Beyond Accuracy: A Geometric Stability Analysis of Large Language Models in Chess Evaluation
cs.AI
Submitted: 2025-12-17
Updated: 2026-11-12
Code: https://github.com/LeelaChessZero/lc0
Terminology
Sources
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- Ensemble Adversarial Training: Attacks and Defenses
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
- Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
- Spectral Normalization for Generative Adversarial Networks
- Explaining and Harnessing Adversarial Examples
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- GPT-4 Technical Report
- Gemini: A Family of Highly Capable Multimodal Models
- DeepSeek-V3 Technical Report
- Qwen3 Technical Report
- Gemma 3 Technical Report
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents