arXiv:2607. 25546v1 Announce Type: new Abstract: Given a model that is already trained, which features does it rely on causally versus spuriously?
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 19618v1 Announce Type: cross Abstract: Genomic language models achieve strong performance across regulatory-genomics tasks, yet what these models internally represent remains opaque, and the field lacks a principled procedure for verifying that an apparent ``concept'' inside a model is real rather than an artifact of sequence composition.
arXiv:2607. 25532v1 Announce Type: new Abstract: Consider a model trained at a single hospital to predict patient recovery, where the measured feature $X$ bundles the patient's true health signal ($C$) with a systematic artefact from that hospital's equipment ($S$).
arXiv:2605. 09169v2 Announce Type: replace-cross Abstract: A Mamba state-space model trained only for next-step prediction appears to recover Granger-causal structure through a simple readout $S = |W_{out} W_{in}|$, with early experiments suggesting the phenomenon generalized across architectures and benefited from interventional data at $p < 10^{-5}$.
arXiv:2607. 20596v1 Announce Type: new Abstract: Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet whether a feature's causal role is stable across SAE families remains untested.
arXiv:2606. 17113v1 Announce Type: new Abstract: Distinguishing causal adverse drug events (ADEs) from spurious correlations remains a central challenge in pharmacovigilance.
arXiv:2602. 01135v3 Announce Type: replace Abstract: Autoregressive models trained via next-token prediction implicitly learn the conditional independence structure of their data-generating process.