Interactive Analysis of LLMs using Meaningful Counterfactuals

arXiv:2405.00708v1 Announce Type: new
Abstract: Counterfactual examples are useful for exploring the decision boundaries of machine learning models and determining feature attributions. How can we apply counterfactual-based methods to analyze and explain LLMs? We identify the following key challenges. First, the generated textual counterfactuals should be meaningful and readable to users and thus can be mentally compared to draw conclusions. Second, to make the solution scalable to long-form text, users should be equipped with tools to create batches of counterfactuals …

abstract analysis analyze apply arxiv challenges counterfactual cs.ai cs.cl cs.hc cs.lg decision examples feature generated identify interactive key llms machine machine learning machine learning models textual type