Keito Inoshita

Keito Inoshita, Takato Ueno

Emotions evolve through the dynamics of conversation, and understanding their transition structure is foundational to applications ranging from mental-health screening to dialogue systems. However, existing studies typically compress multi-rater judgments into a single hard label by majority voting, discarding the uncertainty signal needed to understand turn-to-turn transitions. In this article, we propose Bayesian Spectral Emotion Transition Discovery (BSETD), a two-stage framework that discovers emotion-transition structure from multi-rater soft labels. In the first stage, a hierarchical Dirichlet-Multinomial posterior is constructed through the outer product of soft labels, equipping each cell of the K x K transition matrix with a credible interval and Benjamini-Hochberg (BH) false discovery rate (FDR)-controlled significance. In the second stage, the symmetrized graph Laplacian is spectrally decomposed to separate a low-frequency (inertia) component from a high-frequency (contagion) component. On EmotionLines, BSETD simultaneously recovers the signatures of two distinct affective spaces: the Plutchik-adjacent transitions disgust to anger (log2 lift +0.94) and anger to disgust (+0.86) are over-represented, while the Russell-valence-reversed transitions joy to anger (-0.90) and anger to joy (-0.89) are under-represented. A five-source cross-corpus validation yields pairwise Pearson correlations in 0.91-0.98 within English, 0.79-0.85 against Chinese M3ED, and 0.979 between the human hard labels and the LLM virtual soft labels on the same utterance set, demonstrating that a pipeline preserving annotator uncertainty bridges the computational study of emotion dynamics with established psychological theory.

Keito Inoshita, Takato Ueno

Annotator disagreement in emotion classification reflects ambiguity intrinsic to emotion concepts and is essential for predictor-quality assessment in subjective NLP. Yet no prior work integrates soft-label learning with Bayesian deep learning to evaluate uncertainty along axes including annotator-distribution fidelity. We train a linear head on a frozen RoBERTa via cyclical stochastic gradient Markov chain Monte Carlo (cSG-MCMC), targeting the empirical annotator distribution with a soft-label objective under a five-axis evaluation. On the 28-emotion GoEmotions benchmark, the proposed method outperforms Monte Carlo Dropout and Deep Ensemble simultaneously on three axes -- Jensen-Shannon divergence (JSD) to the annotator distribution, Spearman correlation between per-emotion aleatoric uncertainty and disagreement, and selective-prediction Area Under the Risk-Coverage Curve (AURC) and Area Under the ROC Curve (AUROC) -- showing independent axes are jointly attainable from one posterior. Post-hoc temperature scaling exhibits a bidirectional effect, establishing hard-label calibration and annotator-JSD as independent dimensions and motivating joint reporting as an honest protocol.

Keito Inoshita, Xiaokang Zhou, Akira Kawai et al.

In practical deep learning deployment, the scarcity of data and the imbalance of label distributions often lead to semantically uncovered regions within the real-world data distribution, hindering model training and causing misclassification near class boundaries as well as unstable behaviors in peripheral areas. Although recent large language models (LLMs) show promise for data augmentation, an integrated framework that simultaneously achieves directional control of generation, domain alignment, and quality control has not yet been fully established. To address these challenges, we propose a Cluster-conditioned Interpolative and Extrapolative framework for Geometry-Aware and Domain-aligned data augmentation (CIEGAD), which systematically complements both in-distribution and out-of-distribution semantically uncovered regions. CIEGAD constructs domain profiles through cluster conditioning, allocates generation with a hierarchical frequency-geometric allocation integrating class frequency and geometric indicators, and finely controls generation directions via the coexistence of interpolative and extrapolative synthesis. It further performs quality control through geometry-constrained filtering combined with an LLM-as-a-Judge mechanism. Experiments on multiple classification tasks demonstrate that CIEGAD effectively extends the periphery of real-world data distributions while maintaining high alignment between generated and real-world data as well as semantic diversity. In particular, for long-tailed and multi-class classification tasks, CIEGAD consistently improves F1 and recall, validating the triple harmony of distributional consistency, diversity, and quality. These results indicate that CIEGAD serves as a practically oriented data augmentation framework that complements underrepresented regions while preserving alignment with real-world data.

