Large Language Models and Foundation Models
• Training, fine tuning, and alignment of LLMs
• Instruction following, preference optimization, and RLHF
• Constitutional AI and self alignment
• Mechanistic interpretability and model internals
• Retrieval Augmented Generation (RAG) and knowledge augmented LLMs
• Long context modeling, memory augmented architectures, and recurrent LLMs
• Efficient LLMs: compression, distillation, quantization, pruning
• Multilingual, cross lingual, and low resource LLMs
• Evaluation of LLMs: behavioral, safety, robustness, and benchmarking
• LLM as a judge and automated evaluation frameworks
NLP Agents, Reasoning and Autonomous Systems
• LLM based agents and tool use
• Multi agent systems, emergent behavior, and collective intelligence
• Planning, reasoning, and multi step problem solving
• Workflow synthesis, tool orchestration, and agentic pipelines
• Social simulation using LLM agents
• Embodied AI and language conditioned robotics
• Simulation environments for agent evaluation
Core Natural Language Processing
• Syntax, semantics, pragmatics, and discourse
• Information extraction, information retrieval, and text mining
• Question answering, machine reading, and knowledge intensive NLP
• Dialogue systems, conversational AI, and speech language integration
• Argumentation mining, stance detection, and opinion analysis
• Corpus linguistics and large scale corpus analysis
• Causal inference for NLP
Multimodal and Generative AI
• Vision language, audio language, and video language models
• Cross modal retrieval, grounding, and alignment
• Generative models for text, image, audio, and video
• Narrative generation, creative AI, and story understanding
• Spatial, 3D, and embodied multimodal models
Big Data, Knowledge Systems and Web Scale Intelligence
• Big data analytics and scalable machine learning
• Knowledge graphs, semantic web, and linked data
• Ontologies and semantic processing
• Web and social media analytics
• Data governance, provenance, and dataset auditing
• Data contamination detection and dataset filtering
• Synthetic data generation and data augmentation
• Data centric AI and dataset quality optimization
Trustworthy, Safe and Responsible AI
• Fairness, accountability, transparency, and ethics in NLP
• Bias detection and mitigation in language models
• Privacy preserving NLP (federated learning, differential privacy)
• Adversarial attacks, robustness, and red teaming
• Hallucination detection and mitigation
• Safety evaluation and secure deployment of LLMs
• Governance, auditing, and regulatory compliance for AI systems
• Eco responsible AI and energy efficient NLP
Applied NLP and Domain Specific Intelligence
• NLP for healthcare, biomedical text, and scientific discovery
• NLP for law, finance, policy, and government
• NLP for education, tutoring, and assessment
• Computational social science using NLP
• NLP for climate, sustainability, and social good
• Domain adapted and specialized LLMs
NLP for Emerging Computing Paradigms
• Edge, mobile, and embedded NLP systems
• Personalized and adaptive NLP systems
• Continual learning and lifelong adaptation
• NLP for IoT and smart environments
• NLP for robotics and human robot interaction
• NLP in AR/VR and spatial computing
Code, Math and Scientific NLP
• Code LLMs, program synthesis, and natural language for programming
• Automated software engineering with LLM agents
• Mathematical reasoning and MathNLP
• NLP for scientific literature, discovery, and hypothesis generation
• Knowledge editing, model patching, and fact updating
• Neuro symbolic reasoning and hybrid systems
Cognitive Modeling, NeuroAI and Human Centered NLP
• Cognitive modeling with LLMs
• Brain language alignment and neural decoding
• Human AI collaboration and co creativity
• Social grounding, cultural adaptation, and anthropological NLP
• Human in the loop NLP and interactive learning
Evaluation, Methodology and Reproducibility
• Benchmark creation and dataset design
• Reproducibility, transparency, and open science
• Error analysis, interpretability, and explainability
• Meta evaluation and evaluation of evaluators
• Automated benchmark generation
Systems, Infrastructure and Optimization
• Distributed training and inference for large models
• High performance computing for NLP and big data
• Scalable architectures for real time NLP applications
• Model serving, deployment, and monitoring at scale
• Energy efficient and carbon aware model training

Hard copy of the proceedings will be distributed during the Conference. The softcopy will be available on AIRCC digital library.