Learning Japanese with Jouzu: Interaction Outcomes with Stylized Dialogue Fictional Agents

This study investigates how stylized, voiced agents shape user interaction in a multimodal language learning environment. We conducted a mixed-methods evaluation of 54 participants interacting with anime-inspired characters powered by large language models and expressive text-to-speech synthesis. These agents responded in Japanese character language, offering users asynchronous, semi-structured conversation in varying speech styles and emotional tones. We analyzed user engagement patterns, perceived usability, emotional responses, and learning behaviors, with particular attention to how agent stylization influenced interaction across language proficiency levels and cultural backgrounds. Our findings reveal that agent design, especially voice, persona, and linguistic style, substantially affected user experience, motivation, and strategy. This work contributes to the understanding of affective, culturally stylized agents in human-agent interaction and offers guidance for designing more engaging, socially responsive systems.

Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects

While text-based emotion recognition methods have achieved notable success, real-world dialogue systems often demand a more nuanced emotional understanding than any single modality can offer. Multimodal Emotion Recognition in Conversations (MERC) has thus emerged as a crucial direction for enhancing the naturalness and emotional understanding of human-computer interaction. Its goal is to accurately recognize emotions by integrating information from various modalities such as text, speech, and visual signals. This survey offers a systematic overview of MERC, including its motivations, core tasks, representative methods, and evaluation strategies. We further examine recent trends, highlight key challenges, and outline future directions. As interest in emotionally intelligent systems grows, this survey provides timely guidance for advancing MERC research.

Benchmarking Expressive Japanese Character Text-to-Speech with VITS and Style-BERT-VITS2

Synthesizing expressive Japanese character speech poses unique challenges due to pitch-accent sensitivity and stylistic variability. This paper benchmarks two open-source text-to-speech models--VITS and Style-BERT-VITS2 JP Extra (SBV2JE)--on in-domain, character-driven Japanese speech. Using three character-specific datasets, we evaluate models across naturalness (mean opinion and comparative mean opinion score), intelligibility (word error rate), and speaker consistency. SBV2JE matches human ground truth in naturalness (MOS 4.37 vs. 4.38), achieves lower WER, and shows slight preference in CMOS. Enhanced by pitch-accent controls and a WavLM-based discriminator, SBV2JE proves effective for applications like language learning and character dialogue generation, despite higher computational demands.

VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering

We introduce VoxRAG, a modular speech-to-speech retrieval-augmented generation system that bypasses transcription to retrieve semantically relevant audio segments directly from spoken queries. VoxRAG employs silence-aware segmentation, speaker diarization, CLAP audio embeddings, and FAISS retrieval using L2-normalized cosine similarity. We construct a 50-query test set recorded as spoken input by a native English speaker. Retrieval quality was evaluated using LLM-as-a-judge annotations. For very relevant segments, cosine similarity achieved a Recall@10 of 0.34. For somewhat relevant segments, Recall@10 rose to 0.60 and nDCG@10 to 0.27, highlighting strong topical alignment. Answer quality was judged on a 0--2 scale across relevance, accuracy, completeness, and precision, with mean scores of 0.84, 0.58, 0.56, and 0.46 respectively. While precision and retrieval quality remain key limitations, VoxRAG shows that transcription-free speech-to-speech retrieval is feasible in RAG systems.

Mixed Signals: Understanding Model Disagreement in Multimodal Empathy Detection

Multimodal models play a key role in empathy detection, but their performance can suffer when modalities provide conflicting cues. To understand these failures, we examine cases where unimodal and multimodal predictions diverge. Using fine-tuned models for text, audio, and video, along with a gated fusion model, we find that such disagreements often reflect underlying ambiguity, as evidenced by annotator uncertainty. Our analysis shows that dominant signals in one modality can mislead fusion when unsupported by others. We also observe that humans, like models, do not consistently benefit from multimodal input. These insights position disagreement as a useful diagnostic signal for identifying challenging examples and improving empathy system robustness.

