arXiv subjects

Josef Kuchař

Publications and source records attributed to Josef Kuchař.

6 recordsLinked to original sources

arXiv2026

AIMO Interpretability Challenge

We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' internal mechanisms. The challenge is motivated by a central limitation of standard reasoning benchmarks: strong final-answer accuracy does not reveal whether a model relies on stable reasoning mechanisms or exploits brittle reasoning shortcuts. Building on AI Mathematical Olympiad (AIMO) problems and submissions, together with resources from the Fields Model Initiative, the competition will provide (1) newly-published olympiad-level math reasoning problems and their symbolic representations, allowing generation of novel functional variants, (2) access to frontier reasoning models, and (3) assessments of models' adversarial robustness on these problems. Participants will use these resources, along with our computing infrastructure support, to develop methods for identifying which models solve problems robustly. Our competition will also create a new, open robustness benchmark and baseline systems, aiming to provide a lasting foundation for standard benchmarking in mathematical reasoning and interpretability. Scientifically, the competition connects interpretability and generalization research around a central question in AI research: can we determine if, and to what extent, the decision-making of frontier AI models is generalizable and thus, reliable?

cs.AI↗

arXiv2026

Language Models Learn Universal Representations of Numbers and Here's Why You Should Care

Prior work has shown that large language models (LLMs) often converge to accurate input embedding for numbers, based on sinusoidal representations. In this work, we quantify that these representations are in fact strikingly systematic, to the point of being almost perfectly universal: different LLM families develop equivalent sinusoidal structures, and number representations are broadly interchangeable in a large swathe of experimental setups. We show that properly factoring in this characteristic is crucial when it comes to assessing how accurately LLMs encode numeric and other ordinal information, and that mechanistically enhancing this sinusoidality can also lead to reductions of LLMs' arithmetic errors.

cs.CL↗

arXiv2025

Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers

Pretrained language models (LMs) are prone to arithmetic errors. Existing work showed limited success in probing numeric values from models' representations, indicating that these errors can be attributed to the inherent unreliability of distributionally learned embeddings in representing exact quantities. However, we observe that previous probing methods are inadequate for the emergent structure of learned number embeddings with sinusoidal patterns. In response, we propose a novel probing technique that decodes numeric values from input embeddings with near-perfect accuracy across a range of open-source LMs. This proves that after the sole pre-training, LMs represent numbers with remarkable precision. Finally, we find that the embeddings' precision, judged by our probe's accuracy, explains a large portion of LM's errors in elementary arithmetic, and show that aligning the embeddings with the pattern our probes discover can mitigate these errors.

cs.CL↗

arXiv2025

Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering

A majority of recent work in AI assesses models' generalization capabilities through the lens of performance on out-of-distribution (OOD) datasets. Despite their practicality, such evaluations build upon a strong assumption: that OOD evaluations can capture and reflect upon possible failures in a real-world deployment. In this work, we challenge this assumption and confront the results obtained from OOD evaluations with a set of specific failure modes documented in existing question-answering (QA) models, referred to as a reliance on spurious features or prediction shortcuts. We find that different datasets used for OOD evaluations in QA provide an estimate of models' robustness to shortcuts that have a vastly different quality, some largely under-performing even a simple, in-distribution evaluation. We partially attribute this to the observation that spurious shortcuts are shared across ID+OOD datasets, but also find cases where a dataset's quality for training and evaluation is largely disconnected. Our work underlines limitations of commonly-used OOD-based evaluations of generalization, and provides methodology and recommendations for evaluating generalization within and beyond QA more robustly.

cs.CL↗

arXiv2025

Attend or Perish: Benchmarking Attention in Algorithmic Reasoning

Can transformers learn to perform algorithmic tasks reliably across previously unseen input/output domains? While pre-trained language models show solid accuracy on benchmarks incorporating algorithmic reasoning, assessing the reliability of these results necessitates an ability to distinguish genuine algorithmic understanding from memorization. In this paper, we propose AttentionSpan, an algorithmic benchmark comprising five tasks of infinite input domains where we can disentangle and trace the correct, robust algorithm necessary for the task. This allows us to assess (i) models' ability to extrapolate to unseen types of inputs, including new lengths, value ranges or input domains, but also (ii)to assess the robustness of their learned mechanisms. By analyzing attention maps and performing targeted interventions, we show that attention mechanism directly causes failures in extrapolation. We make the implementation of all our tasks and interpretability methods publicly available at https://github.com/michalspiegel/AttentionSpan .

cs.LG↗

arXiv2025

VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics

We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this task. To foster research in natural language-driven vector graphic generation and editing, we make our resources created within this work publicly available.

cs.LG↗