Statistical Inference for Responsiveness Verification
Many safety failures in machine learning arise when models are used to assign predictions to people (often in settings like lending, hiring, or content moderation) without accounting for how individuals can change their inputs. In this work, we introduce a formal validation procedure for the responsiveness of predictions with respect to interventions on their features. Our procedure frames responsiveness as a type of sensitivity analysis in which practitioners control a set of changes by specifying constraints over interventions and distributions over downstream effects. We describe how to estimate responsiveness for the predictions of any model and any dataset using only black-box access, and how to use these estimates to support tasks such as falsification and failure probability estimation. We develop algorithms that construct these estimates by generating a uniform sample of reachable points, and demonstrate how they can promote safety in real-world applications such as recidivism prediction, organ transplant prioritization, and content moderation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Statistical Verification of Autonomous Systems using Surrogate Models and Conformal Inference
In this paper, we propose conformal inference based approach for statistical verification of CPS models. Cyber-physical systems (CPS) such as autonomous vehicles, avionic systems, and medical devices operate in highly un…
Autonomous VehiclesPrediction IntervalsSpeeding up Speculative Decoding via Sequential Approximate Verification
Speculative Decoding (SD) is a recently proposed technique for faster inference using Large Language Models (LLMs). SD operates by using a smaller draft LLM for autoregressively generating a sequence of tokens and a larg…
Prediction without Preclusion: Recourse Verification with Reachable Sets
Machine learning models are often used to decide who receives a loan, a job interview, or a public benefit. Models in such settings use features without considering their actionability. As a result, they can assign predi…
Adversarial RobustnessPredictionMedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain
Crowdworker-constructed natural language inference (NLI) datasets have been found to contain statistical artifacts associated with the annotation process that allow hypothesis-only classifiers to achieve better-than-rand…
Natural Language InferenceNegationMemory-Based vs. Context-Only Conditioning Produces Distinct Behavioral Patterns in Stateful Personalization
We study how conditioning context shapes personalization behavior in a teacher-facing educational recommender system. We compare contextual conditioning based on the current student question with memory-based conditionin…