Prasanna Sattigeri

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs ACL 2026 Multi-component Causal Tracing in Large Language Models ACL 2026 Evaluating the Prompt Steerability of Large Language Models NAACL 2025 Granite Guardian: Comprehensive LLM Safeguarding NAACL 2025 Multi-Level Explanations for Generative Language Models ACL 2025 Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage? NeurIPS 2024 Causal Bandits with General Causal Models and Interventions AISTATS 2024 ComVas: Contextual Moral Values Alignment System IJCAI 2024 Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling JMLR 2024 Graph-based Uncertainty Metrics for Long-form Language Model Generations NeurIPS 2024 Interventional Causal Discovery in a Mixture of DAGs NeurIPS 2024 Language Models in Dialogue: Conversational Maxims for Human-AI Interactions EMNLP 2024 Thermometer: Towards Universal Calibration for Large Language Models ICML 2024 Value Alignment from Unstructured Text EMNLP 2024 WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia NeurIPS 2024 Causal Bandits for Linear Structural Equation Models JMLR 2023 Effective Human-AI Teams via Learned Natural Language Rules and Onboarding NeurIPS 2023 Efficient Equivariant Transfer Learning from Pretrained Models NeurIPS 2023 Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models AAAI 2023 Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model AAAI 2023 Reliable Gradient-free and Likelihood-free Prompt Tuning EACL 2023 Who Should Predict? Exact Algorithms For Learning to Defer to Humans AISTATS 2023 AI Explainability 360: Impact and Design AAAI 2022 Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting NeurIPS 2022 Intervention target estimation in the presence of latent variables UAI 2022 Selective Regression under Fairness Criteria ICML 2022 AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition ICLR 2021 Conditionally independent data generation UAI 2021 Detector-Free Weakly Supervised Grounding by Separation ICCV 2021 Fair Selective Classification Via Sufficiency ICML 2021 Scalable Intervention Target Estimation in Linear Models NeurIPS 2021 StarNet: towards Weakly Supervised Few-Shot Object Detection AAAI 2021 AI Explainability 360: An Extensible Toolkit for Understanding Data and Machine Learning Models JMLR 2020 A Natural Language Processing System for Extracting Evidence of Drug Repurposing from Scientific Publications AAAI 2020 AR-Net: Adaptive Frame Resolution for Efficient Action Recognition ECCV 2020 Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors AAAI 2020 OnlineAugment: Online Data Augmentation with Less Domain Knowledge ECCV 2020 Optimizing Mode Connectivity via Neuron Alignment NeurIPS 2020 TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification ECCV 2020 Learning New Tricks From Old Dogs: Multi-Source Transfer Learning From Pre-Trained Networks NeurIPS 2019 Co-regularized Alignment for Unsupervised Domain Adaptation NeurIPS 2018 Variational Inference of Disentangled Latent Concepts from Unlabeled Observations ICLR 2018 Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference NeurIPS 2017