Personalized Attacks of Social Engineering in Multi-turn Conversations -- LLM Agents for Simulation and Detection

The rapid advancement of conversational agents, particularly chatbots powered by Large Language Models (LLMs), poses a significant risk of social engineering (SE) attacks on social media platforms. SE detection in multi-turn, chat-based interactions is considerably more complex than single-instance detection due to the dynamic nature of these conversations. A critical factor in mitigating this threat is understanding the mechanisms through which SE attacks operate, specifically how attackers exploit vulnerabilities and how victims' personality traits contribute to their susceptibility. In this work, we propose an LLM-agentic framework, SE-VSim, to simulate SE attack mechanisms by generating multi-turn conversations. We model victim agents with varying personality traits to assess how psychological profiles influence susceptibility to manipulation. Using a dataset of over 1000 simulated conversations, we examine attack scenarios in which adversaries, posing as recruiters, funding agencies, and journalists, attempt to extract sensitive information. Based on this analysis, we present a proof of concept, SE-OmniGuard, to offer personalized protection to users by leveraging prior knowledge of the victims personality, evaluating attack strategies, and monitoring information exchanges in conversations to identify potential SE attempts.

SYNTHEMPATHY: A Scalable Empathy Corpus Generated Using LLMs Without Any Crowdsourcing

Previous research has shown that humans are more receptive towards language models that that exhibit empathetic behavior. While empathy is essential for developing helpful dialogue agents, very few large corpora containing empathetic dialogues are available for fine-tune LLMs. The few existing corpora have largely relied on crowdsourcing to simulate empathetic conversations, a process that is expensive, time-consuming, and not scalable to larger datasets. We propose a data generation framework for developing SYNTHEMPATHY, a large corpus containing 105k empathetic responses to real-life situations compiled through LLM generation. A base Mistral 7B model fine-tuned on our SYNTHEMPATHY corpus exhibits an increase in the average empathy score.

Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges

Understanding pragmatics-the use of language in context-is crucial for developing NLP systems capable of interpreting nuanced language use. Despite recent advances in language technologies, including large language models, evaluating their ability to handle pragmatic phenomena such as implicatures and references remains challenging. To advance pragmatic abilities in models, it is essential to understand current evaluation trends and identify existing limitations. In this survey, we provide a comprehensive review of resources designed for evaluating pragmatic capabilities in NLP, categorizing datasets by the pragmatics phenomena they address. We analyze task designs, data collection methods, evaluation approaches, and their relevance to real-world applications. By examining these resources in the context of modern language models, we highlight emerging trends, challenges, and gaps in existing benchmarks. Our survey aims to clarify the landscape of pragmatic evaluation and guide the development of more comprehensive and targeted benchmarks, ultimately contributing to more nuanced and context-aware NLP models.

Can Open-source LLMs Enhance Data Synthesis for Toxic Detection?: An Experimental Study

Effective toxic content detection relies heavily on high-quality and diverse data, which serves as the foundation for robust content moderation models. This study explores the potential of open-source LLMs for harmful data synthesis, utilizing prompt engineering and fine-tuning techniques to enhance data quality and diversity. In a two-stage evaluation, we first examine the capabilities of six open-source LLMs in generating harmful data across multiple datasets using prompt engineering. In the second stage, we fine-tune these models to improve data generation while addressing challenges such as hallucination, data duplication, and overfitting. Our findings reveal that Mistral excels in generating high-quality and diverse harmful data with minimal hallucination. Furthermore, fine-tuning enhances data quality, offering scalable and cost-effective solutions for augmenting datasets for specific toxic content detection tasks. These results emphasize the significance of data synthesis in building robust, standalone detection models and highlight the potential of open-source LLMs to advance smaller downstream content moderation systems. We implemented this approach in real-world industrial settings, demonstrating the feasibility and efficiency of fine-tuned open-source LLMs for harmful data synthesis.

Can Open-source LLMs Enhance Data Augmentation for Toxic Detection?: An Experimental Study

High-quality, diverse harmful data is essential to addressing real-time applications in content moderation. Current state-of-the-art approaches to toxic content detection using GPT series models are costly and lack explainability. This paper investigates the use of prompt engineering and fine-tuning techniques on open-source LLMs to enhance harmful data augmentation specifically for toxic content detection. We conduct a two-stage empirical study, with stage 1 evaluating six open-source LLMs across multiple datasets using only prompt engineering and stage 2 focusing on fine-tuning. Our findings indicate that Mistral can excel in generating harmful data with minimal hallucination. While fine-tuning these models improves data quality and diversity, challenges such as data duplication and overfitting persist. Our experimental results highlight scalable, cost-effective strategies for enhancing toxic content detection systems. These findings not only demonstrate the potential of open-source LLMs in creating robust content moderation tools. The application of this method in real industrial scenarios further proves the feasibility and efficiency of the fine-tuned open-source LLMs for data augmentation. We hope our study will aid in understanding the capabilities and limitations of current models in toxic content detection and drive further advancements in this field.