Do Generalisation Results Generalise?

2025-12-08

AI Summary

It remains unclear whether a large language model’s (LLM) out-of-distribution (OOD) generalization performance on a single OOD dataset reliably reflects its true robustness under diverse distribution shifts. Method: We introduce the first systematic multi-OOD evaluation framework, leveraging partial correlation analysis to quantify inter-test-set generalization correlations while controlling for in-domain performance confounds. Results: Experiments across OLMo2 and OPT models reveal that OOD generalization exhibits no consistent positive or negative cross-test-set correlations; instead, correlation patterns are highly dependent on specific model–test-set pairings. This demonstrates the inadequacy of single-OOD benchmarks for assessing robust generalization. Our findings provide theoretical grounding and methodological support for developing more reliable, reproducible, and comprehensive generalization evaluation protocols—highlighting the necessity of multi-OOD assessment to uncover latent failure modes and ensure meaningful robustness estimation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Search and Optimization: Evaluation and Analysis

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

A large language model's (LLM's) out-of-distribution (OOD) generalisation ability is crucial to its deployment. Previous work assessing LLMs' generalisation performance, however, typically focuses on a single out-of-distribution dataset. This approach may fail to precisely evaluate the capabilities of the model, as the data shifts encountered once a model is deployed are much more diverse. In this work, we investigate whether OOD generalisation results generalise. More specifically, we evaluate a model's performance across multiple OOD testsets throughout a finetuning run; we then evaluate the partial correlation of performances across these testsets, regressing out in-domain performance. This allows us to assess how correlated are generalisation performances once in-domain performance is controlled for. Analysing OLMo2 and OPT, we observe no overarching trend in generalisation results: the existence of a positive or negative correlation between any two OOD testsets depends strongly on the specific choice of model analysed.

Problem

• Assesses LLM out-of-distribution generalization across multiple datasets
• Investigates if generalization results are consistent when controlling for in-domain performance
• Finds generalization correlations vary by model without an overarching trend

Innovation

• Evaluates multiple out-of-distribution datasets for generalization
• Uses partial correlation to control for in-domain performance
• Analyzes trends across different models like OLMo2 and OPT