paper-with-me

홈 › Papers

Prompt-Counterfactual Explanations for Generative AI System Behavior

2026-01-06 · Sofie Goethals, Foster Provost, João Sedoc arxiv

As generative AI systems become integrated into real-world applications, organizations increasingly need to be able to understand and interpret their behavior. In particular, decision-makers need to understand what causes generative AI systems to exhibit specific output characteristics. Within this general topic, this paper examines a key question: what is it about the input -- the prompt -- that causes an LLM-based generative AI system to produce output that exhibits specific characteristics, such as toxicity, negative sentiment, or political bias. To examine this question, we adapt a common technique from the Explainable AI literature: counterfactual explanations. We explain why traditional counterfactual explanations cannot be applied directly to generative AI systems, due to several differences in how generative AI systems function. We then propose a flexible framework that adapts counterfactual explanations to non-deterministic, generative AI systems in scenarios where downstream classifiers can reveal key characteristics of their outputs. Based on this framework, we introduce an algorithm for generating prompt-counterfactual explanations (PCEs). Finally, we demonstrate the production of counterfactual explanations for generative AI systems with three case studies, examining different output characteristics (viz., political leaning, toxicity, and sentiment). The case studies further show that PCEs can streamline prompt engineering to suppress undesirable output characteristics and can enhance red-teaming efforts to uncover additional prompts that elicit undesirable outputs. Ultimately, this work lays a foundation for prompt-focused interpretability in generative AI: a capability that will become indispensable as these models are entrusted with higher-stakes tasks and subject to emerging regulatory requirements for transparency and accountability.

📄 PDF Abstract BibTeX arXiv:2601.03156

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning

2021-01-29 · Matthew L. Olson, Roli Khanna, Lawrence Neal, Fuxin Li 외

Counterfactual explanations, which deal with "why not?" scenarios, can provide insightful explanations to an AI agent's behavior. In this work, we focus on generating counterfactual explanations for deep reinforcement le…

counterfactualDeep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments

2026-08-17 · Adam Karvonen, Euan Ong, Subhash Kantamneni, Samuel Marks arxiv

Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors. But what constitutes a "good" explanation? In this work, we evaluate explanations thr…

Evaluating Robustness of Counterfactual Explanations

2021-03-03 · André Artelt, Valerie Vaquet, Riza Velioglu, Fabian Hinder 외

Transparency is a fundamental requirement for decision making systems when these should be deployed in the real world. It is usually achieved by providing explanations of the system's behavior. A prominent and intuitive …

counterfactualDecision MakingFairness

Convex optimization for actionable \& plausible counterfactual explanations

2021-05-17 · André Artelt, Barbara Hammer

Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and …

counterfactualDecision Making

CountARFactuals -- Generating plausible model-agnostic counterfactual explanations with adversarial random forests

2024-04-04 · Susanne Dandl, Kristin Blesch, Timo Freiesleben, Gunnar König 외

Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model's behavior, they hint users towards possible acti…

counterfactual