Search papers, labs, and topics across Lattice.
The paper introduces SABA, a reasoning framework designed to mitigate logical inertia in LLMs by promoting self-awareness of incomplete premises before decision-making. SABA employs Information Fusion to create a verifiable base state from the narrative, followed by Query-driven Structured Reasoning to identify and resolve missing information through iterative query generation and state refinement. Experiments on the Detective Puzzle benchmark and other public datasets demonstrate that SABA outperforms existing methods across various difficulty levels.
LLMs can overcome flawed initial hypotheses and achieve state-of-the-art reasoning by proactively identifying and resolving missing information before committing to a solution.
Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is complete. In non-interactive puzzle settings, the narrative is fixed and the underlying structure is hidden; once a model forms an early hypothesis under incomplete premises, it can propagate that error throughout the reasoning process, leading to unstable conclusions. To address this issue, we propose SABA, a reasoning framework that explicitly introduces self-awareness of missing premises before making the final decision. SABA formulates reasoning as a recursive process that alternates between structured state construction and obstacle resolution: it first applies Information Fusion to consolidate the narrative into a verifiable base state, and then uses Query-driven Structured Reasoning to identify and resolve missing or underspecified premises by turning them into queries and progressively completing the reasoning state through hypothesis construction and state refinement. Across multiple evaluation metrics, SABA achieves the best performance on all three difficulty splits of the non-interactive Detective Puzzle benchmark, and it also maintains leading results on multiple public benchmarks.
