Author

Y. Cheah

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.

Jul 2026

Training Large Language Models for Self-Explanation Faithfulness

It is shown that models can be trained to implicitly identify influential factors and disclose them, offering a scalable path toward reducing unfaithful reasoning in LLMs.

Y. Cheah, María Pérez-Ortiz, N. Siegel et al. · arXiv.org · 0 citations