Skip to content

Author

Hong-Nian Huang

1 paper 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.

#natural language process... Preprint Nov 2026

When Every Choice Is Correct: A Causal Study of Numerical Preference in Language Models

When a language model chooses a number between 1 and 30, every integer in the range is valid, yet the model can favor particular answers. We use numerical choice to study how preference is processed across layers and tokens. Perturbation probing and gradient attribution nominate neurons for activation interventions. In...

Hong-Nian Huang, Hong-Liang Liu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.