arXiv AI
Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
1d ago
Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers
The paper audits whether routing entropy in Attention‑Residual transformer variants (Swin‑Tiny and DeiT‑Small) trained on CIFAR‑10/100 can signal prediction uncertainty beyond model confidence. Three tests examine the presence, consistency, and predictive power of routing signals, while a sensitivity audit measures how much injected effect the probes recover. Results show no significant improvement over confidence alone, with only modest recovery of injected signals and no consistent gains across seeds or metrics.
arXiv Machine Learning
Aug 11
Opportunity Is Not Realizability: Selection-Valid Diagnostics for Multi-LLM Routing
arXiv:2608. 08265v1 Announce Type: new Abstract: Oracle routing measures how much a pool of language models could gain from per-query selection, but the diagnostic has two flaws: testing against a best fixed model selected on the same examples invalidates paired inference, and a full-information oracle sees outcomes no deployable router observes.
arXiv Computation and Language
3d ago
From Routing Signals to Selective Review: Visual regrounding in MoE VLMs
arXiv:2609.38111v1 Announce Type: new Abstract: Vision-language models (VLMs) may accept false visual premises, answering questions about a target object's color, count, location, or state even when...
arXiv AI
3d ago
From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning
arXiv:2609.36569v1 Announce Type: cross Abstract: Checkpoint selection is a routine decision in supervised fine-tuning (SFT): training produces multiple checkpoints, but only one is retained. Yet fix...
arXiv AI
Jul 24
Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
arXiv Machine Learning
Aug 14
Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection
arXiv:2608. 12652v1 Announce Type: cross Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release.