一作ACL 2026Findings· Findings of ACL
LIBERT y: A Causal Framework for Benchmarking Concept-Based Explanations of LLM s with Structural Counterfactuals
Gilat Toker · Nitay Calderon · Ohad Amosy · Roi Reichart
摘要
Concept-based explanations quantify how high-level concepts (e.g., gender or experience) influence model behavior, which is crucial for decision-makers in high-stakes domains. Recent work evaluates the faithfulness of such explanations by comparing them to reference causal effects estimated from...