OG-Rank: Learning to Rank Fast and Slow with Uncertainty and Reward-Trend Guided Adaptive Exploration
This provides a practical solution for clinicians needing real-time, justifiable ranking systems, though it appears incremental as it adapts existing ranking and generation techniques to a specific domain.
The paper tackles the problem of creating low-latency ranking systems for clinical decision-making by introducing OG-Rank, a single-decoder approach that scores candidates quickly and generates explanations only when uncertainty is high. It achieves Recall@1 of 0.45-0.56 and nDCG@20 of 0.625-0.699 on encounter-scoped order selection, with a 45% gate rate for explanations.
Clinicians need ranking systems that work in real time and still justify their choices. Motivated by the need for a low-latency, decoder-based reranker, we present OG-Rank, a single-decoder approach that pairs a pooled first-token scoring signal with an uncertainty-gated explanation step. The model scores all candidates in one pass and generates a brief, structured rationale only when the list is genuinely ambiguous, keeping latency predictable. Trained with a curriculum that concentrates effort on hard cases, OG-Rank delivers strong effectiveness on encounter-scoped order selection (fast path: Recall@1~0.45, nDCG@20~0.625) and improves further when the gate activates (Recall@1~0.56, nDCG@20~0.699 at a 45\% gate rate), while compact backbones show similar gains under the same policy. Encoder baselines trail in both effectiveness and flexibility. The result is a practical recipe: rank fast by default and explain when it helps, a pattern that applies broadly to decision tasks where selective generation buys accuracy at acceptable cost. The single-policy design simplifies deployment and budget planning, and the curriculum principle (spend more on the hard cases, less on the easy ones) readily transfers beyond clinical order selection.