English
Related papers

Related papers: The Confidence Manifold: Geometric Structure of Co…

200 papers

Autoregressive transformers make confident errors that output-confidence monitoring cannot catch. Activation monitors catch them only when training leaves a decision-quality signal beyond what the output already exposes. This signal is an…

Machine Learning · Computer Science 2026-05-13 Thomas Carmichael

We find that models report highest confidence precisely when they are fabricating. Across four model families (OLMo-3, Llama-3.1, Qwen3, Mistral), self-reported confidence inversely correlates with accuracy, with AUC ranging from 0.28 to…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Tony Mason , Vaastav Anand

We test whether a geometric hallucination taxonomy -- classifying failures as center-drift (Type~1), wrong-well convergence (Type~2), or coverage gaps (Type~3) -- can distinguish hallucination types through controlled induction in GPT-2.…

Computation and Language · Computer Science 2026-03-03 Matic Korun

The evaluation of Large Language Models (LLMs) in complex reasoning domains typically relies on performance alignment with ground-truth oracles. In the domain of chess, this standard manifests as accuracy benchmarks against strong engines…

Artificial Intelligence · Computer Science 2025-12-18 Xidan Song , Weiqi Wang , Ruifeng Cao , Qingya Hu

Categorical perception (CP) -- enhanced discriminability at category boundaries -- is among the most studied phenomena in perceptual psychology. This paper reports that analogous geometric warping occurs in the hidden-state representations…

Computation and Language · Computer Science 2026-04-27 Jon-Paul Cacioli

Deep neural network classifiers partition input space into high confidence regions for each class. The geometry of these class manifolds (CMs) is widely studied and intimately related to model performance; for example, the margin depends on…

Machine Learning · Computer Science 2022-10-12 Stanislav Fort , Ekin Dogus Cubuk , Surya Ganguli , Samuel S. Schoenholz

We present a novel non-iterative learnable method for partial-to-partial 3D shape registration. The partial alignment task is extremely complex, as it jointly tries to match between points and identify which points do not appear in the…

Computer Vision and Pattern Recognition · Computer Science 2022-01-28 Dvir Ginzburg , Dan Raviv

Understanding the representations of different languages in multilingual language models is essential for comprehending their cross-lingual properties, predicting their performance on downstream tasks, and identifying any biases across…

Computation and Language · Computer Science 2023-05-16 Cheril Shah , Yashashree Chandak , Manan Suri

Consider the task of locating an unknown target point using approximate distance queries: in each round, a reconstructor selects a query point and receives a noisy version of its distance to the target. This problem arises naturally in…

Machine Learning · Computer Science 2025-11-11 Shay Moran , Elizaveta Nesterova

Large Language Models (LLMs) frequently prioritize conflicting in-context information over pre-existing parametric memory, a phenomenon often termed sycophancy or compliance. However, the mechanistic realization of this behavior remains…

Machine Learning · Computer Science 2026-02-09 Long Zhang , Fangwei Lin

AI text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary. On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834…

Machine Learning · Computer Science 2026-05-22 Alexander Smirnov

Noisy correspondence that refers to mismatches in cross-modal data pairs, is prevalent on human-annotated or web-crawled datasets. Prior approaches to leverage such data mainly consider the application of uni-modal noisy label learning…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Zihua Zhao , Mengxi Chen , Tianjie Dai , Jiangchao Yao , Bo han , Ya Zhang , Yanfeng Wang

Deep generative models are tremendously successful in learning low-dimensional latent representations that well-describe the data. These representations, however, tend to much distort relationships between points, i.e. pairwise distances…

Machine Learning · Computer Science 2018-09-14 Tao Yang , Georgios Arvanitidis , Dongmei Fu , Xiaogang Li , Søren Hauberg

Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a model will accept targeted behavioral control, and detecting when its internal structure…

Machine Learning · Computer Science 2026-04-30 Prashant C. Raju

We show that, for each of five datasets of increasing complexity, certain training samples are more informative of class membership than others. These samples can be identified a priori to training by analyzing their position in reduced…

Machine Learning · Computer Science 2022-02-08 Adam Byerly , Tatiana Kalganova

Current evaluation of mathematical reasoning in language models relies primarily on answer accuracy, potentially masking fundamental failures in logical computation. We introduce a diagnostic framework that distinguishes genuine…

Computation and Language · Computer Science 2025-12-02 Subramanyam Sahoo , Vinija Jain , Saanidhya Vats , Siddharth Mohapatra , Rui Min , Aman Chadha , Divya Chaudhary

We address the problem of finding reliable dense correspondences between a pair of images. This is a challenging task due to strong appearance differences between the corresponding scene elements and ambiguities generated by repetitive…

Computer Vision and Pattern Recognition · Computer Science 2018-11-30 Ignacio Rocco , Mircea Cimpoi , Relja Arandjelović , Akihiko Torii , Tomas Pajdla , Josef Sivic

Automated scoring of student work at scale requires balancing accuracy against cost and latency. In "cascade" systems, small language models (LMs) handle easier scoring tasks while escalating harder ones to larger LMs -- but the challenge…

Computers and Society · Computer Science 2026-04-23 Tyler Burleigh

Linear probes can detect when language models produce outputs they "know" are wrong, a capability relevant to both deception and reward hacking. However, single-layer probes are fragile: the best layer varies across models and tasks, and…

Machine Learning · Computer Science 2026-04-16 Erik Nordby , Tasha Pais , Aviel Parrack

We propose a novel method of introducing structure into existing machine learning techniques by developing structure-based similarity and distance measures. To learn structural information, low-dimensional structure of the data is captured…

Machine Learning · Statistics 2011-10-27 Joseph Wang , Venkatesh Saligrama , David A. Castañón