BehaviorBox: Automated Behavioral Comparison of Language Models

ACL ARR 2025 February Submission7500 Authors

Abstract: Language model evaluation is a daunting task: prompts are brittle, corpus-level perplexities are vague, and the choice of benchmarks are endless. Choosing examples that show meaningful, generalizable differences between two LMs is crucial to understanding where one model succeeds and another fails. Can this process be done automatically? In this work, we propose methodology for automated behavioral comparison of language models that uses performance-aware contextual embeddings to find fine-grained features of text where one LM outperforms another. Our method, which we name BehaviorBox, is able to extract coherent features that also demonstrate statistically significant differences with respect to the ease of generation between two LMs. We apply BehaviorBox to compare models that vary in size, model family, and post-training, and enumerate insights into specific contexts that illustrate meaningful differences in performance.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: free-text/natural language explanations, feature attribution

Contribution Types: Model analysis & interpretability, Data analysis

Languages Studied: English

Submission Number: 7500