Author

Jia-Lu Wang

2 papers indexed here

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

When Attribution Patching Lies: Diagnosis and a Second-Order Correction

This work characterize the source of this unreliability, demonstrating that the dominant error stems from the non-linearities in the downstream network rather than local curvature at the patched component.

Lu-Yang Zhang, Jia-Lu Wang · arXiv.org · 5 citations

#artificial intelligence Preprint Sep 2026

Pick the Mixture, Not the Samples: Combinatorial Data Selection for LLMs

Data selection for LLM fine-tuning faces two facts about real training: data pools draw from many distinct domains, and evaluation spans diverse tasks. As a result, the same sample helps different tasks differently, and samples interact during training so that a subset's value is not the sum of its parts. Current data-...

Lu-Yang Zhang, Jia-Lu Wang, Bebei Li · 0 citations