5 papers
One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail
Zhaoyang Jiang, Zhizhong Fu, Yunsoo Kim +5
Given a patient's clinical findings, a diagnostic system ranks possible diseases and must decide when to endorse its first prediction or defer it for review. This decision is usual…
Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluation
Zhaoyang Jiang, Zhizhong Fu, Zicheng Li +5
AI systems increasingly retrieve from records that revise themselves: issue threads, encyclopedic histories, policy logs, and long conversations. The challenge is not only finding…
Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation
Zhaoyang Jiang, Xuanqi Peng, Fei Teng +5
Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but it is typically evaluated by final-answer metrics including accuracy. We ask…
HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds
Honghan Wu, Tianyan Wang, Jiacong Mi +2
Rare semantic innovations in high-dimensional, mission-critical domains are often obscured by dense background contexts, a challenge we define as \textit{feature density conflict}.…
A Regime Theory of Controller Class Selection for LLM Action Decisions
Zhaoyang Jiang, Zhizhong Fu, Yunsoo Kim +4
Deployed language and vision-language models must decide, on each input, whether to answer directly, retrieve evidence, defer to a stronger model, or abstain. Contrary to the commo…