@inproceedings{malladi-etal-2025-explaining,
    title = "Explaining Differences Between Model Pairs in Natural Language through Sample Learning",
    author = "Malladi, Advaith  and
      R Menon, Rakesh  and
      Jain, Yuvraj  and
      Srivastava, Shashank",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1462/",
    pages = "28725--28747",
    ISBN = "979-8-89176-332-6",
    abstract = "With the growing adoption of machine learning models in critical domains, techniques for explaining differences between models have become essential for trust, debugging, and informed deployment. Previous approaches address this by identifying input transformations that cause divergent predictions or by learning joint surrogate models to align and contrast behaviors. These methods often require access to training data and do not produce natural language explanations. In this paper, we introduce SLED, a framework that generates faithful natural language explanations of when and how two ML models converge or diverge in their predictions. SLED first uses gradient-based optimization to synthesize input samples that highlight divergence and convergence patterns, and then leverages a large language model (LLM) to generate explanations grounded in these synthetic samples. Across both text-based (3 tasks, 7 models) and structured (10 tasks, 4 models) classification tasks, we show that SLED explanations are 18{--}24{\%} more faithful than the strongest baselines. User studies also indicate that SLED explanations achieve a real-world simulatability of 63.5{\%}. Importantly, SLED requires minimal access to training data and generalizes well to real-world samples, enabling transparent and data-efficient model comparison."
}