Anish Sathyanarayanan

Karan Bania, Soham Kalburgi, Manit Tanwar et al.

Linear recurrent neural networks (LRNNs) provide a structured approach to sequence modeling that bridges classical linear dynamical systems and modern deep learning, offering both expressive power and theoretical guarantees on stability and trainability. In recent years, multiple LRNN-based architectures have been proposed, each introducing distinct parameterizations, discretization schemes, and implementation constraints. However, existing implementations are fragmented across different software frameworks, often rely on framework-specific optimizations, and in some cases require custom CUDA kernels or lack publicly available code altogether. As a result, using, comparing, or extending LRNNs requires substantial implementation effort. To address this, we introduce $\texttt{lrnnx}$, a unified software library that implements several modern LRNN architectures under a common interface. The library exposes multiple levels of control, allowing users to work directly with core components or higher-level model abstractions. $\texttt{lrnnx}$ aims to improve accessibility, reproducibility, and extensibility of LRNN research and applications. We make our code available under a permissive MIT license.

Anish Sathyanarayanan, Aditya Nagarsekar, Aarush Rathore

Chain-of-thought (CoT) prompting is widely assumed to expose a model's reasoning process and improve transparency. We attempted to enforce this assumption by penalizing unfaithful reasoning, but found that surface-level compliance does not guarantee causal reliance. Our central finding is negative: even when CoT is verbose, strategic, and flagged by surface-level manipulation detectors, model answers are often causally independent of the CoT content. We present a diagnostic framework for auditing this failure mode: it combines (i) an interpretable behavioral module that scores manipulation-relevant signals in CoT text and (ii) a causal probe that measures CoT-mediated influence (CMI) via hidden-state patching and reports a bypass score ($1-\mathrm{CMI}$), quantifying the degree to which the answer is produced by a bypass circuit independent of the rationale. In pilot evaluations, audit-aware prompting increases detectable manipulation signals (mean risk-score delta: $+5.10$), yet causal probes reveal task-dependent mediation: many QA items exhibit near-total bypass (CMI $\approx 0$), while some logic problems show stronger mediation (CMI up to $0.56$). Layer-wise analysis reveals narrow and task-dependent ``reasoning windows'' even when mean CMI is low.