arXiv:2606. 19317v1 Announce Type: cross Abstract: A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions.
By Amiri Hayes, Belinda Li, Jacob Andreas
arXiv:2510. 25013v2 Announce Type: replace-cross Abstract: Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits.
By Rabin Adhikari
arXiv:2608. 02879v1 Announce Type: new Abstract: The widespread adoption of proprietary Large Language Models (LLMs) accessed strictly through closed APIs has created a critical challenge for responsible deployment: a fundamental lack of interpretability.
By Maryam Rezaee, Pooriya Safaei, Maryam Asgarinezhad, Fatemeh Seyyedsalehi
arXiv:2605. 18079v2 Announce Type: replace Abstract: Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice.
By Moritz Br\"osamle, Stephan Eckstein
arXiv:2609.25438v1 Announce Type: new
Abstract: Diverse pretraining has been shown to be an effective method for learning reusable, domain-aware representations that provide a starting point for fine...
By Henry Kvinge
The paper proposes a lightweight recurrent memory module inserted between the lower and upper halves of a 6‑layer decoder‑only transformer. This module, which uses cross‑attention to observe hidden states, a GRU to update a persistent state, and gated addition to modulate subsequent layers, adds only 3.7% more parameters. It reduces evaluation loss by 28.5% and narrows the generalization gap, with ablations showing the benefit comes solely from the memory topology rather than auxiliary losses.
By Eduardo Novaes Hering