Author

Chen Shen

h-index 3 View on Semantic Scholar

We have 4 of 15 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Sep 2026

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

The Distributional Answer Commitment Score (DACS) is proposed, a distributional confidence estimator that measures the entropy of the model's probability distribution over answer commitment at each reasoning step to capture how concentrated the model's answer belief is without requiring ground-truth answers or task-spe...

Zhao-Han Zhang, Jun-Jie Liu, Chengzhengxu Li et al. · 0 citations

#artificial intelligence Preprint Sep 2026

What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory

To the authors' knowledge, this is the first per-item, per-question restore-counterfactual audit of eviction for external agent-memory stores on a standard conversational benchmark.

Chen Shen · 0 citations

Preprint Aug 2026

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...

Yu Feng, Chun-Ting Zang, Chen Shen et al. · 1 citation

Jul 2026

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy

Although multi-turn inference remains more expensive than single-call retrieval, VecTree-RAG provides a structure-aware and traceable architecture for scientific literature question answering.

Xinyan Zhong, Yu-Wei Shi, Yu-Qi Wei et al. · arXiv.org · 0 citations