Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Perplexity Cost Understates What Activation Quantisation Breaks
Anish Sathyanarayanan
Activation quantisation is usually evaluated with an aggregate metric, perplexity, averaged over every token a model predicts. We ask whether that average identifies which computat…
cs.LG2026
: A library for Linear RNNs
Karan Bania, Soham Kalburgi, Manit Tanwar +8
Linear recurrent neural networks (LRNNs) provide a structured approach to sequence modeling that bridges classical linear dynamical systems and modern deep learning, offering both…
cs.LG2026
Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models
Anish Sathyanarayanan, Aditya Nagarsekar, Aarush Rathore
Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply that the model's in…