Keito Inoshita, Nobuhiro Hayashida, Akira Imanishi

Multi-task learning for advanced driver assistance systems requires modeling the complex interplay between driver internal states and external traffic environments. However, existing methods treat recognition tasks as flat and independent objectives, failing to exploit the cognitive causal structure underlying driving behavior. In this paper, we propose CauPsi, a cognitive science-grounded causal multi-task learning framework that explicitly models the hierarchical dependencies among Traffic Context Recognition (TCR), Vehicle Context Recognition (VCR), Driver Emotion Recognition (DER), and Driver Behavior Recognition (DBR). The proposed framework introduces two key mechanisms. First, a Causal Task Chain propagates upstream task predictions to downstream tasks via learnable prototype embeddings, realizing the cognitive cascade from environmental perception to behavioral regulation in a differentiable manner. Second, Cross-Task Psychological Conditioning (CTPC) estimates a psychological state signal from driver facial expressions and body posture and injects it as a conditioning input to all tasks including environmental recognition, thereby modeling the modulatory effect of driver internal states on cognitive and decision-making processes. Evaluated on the AIDE dataset, CauPsi achieves a mean accuracy of 82.71% with only 5.05M parameters, surpassing prior work by +1.0% overall, with notable improvements on DER (+3.65%) and DBR (+7.53%). Ablation studies validate the independent contribution of each component, and analysis of the psychological state signal confirms that it acquires systematic task-label-dependent patterns in a self-supervised manner without explicit psychological annotations.

Keito Inoshita, Michiaki Omura, Tsukasa Yamanaka et al.

As Large Language Models (LLMs) have become capable of effortlessly generating high-quality text, traditional quality-focused writing assessment is losing its significance. If the essential goal of education is to foster critical thinking and original perspectives, assessment must also shift its paradigm from quality to originality. This study proposes Argument Rarity-based Originality Assessment (AROA), a framework for automatically evaluating argumentative originality in student essays. AROA defines originality as rarity within a reference corpus and evaluates it through four complementary components: structural rarity, claim rarity, evidence rarity, and cognitive depth. The framework quantifies the rarity of each component using density estimation and integrates them with a quality adjustment mechanism, thereby treating quality and originality as independent evaluation axes. Experiments using human essays and AI-generated essays revealed a strong negative correlation between quality and claim rarity, demonstrating a quality-originality trade-off where higher-quality texts tend to rely on typical claim patterns. Furthermore, while AI essays achieved comparable levels of structural complexity to human essays, their claim rarity was substantially lower than that of humans, indicating that LLMs can reproduce the form of argumentation but have limitations in the originality of content.

Keito Inoshita, Xiaokang Zhou, Akira Kawai et al.

Human annotators frequently disagree on emotion labels, yet most evaluations of Large Language Model (LLM) emotion annotation collapse these judgments into a single gold standard, discarding the distributional information that disagreement encodes. We ask whether LLMs capture the structure of this disagreement, not just majority labels, by comparing emotion judgment distributions between human annotators and four zero-shot LLMs, plus a fine-tuned RoBERTa baseline, across two complementary benchmarks: GoEmotions and EmoBank, totaling 640,000 LLM responses. Zero-shot models diverge substantially from human distributions, and in-domain fine-tuning, not model scale, is required to close the gap. We formalize a lexical-grounding gradient through a quantitative transparency score that predicts per-category human--LLM agreement: LLMs reliably capture emotions with explicit lexical markers but systematically fail on pragmatically complex emotions requiring contextual inference, a pattern that replicates across both categorical and continuous emotion frameworks. We further propose three lightweight post-hoc calibration methods that reduce the distributional gap by up to 14\%, and provide actionable guidelines for when LLM emotion annotations can, and cannot, substitute for human labeling.

Keito Inoshita, Michiaki Omura, Tsukasa Yamanaka et al.

While AI-assisted writing has been widely reported to improve essay quality, its impact on the structural diversity of student thinking remains unexplored. Analyzing 6,875 essays across five conditions (Human-only, AI-only, and three Human+AI prompt strategies), we provide the first empirical evidence of a Quality-Homogenization Tradeoff, in which substantial quality gains co-occur with significant homogenization. The effect is dimension-specific: cohesion architecture lost 70-78% of its variance, whereas perspective plurality was diversified. Convergence target analysis further revealed that AI-augmented essays were pulled toward AI structural patterns yet deviated significantly from the Human-AI axis, indicating simultaneous partial replacement and partial emergence. Crucially, prompt specificity reversed homogenization into diversification on argument depth, demonstrating that homogenization is not an intrinsic property of AI but a function of interaction design.

Keito Inoshita

Driver distraction behavior recognition using in-vehicle cameras demands real-time inference on edge devices. However, lightweight models often fail to capture fine-grained behavioral cues, resulting in reduced performance on unseen drivers or under varying conditions. ROI-based methods also increase computational cost, making it difficult to balance efficiency and accuracy. This work addresses the need for a lightweight architecture that overcomes these constraints. We propose Computationally efficient Dynamic region of Interest Routing and domain-invariant Adversarial learning for lightweight driver behavior recognition (C-DIRA). The framework combines saliency-driven Top-K ROI pooling and fused classification for local feature extraction and integration. Dynamic ROI routing enables selective computation by applying ROI inference only to high difficulty data samples. Moreover, pseudo-domain labeling and adversarial learning are used to learn domain-invariant features robust to driver and background variation. Experiments on the State Farm Distracted Driver Detection Dataset show that C-DIRA maintains high accuracy with significantly fewer FLOPs and lower latency than prior lightweight models. It also demonstrates robustness under visual degradation such as blur and low-light, and stable performance across unseen domains. These results confirm C-DIRA's effectiveness in achieving compactness, efficiency, and generalization.

Keito Inoshita, Shinnosuke Mizuno

Sarcasm understanding is a challenging problem in natural language processing, as it requires capturing the discrepancy between the surface meaning of an utterance and the speaker's intentions as well as the surrounding social context. Although recent advances in deep learning and Large Language Models (LLMs) have substantially improved performance, most existing approaches still rely on black-box predictions of a single model, making it difficult to structurally explain the cognitive factors underlying sarcasm. Moreover, while sarcasm often emerges as a mismatch between semantic evaluation and normative expectations or intentions, frameworks that explicitly decompose and model these components remain limited. In this work, we reformulate sarcasm understanding as a world model inspired reasoning process and propose World Model inspired SArcasm Reasoning (WM-SAR), which decomposes literal meaning, context, normative expectation, and intention into specialized LLM-based agents. The discrepancy between literal evaluation and normative expectation is explicitly quantified as a deterministic inconsistency score, and together with an intention score, these signals are integrated by a lightweight Logistic Regression model to infer the final sarcasm probability. This design leverages the reasoning capability of LLMs while maintaining an interpretable numerical decision structure. Experiments on representative sarcasm detection benchmarks show that WM-SAR consistently outperforms existing deep learning and LLM-based methods. Ablation studies and case analyses further demonstrate that integrating semantic inconsistency and intention reasoning is essential for effective sarcasm detection, achieving both strong performance and high interpretability.

