Abstract
Abstract coming soon. This paper has been accepted but the arXiv preprint is not yet available.
Back to Research
Accepted to BlackboxNLP @ EMNLP 2025
Peering into the Black Box: A Mechanistic Interpretation of a Latent Reasoning Model
Brad Peters, Sayam Goyal, María Emilia Granda, Akshath Vijayakumar Narmadha
Citation
Brad Peters, Sayam Goyal, María Emilia Granda, Akshath Vijayakumar Narmadha. "Peering into the Black Box: A Mechanistic Interpretation of a Latent Reasoning Model". Accepted to BlackboxNLP @ EMNLP 2025.
Resources
Details
- Conference
- Accepted to BlackboxNLP @ EMNLP 2025
- Authors
- 4 authors
Related Publications
Explore more research from Algoverse
NeurIPS 2025 (Spotlight)
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
Daniel Aarao Reis Arturi, Eric Zhang, Andrew Adrian Ansah
NeurIPS 2025 (Spotlight)
Scratchpad Thinking: Alternation Between Storage and Computation in Latent Reasoning Models
Sayam Goyal, Brad Peters, María Emilia Granda, Akshath Vijayakumar Narmadha, Dharunish Yugeswardeenoo
NeurIPS 2025 (Spotlight)
WOLF: Werewolf-based Observations for LLM Deception and Falsehoods
Mrinal Agarwal, Saad Rana, Theo Sundoro, Hermela Berhe
Publish Your Research
Join Algoverse and work with world-class mentors to publish at top AI conferences.
Start Your Application