Profiles2024-2026
Dan Shi
Tianjin University
6Papers
0Last author
6Unique co-authors
4First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers6
- Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language ModelsAuthor 1 of 6ACL 2026 · 1 citation
- ERRV: Eliciting Efficient Reasoning through Reasoning Vectors for Policy Optimization in Large Language ModelsAuthor 4 of 6ACL Findings 2026
- Neuronal Insights into LLM Attacks: Targeted Neuron Tuning for Precise and Robust Vulnerability PatchingAuthor 1 of 7ACL Findings 2026
- Towards a Unified Paradigm of Concept Editing in Large Language ModelsAuthor 3 of 5EMNLP 2025
- IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware NeuronsAuthor 1 of 6NeurIPS 2024 · 44 citations
- CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language ModelsAuthor 1 of 5AAAI 2024 · 3 citations