Keito Inoshita

Predicting nationality from personal names has practical value in marketing, demographic research, and genealogical studies. Conventional neural models learn statistical correspondences between names and nationalities from task-specific training data, posing challenges in generalizing to low-frequency nationalities and distinguishing similar nationalities within the same region. Large language models (LLMs) have the potential to address these challenges by leveraging world knowledge acquired during pre-training. In this study, we comprehensively compare neural models and LLMs on nationality prediction, evaluating six neural models and six LLM prompting strategies across three granularity levels (nationality, region, and continent), with frequency-based stratified analysis and error analysis. Results show that LLMs outperform neural models at all granularity levels, with the gap narrowing as granularity becomes coarser. Simple machine learning methods exhibit the highest frequency robustness, while pre-trained models and LLMs show degradation for low-frequency nationalities. Error analysis reveals that LLMs tend to make ``near-miss'' errors, predicting the correct region even when nationality is incorrect, whereas neural models exhibit more cross-regional errors and bias toward high-frequency classes. These findings indicate that LLM superiority stems from world knowledge, model selection should consider required granularity, and evaluation should account for error quality beyond accuracy.

Keito Inoshita

In the attention economy, sensational content exposes consumers to excessive emotional stimulation, hindering calm decision-making. This study proposes Multi-Agent LLM-based Emotional deToxification (MALLET), a multi-agent information sanitization system consisting of four agents: Emotion Analysis, Emotion Adjustment, Balance Monitoring, and Personal Guide. The Emotion Analysis Agent quantifies stimulus intensity using a 6-emotion BERT classifier, and the Emotion Adjustment Agent rewrites texts into two presentation modes, BALANCED (neutralized text) and COOL (neutralized text + supplementary text), using an LLM. The Balance Monitoring Agent aggregates weekly information consumption patterns and generates personalized advice, while the Personal Guide Agent recommends a presentation mode according to consumer sensitivity. Experiments on 800 AG News articles demonstrated significant stimulus score reduction (up to 19.3%) and improved emotion balance while maintaining semantic preservation. Near-zero correlation between stimulus reduction and semantic preservation confirmed that the two are independently controllable. Category-level analysis revealed substantial reduction (17.8-33.8%) in Sports, Business, and Sci/Tech, whereas the effect was limited in the World category, where facts themselves are inherently high-stimulus. The proposed system provides a framework for supporting calm information reception of consumers without restricting access to the original text.

Keito Inoshita, Kota Nojiri, Haruto Sugeno et al.

Scientific names of organisms consist of a genus name and a species epithet, with the latter often reflecting aspects such as morphology, ecology, distribution, and cultural background. Traditionally, researchers have manually labeled species names by carefully examining taxonomic descriptions, a process that demands substantial time and effort when dealing with large datasets. This study evaluates the feasibility of automatic species name labeling using large language model (LLM) by leveraging their text classification and semantic extraction capabilities. Using the spider name dataset compiled by Mammola et al., we compared LLM-based labeling results-enhanced through prompt engineering-with human annotations. The results indicate that LLM-based classification achieved high accuracy in Morphology, Geography, and People categories. However, classification accuracy was lower in Ecology & Behavior and Modern & Past Culture, revealing challenges in interpreting animal behavior and cultural contexts. Future research will focus on improving accuracy through optimized few-shot learning and retrieval-augmented generation techniques, while also expanding the applicability of LLM-based labeling to diverse biological taxa.

Keito Inoshita

Large language models (LLMs) possess extensive world knowledge, yet methods for effectively eliciting this knowledge remain underexplored. Nationality and region prediction tasks require understanding of not only linguistic features but also cultural and historical background, making LLM world knowledge particularly valuable. However, conventional LLM prompting methods rely on direct reasoning approaches, which have limitations in applying abstract linguistic rules. We propose LLM Associative Memory Agents (LAMA), a novel framework that leverages LLM world knowledge as associative memory. Rather than directly inferring nationality from names, LAMA recalls famous individuals with the same name and aggregates their nationalities through indirect reasoning. A dual-agent architecture comprising a Person Agent and a Media Agent, specialized in different knowledge domains, recalls famous individuals in parallel, generating Top-1 predictions through voting and Top-K predictions through conditional completion. On a 99-country nationality prediction task, LAMA achieved 0.817 accuracy, substantially outperforming conventional LLM prompting methods and neural models. Our experiments reveal that LLMs exhibit higher reliability in recalling concrete examples than in abstract reasoning, that recall-based approaches are robust to low-frequency nationalities independent of data frequency distributions, and that the dual-agent architecture functions complementarily to produce synergistic effects. These results demonstrate the effectiveness of a new multi-agent system that retrieves and aggregates LLM knowledge rather than prompting reasoning.

