📢 Announcement
The Fifth Workshop on Low Resource Cross-Domain, Cross-Lingual, and Cross-Modal Content Analysis (LC4) invites submissions addressing novel techniques for detecting, classifying, and modeling multimedia content under cross-domain, cross-lingual, and cross-modal settings. With the proliferation of the internet and the advent of generative AI and Large Language Models (LLMs), the creation and spread of multimedia content across diverse platforms have intensified. This raises new challenges in agentic content monitoring, adaptive reasoning, and trust-aware decision-making, particularly in low-resource settings. Invited speakers and final dates will be announced soon. Official site: lc4workshop.github.io.
Submission now open via OpenReview.
Mode: In‑person workshop with remote presentation option for participants who cannot travel.
🎯 Overview
LC4 invites work on novel computational methods to detect, classify, and model multimedia content across domains, languages, and modalities— with a special focus on Agentic AI & Autonomous Multimodal Intelligence , Low-Resource and Cross-Lingual Learning, and Human-Centered and Responsible AI in supervision‑sparse settings. We especially welcome contributions that leverage foundational models (LLMs and multimodal agents) for robust, interpretable, and socially impactful analysis in low‑resource contexts.
🧩 Topics of Interest
Agentic AI & Autonomous Multimodal Intelligence
- Agentic workflows for multilingual analysis
- Large Language Models (LLMs)
- Vision-Language Foundation Models (VLMs)
- Speech Foundation Models
- Retrieval-Augmented Generation (RAG)
- Agentic AI for multimedia analysis
- Multi-agent collaboration for content understanding
- Parameter-efficient fine-tuning and prompting strategies
- Multimodal document intelligence
- OCR and document understanding for low-resource scripts
Low-Resource and Cross-Lingual Learning
- Multilingual and low-resource language models
- Transfer learning for underrepresented languages
- Cross-lingual retrieval and semantic alignment
- Multilingual summarization, question answering, and information extraction
- Code-mixed misinformation detection
- Cross-lingual knowledge transfer
- Synthetic data generation
- Indigenous and endangered language resources
Human-Centered and Responsible AI
- Human–AI collaborative fact-checking
- Annotation quality and consensus modeling
- Bias and fairness in moderation systems
- Privacy-preserving misinformation analysis
- Transparent and interpretable AI systems
- Ethical deployment in sensitive contexts
Invited Speakers: TBA
📅 Key Dates TBA
🧑⚖️ Program Committee
- Bhuvana J, Shiv Nadar University, Chennai, India
- Dhanalakshmi V, Subramania Bharathi School of Tamil Language & Literature, Pondicherry University, India
- Ramesh Kannan R, Vellore Institute of Technology, Chennai, India
- Dhivya Chinnappa, JP Morgan Chase & Co., Texas, USA
- Onkar Krishna, Hitachi Ltd., Japan
- Sathyaraj T, Sri Krishna Adithya College of Arts and Science, Coimbatore, India
- Sharath Kumar, Hitachi India R&D, India
- Soubraylu Sivakumar, SRM Institute of Science and Technology, Chennai, India
- Vaishali Ganganwar, Army Institute of Technology, Pune, India
- Yuta Koreeda, Hitachi Ltd., Japan
📚 Selected References
- Sakshi Gupta, Shunmuga Priya Muthusamy Chinnan, Saranya Rajiakodi, Ratnavel Rajalakshmi, and Bharathi Raja Chakravarthi. 2026. GYAAN-SAHIT: A Persona-Driven Multi-Agent Framework for Caste-Based Hate Speech Detection. In Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 76–90, Association for Computational Linguistics.
- Rajalakshmi, R., Karmarkar, O.P., Mallik, B. (2026). Multilingual Content Moderation: Advanced Hate Speech Detection with XLM-RoBERTa. In: Bhateja, V., El Barachi, M., Azar, A.T., Sharma, D.K. (eds) Information System Design: Big Data Analytics and Data Science. ISDIA 2025. Lecture Notes in Networks and Systems, vol 1539. Springer, Singapore. https://doi.org/10.1007/978-981-96-9248-4_6
- Premjith B, Jyothish Lal G, Bharathi Raja Chakravarthi, Saranya Rajiakodi, Thenmozhi Durairaj, Ratnavel Rajalakshmi, Rahul Ponnusamy, and Chinthala Bhuvanesh. 2026. Shared Task on Prompt Style Recovery for Large Language Models in Telugu. In Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 124–133, Underline (Virtual). Association for Computational Linguistics.
- Shibani, A., Mattins, F., Selvaraj, S., Rajalakshmi, R., & Bharathy, G. (2024). Tamil Co-Writer: Towards Inclusive Use of Generative AI for Writing Support. In LAK Workshops (pp. 240-248).
- Manikandan Ravikiran, Ratnavel Rajalakshmi, Bharathi Raja Chakravarthi, Anand Kumar Madasamy, and Sajeetha Thavareesan. 2024. Findings of the First Shared Task on Offensive Span Identification from Code-Mixed Kannada-English Comments. In Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 43–48, St. Julian's, Malta. Association for Computational Linguistics.
- Ravikiran, M., Chakravarthi, B., Madasamy, A.B., Sivanesan, S., Rajalakshmi, R., Thavareesan, S., Ponnusamy, R., & Mahadevan., S. (2022). Findings of the Shared Task on Offensive Span Identification fromCode-Mixed Tamil-English Comments. ArXiv, abs/2205.06118.