Large autoregressive language models exhibit a self-correction blind spot: they reliably fix identical errors when attributed to an external source yet fail to fix the same errors in their own outputs. Prior work has documented this phenomenon empirically, through controlled error injection, error-depth decompositions, RL-based verifier-corrector training, and intrinsic self-verification, but offers no formal model of why generating a token suppresses the ability to detect its error, no quantitative activation condition for correction markers, and no convergence guarantee for reinforcement-learning-based self-correction.
arXiv:2507. 02778v3 Announce Type: replace-cross Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths.
By Ken Tsui
arXiv:2608. 05675v1 Announce Type: new Abstract: Label-free reliability for vision-language models rests on invariance: perturb the input and a faithful reader's answer should not change.
By Rasul Khanbayov, Hasan Kurban
Label-free reliability for vision-language models rests on invariance: perturb the input and a faithful reader's answer should not change. This has a known blind spot, a systematic misreading survives the perturbation and gets certified wrong, which we show is computable, not just real: an error is invisible to an edit exactly when the two commute, so the errors a suite cannot reach form its joint centralizer, a set that shrinks as edits are added and can be written down rather than guessed at.
arXiv:2606. 24964v1 Announce Type: new Abstract: Understanding the features of large language models (LLMs) is a central goal of interpretability.
By Francisco Ferreira da Silva, Stefan Heimersheim
arXiv:2606. 13156v2 Announce Type: replace-cross Abstract: Letting a vision-language model (VLM) think longer at test time has driven much recent progress.
By Animesh Tripathy, Aswanth Krishnan
SPARCL introduces a spectral partitioned analytic continual learning method that addresses forgetting in analytic class‑incremental learning. By decomposing the running autocorrelation into a high‑energy core and a residual complement, SPARCL freezes core components for old classes and updates only the residual block, ensuring closed‑form updates with an invariance guarantee. Experiments on CIFAR‑100, CUB‑200, ImageNet‑R, and ImageNet‑A with a frozen ViT‑B/16 protocol show that SPARCL narrows the performance gap between classical analytic learners and strong representation matchers while complementing sparse feature‑decorrelation approaches.
By James Hartley, Zeropy Surio, Daniel Whitmore, Hannah Clarke, Thomas Reed
arXiv:2607. 02089v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning.
By Tien-Huy Nguyen, Minh-Nhat Nguyen, Nguyen Nhat Huy, Hung Viet Nguyen, Huy Nguyen Minh Nhat, Thanh-Huy Nguyen, Cuong Tuan Nguyen, Hoang M. Le, Dat Nguyen, Phat Kim Huynh, Min Xu, Ulas Bagci
arXiv:2609.15825v1 Announce Type: new
Abstract: A self-supervised encoder is trained once, frozen, and reused through lightweight probes on tasks nobody named at training time; the practitioner's que...
By Dier Tang, Jing Yee Tan, Guangyue Han
arXiv:2606. 13156v1 Announce Type: cross Abstract: Vision-language models (VLMs) achieve strong singleshot spatial grounding, yet lack any mechanism to observe and correct their own predictions.
By Animesh Tripathy, Aswanth Krishnan
arXiv:2605. 30290v2 Announce Type: replace-cross Abstract: Self-improvement at scale has been a longstanding goal for reasoning models, and there are two natural places to do it: at test time, through verification-refinement (V-R) loops; and at training time, through self-training methods.
By Chen Henry Wu, Aditi Raghunathan
arXiv:2607. 07513v1 Announce Type: new Abstract: Self-supervised learning matches supervised accuracy from a fraction of the labels, but the labeled-sample efficiency behind this has lacked a theoretical explanation.
By Adam M. Oberman