# Verbalising Model's Computation for Chain-of-Thought Faithfulness Detection

Authors: Yujing Wang, Yulan He, Wenya Wang, Hanqi Yan.

Projects hidden states into vocabulary directions to track how internal information changes across layers and written reasoning steps. Uses these trajectories to detect unfaithful chains of thought and test transfer across tasks and models.

First public: 2026-10-16.
ArXiv initial submission: 2026-10-16.

[Original paper](https://arxiv.org/abs/2610.23275) · [PDF](https://arxiv.org/pdf/2610.23275) · [HTML](https://arxiv.org/html/2610.23275v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.23275/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.23275/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.23275/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.23275/record.json)

## Approaches

- [Analysis and evaluation](https://latent-implicit-thinking.github.io/topics/implicit-reasoning-evaluation/): Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.

Reading-list version 0.11.0; literature checked through 2026-10-26.