conversational-ai
Filtering by topic conversational-ai(3)Clear all filters
- PaperComputers and Education: Artificial Intelligence22 Jun 2026
Conversational AI as a catalyst for informal learning: An empirical large-scale study on LLM use in everyday learning
Nađa Terzimehić, Babette Bühler, Enkelejda Kasneci
A large-scale survey of 776 German participants reveals that 88% already incorporate LLMs into everyday informal learning routines. Young adults are at the forefront, using LLMs to enhance learning independently of time and space, and four distinct learner types emerge based on tasks and devices. The study also highlights paradoxical user behaviors regarding trust in LLM accuracy and privacy, emphasizing the need for diverse media, collaborative learning, and source transparency.
Original abstract
Large language models have not only captivated the public imagination but have also sparked a profound rethinking of how we learn. In the third year following the breakthrough launch of ChatGPT, everyday informal learning has been transformed as these novel tools become easily and widely available. Who is embracing LLMs for self-directed learning, and who remains hesitant? What are their reasons for adoption or avoidance? What learning patterns emerge with this novel technological landscape? We present an in-depth analysis from a large-scale survey of 776 German participants, showcasing that 88% of our respondents already incorporate LLMs into their everyday learning routines for a wide variety of (learning) tasks. Young adults among German-based, digitally engaged users are at the forefront of adopting LLMs, primarily to enhance their learning experiences independently of time and space. Four types of learners emerge across learning contexts, depending on the tasks they perform with LLMs and the devices they use to access them. Interestingly, our respondents exhibit paradoxical behaviours regarding their trust in LLMs’ accuracy and privacy protection measures. Our implications emphasize the importance of including different media types for learning, enabling collaborative learning, providing sources and meeting the needs of different types of learners and learning by design.
- PaperarXiv — Language & NLP (cs.CL)21 May 2026
From Lexicon to AI: A Structured-Data Pipeline for Specialized Conversational Systems in Low-Resource Languages
Siddhant Hitesh Mantri, Dhara Gorasiya, Malhar Kulkarni, Pushpak Bhattacharya
Researchers transformed Hindi WordNet into 1.25 million instruction-response pairs to fine-tune a 12B-parameter language model, creating a Hindi language learning chatbot. The system achieved higher pedagogical effectiveness (91.0) than general-purpose models (79.4-83.6), demonstrating that structured linguistic resources can enable specialized conversational AI for low-resource languages.
Original abstract
Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training corpora. We present a systematic methodology for transforming structured linguistic resources into specialized AI systems, demonstrating that expert-curated lexical databases can serve as effective foundations for conversational AI development. Our approach converts Hindi WordNet into 1.25 million diverse instruction-response pairs, fine-tunes a 12B-parameter language model using resource-efficient LoRA with 4-bit quantization. Evaluation through a Hindi language learning chatbot demonstrates that structured-knowledge-based systems achieve superior pedagogical effectiveness (91.0 vs. 79.4-83.6 for general-purpose models) while maintaining competitive semantic performance and exceptional consistency. The complete pipeline demonstrates a proof-of-concept methodology using Hindi for developing specialized AI systems for any languages with WordNet resources. This work addresses the critical gap in AI accessibility for low-resource languages, offering a practical alternative to corpus-intensive approaches and potentially enabling specialized AI development for the hundreds of languages with existing WordNet resources.
- PaperarXiv — Language & NLP (cs.CL)18 May 2026
Bridging the Gap: Converting Read Text to Conversational Dialogue
Parshav Singla, Agnik Banerjee, Aaditya Arora, Shruti Aggarwal et al.
A novel approach, Prosodic Adjustment with Conversational Context (PACC), converts read speech into conversational speech using HiFi-GAN, improving naturalness and intelligibility. The method modifies prosodic features like intonation and rhythm, achieving better MOS scores. This technique has applications in virtual assistants and language learning tools.
Original abstract
In recent advancements within speech processing, converting read speech to conversational speech has gained significant attention. The primary challenge in this domain is maintaining naturalness and intelligibility while minimizing computational overhead for real-time applications. Traditional read speech often lacks the nuanced prosodic variation essential for natural conversational interactions, posing challenges for applications in virtual assistants, customer service, and language learning tools. This paper introduces a novel approach, Prosodic Adjustment with Conversational Context (PACC), aimed at converting read speech into natural conversational speech used in various modern applications. PACC utilizes advanced deep neural networks to analyze and modify prosodic features such as intonation, stress, and rhythm. Unlike conventional methods, our approach uses High-Fidelity Generative Adversarial Networks (HiFi-GAN) for speech synthesis. Our experimental results demonstrate significant improvements in speech conversion, enhancing naturalness and achieving better model accuracy with additional training on speech datasets. This research establishes new benchmarks in speech conversion tasks and Mean Opinion Score (MOS) evaluation for testing model accuracy, and we show that our approach can be successfully extended to other speech conversion applications.