Jieping Ye

When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment

The reasoning trajectory of a Large Language Model (LLM) is often treated as a verbalized description of its internal reasoning. However, such trajectories can be unfaithful: a model may rely on shortcuts to reach an answer and then post-rationalize the decision with a seemingly coherent chain of thought. Detecting thi...

When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models

To mitigate the refusal-cue shortcut, sparse complementary masking is adapted as a lightweight post-hoc intervention that identifies and suppresses a small set of shortcut-associated attention heads and MLP neurons without retraining and achieves an approximately 79% relative reduction in response-initial detection fai...

DDPT: Enhancing complex reasoning in large language models via distillation and dynamic prompt tuning