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.
By Wenhao Liang, Lin Yue, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong Chen
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.
By Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb
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...
By Hongzhu Guo, Mohsen Fayyaz, Nanyun Peng
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...
By Yupeng Chang, Wenxuan Zhang, Yuan Wu
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.
By Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz
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.
By Florian Braun
arXiv:2610.01535v1 Announce Type: cross
Abstract: Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that comparat...
By Amit Singh Bhatti, Vishal Vaddina
arXiv:2601. 07965v2 Announce Type: replace Abstract: When a model knows when it does not know, many possibilities emerge.
By Chenjie Hao, Weyl Lu, Yuko Ishiwaka, Zengyi Li, Weier Wan, Yubei Chen
arXiv:2608. 10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment.
By Joyjeet Singh
arXiv:2603. 25450v2 Announce Type: replace Abstract: Detecting when a language model is wrong without ground truth labels is a fundamental challenge for safe deployment.
By Matt Gorbett, Suman Jana
The paper investigates how a probe can decode in‑context bindings on model errors and how probe‑guided steering can repair them. It tracks probe accuracy, model output, and steering response across public pretraining and post‑training checkpoints, noting that probe accuracy improves during Pythia pretraining and that steering benefits grow with model size. The study also shows that decoders trained on final state or candidate logits do not outperform each other on late‑checkpoint errors, and presents an information‑theoretic counterexample explaining why decodability on errors alone cannot prove discarded output information.
By Manas Venkata Sai Ravulapalli, Samrath Singh Chadha
arXiv:2605.00915v2 Announce Type: replace
Abstract: Probing frozen vision transformers typically uses permutation-invariant aggregation (GAP or $\texttt{[CLS]}$), treating patch tokens as an unstruct...
By Zice Wang, Zhenyu Zhang