Keito Inoshita, Rushia Harada

In the field of emotion recognition, the development of high-performance models remains a challenge due to the scarcity of high-quality, diverse emotional datasets. Emotional expressions are inherently subjective, shaped by individual personality traits, socio-cultural backgrounds, and contextual factors, making large-scale, generalizable data collection both ethically and practically difficult. To address this issue, we introduce PersonaGen, a novel framework for generating emotionally rich text using a Large Language Model (LLM) through multi-stage persona-based conditioning. PersonaGen constructs layered virtual personas by combining demographic attributes, socio-cultural backgrounds, and detailed situational contexts, which are then used to guide emotion expression generation. We conduct comprehensive evaluations of the generated synthetic data, assessing semantic diversity through clustering and distributional metrics, human-likeness via LLM-based quality scoring, realism through comparison with real-world emotion corpora, and practical utility in downstream emotion classification tasks. Experimental results show that PersonaGen significantly outperforms baseline methods in generating diverse, coherent, and discriminative emotion expressions, demonstrating its potential as a robust alternative for augmenting or replacing real-world emotional datasets.

Rushia Harada, Yuken Kimura, Keito Inoshita

Well-being in family settings involves subtle psychological dynamics that conventional metrics often overlook. In particular, unconscious parental expectations, termed ideal parent bias, can suppress children's emotional expression and autonomy. This suppression, referred to as suppressed emotion, often stems from well-meaning but value-driven communication, which is difficult to detect or address from outside the family. Focusing on these latent dynamics, this study explores Large Language Model (LLM)-based support for psychologically safe family communication. We constructed a Japanese parent-child dialogue corpus of 30 scenarios, each annotated with metadata on ideal parent bias and suppressed emotion. Based on this corpus, we developed a Role-Playing LLM-based multi-agent dialogue support framework that analyzes dialogue and generates feedback. Specialized agents detect suppressed emotion, describe implicit ideal parent bias in parental speech, and infer contextual attributes such as the child's age and background. A meta-agent compiles these outputs into a structured report, which is then passed to five selected expert agents. These agents collaboratively generate empathetic and actionable feedback through a structured four-step discussion process. Experiments show that the system can detect categories of suppressed emotion with moderate accuracy and produce feedback rated highly in empathy and practicality. Moreover, simulated follow-up dialogues incorporating this feedback exhibited signs of improved emotional expression and mutual understanding, suggesting the framework's potential in supporting positive transformation in family interactions.

Takato Ueno, Keito Inoshita

Japan's kairanban culture and idobata conversations have long functioned as traditional communication practices that foster nuanced dialogue among community members and contribute to the formation of social balance. Inspired by these information exchange processes, this study proposes a multi-agent inference framework (KCS+IBC) that integrates multiple large language models (LLMs) to achieve bias mitigation, improved explainability, and probabilistic prediction in sentiment analysis. In addition to sequentially sharing prediction results, the proposed method incorporates a mid-phase casual dialogue session to blend formal inference with individual perspectives and introduces probabilistic sentiment prediction. Experimental results show that KCS achieves accuracy comparable to that of a single LLM across datasets, while KCS+IBC exhibits a consistent decrease in entropy and a gradual increase in variance during the latter stages of inference, suggesting the framework's ability to balance aggregation and diversity of predictions. Future work will quantitatively assess the impact of these characteristics on bias correction and aim to develop more advanced sentiment analysis systems.