Author

Yi-Long Li

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 Preprint Oct 2026

Does the Model Use the Feature? Separating Steering from Mechanism in LLMs

Internal features in LLMs are often interpreted as mechanisms when they track a concept and their manipulation changes a related behavior. Yet steering can push a feature far outside its natural range, where its effects need not reflect the model's own computation. We examine this inference and propose an empirical con...

Che-Ah-Yi Tong, Yi-Long Li · 0 citations

#natural language process... Preprint Sep 2026

Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference

This work separate factual recall into three steps: generating a correct candidate, ranking the available candidates, and selecting the final answer, and shows that these capabilities do not collapse into a single notion of ``knowing''.

Yi-Long Li, Cheng-Po Yan, Aayan Arish et al. · 0 citations