A Geometric View of Counterfactual Behavior: Interaction of Boundary Proximity and Local Support
Counterfactual explanations seek small, semantically meaningful changes to an input that alter a model's prediction, and are widely used to interpret and audit machine learning systems. In modern vision, language, and multimodal systems, pretrained encoders map inputs to representation spaces, and downstream classifier heads impose decision boundaries within those spaces. As a result, the feasibility and distance of nearby counterfactuals depend on boundary placement relative to the data. Yet models with similar predictive performance can differ substantially in whether such changes are achievable and how far representations must move. This work examines this variation using a standardized local search probe across several pretrained encoders and linear classifier heads. Results show that despite similar predictive performance, models differ substantially in their counterfactual behavior. Under fixed representations, varying only the classifier head alters counterfactual outcomes while leaving predictive performance largely unchanged. This variation is explained by the interaction of decision-boundary proximity and local data support, which jointly determine whether prediction changes are both feasible and lie in regions supported by the data, and can also improve counterfactual search within fixed models. Together, these findings identify counterfactual behavior as a distinct dimension beyond predictive performance and show that it can be altered without changing accuracy, with implications for model selection, robustness, and the reliability of counterfactual methods.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Towards Personalized Treatment Plan: Geometrical Model-Agnostic Approach to Counterfactual Explanations
In our article, we describe a method for generating counterfactual explanations in high-dimensional spaces using four steps that involve fitting our dataset to a model, finding the decision boundary, determining constrai…
CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations
LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal mechanisms behind macro outcomes often remain unclear. This is challenging because emergence arises from inte…
Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations
Knowledge distillation is a promising approach to transfer capabilities from complex teacher models to smaller, resource-efficient student models that can be deployed easily, particularly in task-aware scenarios. However…
Knowledge DistillationClassifier Reconstruction Through Counterfactual-Aware Wasserstein Prototypes
Counterfactual explanations provide actionable insights by identifying minimal input changes required to achieve a desired model prediction. Beyond their interpretability benefits, counterfactuals can also be leveraged f…
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction
When language models process syntactically complex sentences, do they use their representations of syntax in a manner that is consistent with the grammar of the language? We propose AlterRep, an intervention-based method…
counterfactualSentence