Overcoming Knowledge Discrepancies: Structuring Reasoning Threads through Knowledge Balancing in Interactive Scenarios
This addresses the problem of improving reasoning in interactive problem-solving for users by providing structured and effective guidance, though it appears incremental as it builds on existing methods.
The paper tackled the problem of reasoning models lacking explicit semantic hierarchies and user-domain knowledge alignment in interactive scenarios, resulting in lengthy generic output, by proposing the ReT-Eval framework, which enhances user understanding and outperforms state-of-the-art reasoning models.
Reasoning in interactive problem solving scenarios requires models to construct reasoning threads that reflect user understanding and align with structured domain knowledge. However, current reasoning models often lack explicit semantic hierarchies, user-domain knowledge alignment, and principled mechanisms to prune reasoning threads for effectiveness. These limitations result in lengthy generic output that does not guide users through goal-oriented reasoning steps. To address this, we propose a prototype-inspired, two-phases Reasoning-Threads-Evaluation (ReT-Eval) framework, drawing inspiration from human-like reasoning strategies that emphasize structured knowledge reuse. In the first phase, semantically relevant knowledge structures are extracted from a sparse domain knowledge graph using a graph neural network and enriched with intrinsic large language model knowledge to resolve knowledge discrepancies. In the second phase, these threads are evaluated and pruned using a reward-guided strategy aimed at maintaining semantic coherence to generate effective reasoning threads. Experiments and expert evaluations show that ReT-Eval enhances user understanding and outperforms state-of-the-art reasoning models.