Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs

arXiv:2610.01428 · cs.CL, cs.AI, cs.LG · Submitted 2026-10-01 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Generalization — 35× in this paper · explained in 13 episodes
• Consistency — 24× in this paper · explained in 3 episodes
• Robustness — 24× in this paper · explained in 5 episodes
• Benchmark — 21× in this paper · explained in 2 episodes
• Accuracy — 12× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Failure Modes — 4× in this paper · explained in 3 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Distribution Shift — 3× in this paper · explained in 5 episodes
• Stability-Aware Generalization Objective — 3× in this paper
• Benchmarking — 2× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Activation Patching — 1× in this paper · explained in 2 episodes
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes

Sources

• Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)
• The Llama 3 Herd of Models
• SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge
• Measuring Massive Multitask Language Understanding
• Silent Tokens, Loud Effects: Padding in LLMs
• Jailbreak Attack Initializations as Extractors of Compliance Directions
• Estimating LLM Uncertainty with Evidence
• Qwen2.5 Technical Report
• When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs
• Gemma: Open Models Based on Gemini Research and Technology
• BERTScore: Evaluating Text Generation with BERT

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering