Get started
Author

Chenpeng Wang

Observed name: Wang, Chenpeng
OpenAlex ID: A5139135714
CANS: Capability-Preserving Neuron Steering for Large Language Models
2026 · Wu, Yucheng, Xie, Chengyi, et al. · arXiv (Cornell University)
PDF
Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts
2026 · Lou, Yibin, Hu, Yi, et al. · arXiv (Cornell University)
PDF
Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods
2026 · Yang, Haotian, Jiang, Huikang, et al. · arXiv (Cornell University)
PDF
From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution
2026 · Luo, Yuzhang, Wang, Chenpeng, et al. · arXiv (Cornell University)
PDF
Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
2026 · Zuo, Zhuo, Yue, Li, et al. · arXiv (Cornell University)
PDF
HOLogicBench: Evaluating Higher-Order Logical Reasoning in LLMs
2026 · Wu, Yucheng, Xu, Jundong, et al. · arXiv (Cornell University)
PDF
Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models
2026 · Danchun Chen, Qiyao Yan, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Where Steering Signals Come From: Activation Source Selection in Activation Steering
2026 · Jiaran Ye, Lingxu Ran, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores
2026 · Qiyao Yan, Chenpeng Wang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 9
Citation count:
H-index:
I10-index:
Year
Topic
Type