IBM at SIGMOD + PODS 2026

Conversational Question Answering over Knowledge Graphs (KGs) combines the factual grounding of KG-based QA with the interactive nature of dialogue systems. KGs are widely used in enterprise and domain applications to provide structured, evolving, and reliable knowledge. Large language models (LLMs) enable natural and context-aware conversations, but lack direct access to private and dynamic KGs. Retrieval-augmented generation (RAG) systems can retrieve graph content but often serialize structure, struggle with multi-turn context, and require heavy indexing. Traditional KGQA systems preserve structure but typically support only single-turn QA, incur high latency, and struggle with coreference and context tracking. To address these limitations, we propose Chatty-KG, a modular multi-agent system for conversational QA over KGs. Chatty-KG combines RAG-style retrieval with structured execution by generating SPARQL queries through task-specialized LLM agents. These agents collaborate for contextual interpretation, dialogue tracking, entity and relation linking, and efficient query planning, enabling accurate and low-latency translation of natural questions into executable queries. Experiments on large and diverse KGs show that Chatty-KG significantly outperforms state-of-the-art baselines in both single-turn and multi-turn settings, achieving higher F1 and P@1 scores. Its modular design preserves dialogue coherence and supports evolving KGs without fine-tuning or pre-processing. Evaluations with commercial (e.g., GPT-4o, Gemini-2.0) and open-weight (e.g., Phi-4, Gemma 3) LLMs confirm broad compatibility and stable performance. Overall, Chatty-KG unifies conversational flexibility with structured KG grounding, offering a scalable and extensible approach for reliable multi-turn KGQA.

Manish Kesarwani (IBM Research), Jayant R. Haritsa (Indian Institute of Science)

Thursday: 11 am to 12:30 pm - Part I Thursday: 4 pm to 5 pm - Part-II

Abstract: Recent advances in quantum computing have led to early-stage platforms with over 1,000 qubits, alongside roadmaps targeting fault-tolerant, industry-scale systems within this decade. To harness the immense potential of these emerging systems, it is essential to explore the feasibility of hosting relational database engines on quantum platforms. Encouragingly, several early studies have already investigated the applicability of quantum computing to core DBMS components such as multi-query optimization, join-order optimization and index-configuration selection offering initial insights into key challenges and practical implementation considerations.

In this tutorial, we provide an in-depth exploration of how quantum computing can be harnessed to advance database technologies. We begin by introducing the foundational principles of quantum computation and then outline the distinct technical challenges that emerge when operating on quantum hardware. The discussion proceeds to quantum-driven optimization methods, applicable to various DBMS components such as query optimization and physical schema design. Subsequently, we examine quantum-based query execution for core relational operators, emphasizing the architectural strategies proposed to work around the probabilistic computational framework. We conclude by outlining open research problems that must be solved to realize practical quantum databases.

In the concluding segment, participants will engage in a comprehensive demonstration, followed by a practical session where they will design quantum database algorithms and deploy them on both quantum simulators and real quantum hardware.