Generative Interpretability via Scalable Neuro-Symbolic Models

The paper argues that as Large Language Models transition from chatbots to agentic systems, the current post-hoc interpretability paradigm is insufficient for safe deployment because it cannot audit or intervene before an output is produced. It proposes a shift to generative interpretability, where a model’s inference process inherently exposes semantically meaningful checkpoints that are human-understandable and can be causally intervened upon. The authors illustrate the advantages of this approach and introduce Neuro‑Symbolic Models as a concrete implementation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• safety