, generates multiple candidates for every character--situation pair and jointly selects a complete matrix using four embedding-based consistency and diversity objectives. Because a weighted sum can improve some dimensions by sacrificing another, TalkMatrix maximizes the worst-performing objective through a two-level minimax formulation. We approximately optimize the resulting discrete objective with multi-start coordinate ascent, and compare it with local, partial-matrix, and generic combinatorial search baselines. We run experiments on $50$ synthetic role-playing scenarios and $25$ curated board game scenarios where multiple characters interact in predefined situations. An LLM-as-a-judge rates matrix-level selection higher than random and independent cell-level selection baselines. These results show the value of structured selection for globally controlled dialogue generation, while our empirical validation remains specific to role-playing scenarios.

cs.CL↗

arXiv2026

Same Image, Different Meanings: Toward Retrieval of Context-Dependent Meanings

A scene of two people in the rain can convey hope and warmth in a reunion story or sorrow and finality in a farewell story. We investigate this context-dependent nature of image meaning and its implications for retrieval. Our key observation is that context dependency correlates with semantic abstraction: concrete elements (objects, actions) remain stable across contexts, while abstract elements (atmosphere, intent) shift with context. We operationalize this as the L1--L4 framework, organizing image semantics from context-independent (L1) to maximally context-dependent (L4). Using synthetic story contexts and queries for controlled evaluation, we examine how injecting narrative context into embeddings affects retrieval across abstraction levels. Concrete queries are retrievable without context, while abstract levels increasingly depend on narrative grounding. Where context is injected also matters, with image-side enrichment proving particularly effective. The most abstract level, however, remains challenging even with full context, highlighting context-dependent image retrieval as an important open problem. Our framework and findings lay groundwork toward retrieval systems that handle the context-dependent meanings images acquire in narrative settings.

cs.IR↗

arXiv2026

The TMU System for the XACLE Challenge: Training Large Audio Language Models with CLAP Pseudo-Labels

In this paper, we propose a submission to the x-to-audio alignment (XACLE) challenge. The goal is to predict semantic alignment of a given general audio and text pair. The proposed system is based on a large audio language model (LALM) architecture. We employ a three-stage training pipeline: automated audio captioning pretraining, pretraining with CLAP pseudo-labels, and fine-tuning on the XACLE dataset. Our experiments show that pretraining with CLAP pseudo-labels is the primary performance driver. On the XACLE test set, our system reaches an SRCC of 0.632, significantly outperforming the baseline system (0.334) and securing third place in the challenge team ranking. Code and models can be found at https://github.com/shiotalab-tmu/tmu-xacle2026

cs.SD↗

arXiv2025

Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales

Although Large Language Models (LLMs) have demonstrated strong language understanding and generation abilities across various languages, their cultural knowledge is often limited to English-speaking communities, which can marginalize the cultures of non-English communities. To address the problem, evaluation of the cultural awareness of the LLMs and the methods to develop culturally aware LLMs have been investigated. In this study, we focus on evaluating knowledge of folktales, a key medium for conveying and circulating culture. In particular, we focus on Japanese folktales, specifically on knowledge of Yokai. Yokai are supernatural creatures originating from Japanese folktales that continue to be popular motifs in art and entertainment today. Yokai have long served as a medium for cultural expression, making them an ideal subject for assessing the cultural awareness of LLMs. We introduce YokaiEval, a benchmark dataset consisting of 809 multiple-choice questions (each with four options) designed to probe knowledge about yokai. We evaluate the performance of 31 Japanese and multilingual LLMs on this dataset. The results show that models trained with Japanese language resources achieve higher accuracy than English-centric models, with those that underwent continued pretraining in Japanese, particularly those based on Llama-3, performing especially well. The code and dataset are available at https://github.com/CyberAgentA ILab/YokaiEval.

cs.CL↗