Author

Boxi Yu

h-index 8 View on Semantic Scholar

We have 3 of 20 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.

#artificial intelligence Jun 2026

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment

This paper proposes TRACE, which simulates harmful SFT trajectories to produce progressively corrupted model states, and optimizes a safety patch simultaneously across these states, and improves the safety rate by up to 77 percentage points over the best baselines, while maintaining comparable utility to the undefended...

Changyue Li, Jiaming He, Youliang Yuan et al. · arXiv.org · 0 citations

#artificial intelligence Preprint Sep 2026

When Is Graph Structure Worth Its Cost? The Case for Structure Pricing in Retrieval-Augmented Generation

Graph-based retrieval-augmented generation (RAG) can help answer questions that require information from many documents. However, building a graph often requires many language-model calls during ingestion. It is therefore important to ask whether its quality gains justify the additional cost. We present EffiRAG, a grap...

Yu-Zhong Zhang, Hao-Yang Ma, Chao Peng et al. · 0 citations

Preprint Jul 2026

BeSpec: Behavior-Level Specification Alignment for Code Generation

BeSpec is presented, a behavioral model-based approach to specification alignment that treats the task description as partial evidence about the intended behavior of the correct program, and first builds an explicit behavioral model, which are checkable properties that valid outputs must satisfy.

Qinghua Xu, Guancheng Wang, Boxi Yu et al. · 0 citations