Search papers, labs, and topics across Lattice.
Rose-SQL is introduced as a training-free framework that uses in-context learning with small-scale Large Reasoning Models (LRMs) for multi-turn Text-to-SQL tasks. It employs a Role-State representation to bridge schema linking and SQL generation, and tracks the evolution of this Role-State through historical context using structural isomorphism checks. Experiments on SParC and CoSQL show Rose-SQL outperforms in-context learning baselines at the 4B scale and surpasses fine-tuned models at the 8B and 14B scales within the Qwen3 series.
Rose-SQL achieves state-of-the-art multi-turn Text-to-SQL performance with small models, outperforming larger fine-tuned models without any training.
Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought have demonstrated remarkable capabilities in code generation and mathematical reasoning. However, their potential in multi-turn Text-to-SQL tasks remains largely underexplored. Existing approaches typically rely on unstable API-based inference or require expensive fine-tuning on small-scale models. In this work, we present Rose-SQL, a training-free framework that leverages small-scale LRMs through in-context learning to enable accurate context-dependent parsing. We introduce the Role-State, a fine-grained representation that bridges the structural gap between schema linking and SQL generation by serving as a structural blueprint. To handle conversational dependencies, Rose-SQL traces the evolution of Role-State through historical context via structural isomorphism checks, guiding the model to infer the possible SQL composition for the current question through verified interaction trajectories. Experiments on the SParC and CoSQL benchmarks show that, within the Qwen3 series, Rose-SQL outperforms in-context learning baselines at the 4B scale and substantially surpasses state-of-the-art fine-tuned models at the 8B and 14B scales, while showing consistent gains on additional reasoning backbones.
