Cover Image

Out-of-distribution Tests Reveal Compositionality in Chess Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mészáros, Anna, Reizinger, Patrik, Huszár, Ferenc
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts
by: Mészáros, Anna, et al.
Published: (2024)

Position: Understanding LLMs Requires More Than Statistical Generalization
by: Reizinger, Patrik, et al.
Published: (2024)

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
by: Reizinger, Patrik, et al.
Published: (2024)

Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data
by: Guo, Siyuan, et al.
Published: (2022)

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
by: Reizinger, Patrik, et al.
Published: (2025)

Estimating Treatment Effects with Independent Component Analysis
by: Reizinger, Patrik, et al.
Published: (2025)

Do Finetti: On Causal Effects for Exchangeable Data
by: Guo, Siyuan, et al.
Published: (2024)

From superposition to sparse codes: interpretable representations in neural networks
by: Klindt, David, et al.
Published: (2025)

Predicting Chess Puzzle Difficulty with Transformers
by: Miłosz, Szymon, et al.
Published: (2024)

Mastering Chess with a Transformer Model
by: Monroe, Daniel, et al.
Published: (2024)

An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis
by: Rajendran, Goutham, et al.
Published: (2023)

Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations
by: Joshi, Shruti, et al.
Published: (2026)

Causality is Key for Interpretability Claims to Generalise
by: Joshi, Shruti, et al.
Published: (2026)

Beyond the Boundaries of Proximal Policy Optimization
by: Tan, Charlie B., et al.
Published: (2024)

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning
by: Reizinger, Patrik, et al.
Published: (2025)

Tracing the Thought of a Grandmaster-level Chess-Playing Transformer
by: Lin, Rui, et al.
Published: (2026)

Thinking in Groups: Permutation Tests Reveal Near-Out-of-Distribution
by: Jayawardana, Yasith, et al.
Published: (2024)

Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMs
by: Guo, Siyuan, et al.
Published: (2024)

Adversarial Testing as a Tool for Interpretability: Length-based Overfitting of Elementary Functions in Transformers
by: Zavoral, Patrik, et al.
Published: (2024)

InfoNCE: Identifying the Gap Between Theory and Practice
by: Rusak, Evgenia, et al.
Published: (2024)

Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions
by: Veeriah, Vivek, et al.
Published: (2025)

ChessQA: Evaluating Large Language Models for Chess Understanding
by: Wen, Qianfeng, et al.
Published: (2025)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
by: Mueller, Aaron, et al.
Published: (2025)

Cross-Entropy Is All You Need To Invert the Data Generating Process
by: Reizinger, Patrik, et al.
Published: (2024)

Amortized Planning with Large-Scale Transformers: A Case Study on Chess
by: Ruoss, Anian, et al.
Published: (2024)

Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences
by: Walker, Benjamin, et al.
Published: (2026)

Complete Chess Games Enable LLM Become A Chess Master
by: Zhang, Yinqi, et al.
Published: (2025)

Generating Creative Chess Puzzles
by: Feng, Xidong, et al.
Published: (2025)

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
by: Liu, Jincheng, et al.
Published: (2025)

Chessformer: A Unified Architecture for Chess Modeling
by: Monroe, Daniel, et al.
Published: (2026)

Dual Test-time Training for Out-of-distribution Recommender System
by: Yang, Xihong, et al.
Published: (2024)

Liquid Reasoning Transformers: A Sudoku-Based Prototype for Chess-Scale Algorithmic Tasks
by: Sahni, Shivansh, et al.
Published: (2025)

STEP: Structured Training and Evaluation Platform for benchmarking trajectory prediction models
by: Schumann, Julian F., et al.
Published: (2025)

Exploring Human-AI Conceptual Alignment through the Prism of Chess
by: Lomasov, Semyon, et al.
Published: (2025)

Human-aligned Chess with a Bit of Search
by: Zhang, Yiming, et al.
Published: (2024)

Enhancing Chess Reinforcement Learning with Graph Representation
by: Rigaux, Tomas, et al.
Published: (2024)

Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
by: Lei, Yutian, et al.
Published: (2024)

Feature Protection For Out-of-distribution Generalization
by: Tan, Lu, et al.
Published: (2024)

Towards Piece-by-Piece Explanations for Chess Positions with SHAP
by: Spinnato, Francesco
Published: (2025)

Iterative Inference in a Chess-Playing Neural Network
by: Sandmann, Elias, et al.
Published: (2025)