Computer Science > Machine Learning

[Submitted on 6 Apr 2026 (v1), last revised 10 Aug 2026 (this version, v2)]

Title:Are Latent Reasoning Models Easily Interpretable?

Authors:Connor Dilgren, Sarah Wiegreffe

View a PDF of the paper titled Are Latent Reasoning Models Easily Interpretable?, by Connor Dilgren and Sarah Wiegreffe

View PDF HTML (experimental)

Abstract:Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models) and theoretical ability to explore multiple reasoning paths in parallel. However, these benefits come at the cost of reduced interpretability: LRMs are difficult to monitor because they do not reason in natural language. This paper presents an investigation into LRM interpretability by examining two state-of-the-art LRMs. First, we find that latent reasoning tokens are often unnecessary for LRMs' predictions; on logical reasoning datasets, LRMs can almost always produce the same final answers without using latent reasoning at all. This underutilization of reasoning tokens may partially explain why LRMs do not consistently outperform explicit reasoning methods and raises doubts about the stated role of these tokens in prior work. Second, we demonstrate that when latent reasoning tokens are necessary for performance, we can decode gold reasoning traces up to 65-93% of the time for correctly predicted instances. This suggests LRMs often implement the expected solution rather than an uninterpretable reasoning process. Finally, we present a method to decode a verified natural language reasoning trace from latent tokens without knowing a gold reasoning trace a priori, demonstrating that it is possible to find a verified trace for a majority of correct predictions but only a minority of incorrect predictions. Our findings highlight that current LRMs largely encode interpretable processes, and interpretability itself can be a signal of prediction correctness.

https://doi.org/10.48550/arXiv.2604.04902

arXiv-issued DOI via DataCite

Comments:
Subjects:	Machine Learning (cs.LG)
Cite as:	arXiv:2604.04902 [cs.LG]
	(or arXiv:2604.04902v2 [cs.LG] for this version)

Submission history

From: Connor Dilgren [view email] [v1] Mon, 6 Apr 2026 17:50:06 UTC (651 KB) [v2] Mon, 10 Aug 2026 13:30:13 UTC (699 KB)

Full-text links:

Access Paper:

• View a PDF of the paper titled Are Latent Reasoning Models Easily Interpretable?, by Connor Dilgren and Sarah Wiegreffe

• View PDF

• HTML (experimental)

• TeX Source

view license

Current browse context:

cs.LG

< prev | next >

new | recent | 2026-04

Change to browse by:

cs

References & Citations

• NASA ADS

• Google Scholar

• Semantic Scholar

Loading...

BibTeX formatted citation

Data provided by:

Bookmark

Bibliographic and Citation Tools

Bibliographic Explorer (What is the Explorer?)

Connected Papers (What is Connected Papers?)

Litmaps (What is Litmaps?)

scite Smart Citations (What are Smart Citations?)

Code, Data and Media Associated with this Article

alphaXiv (What is alphaXiv?)

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub (What is DagsHub?)

Gotit.pub (What is GotitPub?)

Hugging Face (What is Huggingface?)

ScienceCast (What is ScienceCast?)

Demos

Replicate (What is Replicate?)

Hugging Face Spaces (What is Spaces?)

TXYZ.AI (What is TXYZ.AI?)

Recommenders and Search Tools

Influence Flower (What are Influence Flowers?)

CORE Recommender (What is CORE?)

IArxiv Recommender (What is IArxiv?)

• Author

• Venue

• Institution

• Topic

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)