Anthony Sicilia

45 papers A* 4A 1Journal 28Unranked 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
MixDPO: Modeling Preference Strength for Pluralistic Alignment.
CoRR
Saki Imai, Pedram Heydari, Anthony Sicilia, Asteria Kaeberlein, Katherine Atwell, Malihe Alikhani
2025 — conf
Accounting for Sycophancy in Language Model Uncertainty Estimation.
NAACL (Findings)
Anthony Sicilia, Mert Inan, Malihe Alikhani
2025 — conf
Adaptive Platt Scaling with Causal Interpretations for Self-Reflective Language Model Uncertainty Estimates.
EMNLP (Findings)
Anthony Sicilia, Malihe Alikhani
2025 J jnl
Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems.
CoRR
Mert Inan, Anthony Sicilia, Suvodip Dey, Vardhan Dongre, Tejas Srinivasan, Jesse Thomason, Gökhan Tür, Dilek Hakkani-Tür, Malihe Alikhani
2025 J jnl
Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI.
CoRR
Yuya Asano, Sabit Hassan, Paras Sharma, Anthony Sicilia, Katherine Atwell, Diane J. Litman, Malihe Alikhani
2025 A* conf
Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generation.
EMNLP
Mert Inan, Anthony Sicilia, Alex Xie, Saujas Vaduguru, Daniel Fried, Malihe Alikhani
2025 J jnl
Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generation.
CoRR
Mert Inan, Anthony Sicilia, Alex Xie, Saujas Vaduguru, Daniel Fried, Malihe Alikhani
2025 J jnl
Measuring How (Not Just Whether) VLMs Build Common Ground.
CoRR
Saki Imai, Mert Inan, Anthony Sicilia, Malihe Alikhani
2025 J jnl
Quantifying Sycophancy as Deviations from Bayesian Rationality in LLMs.
CoRR
Katherine Atwell, Pedram Heydari, Anthony Sicilia, Malihe Alikhani
2025 J jnl
SiLVERScore: Semantically-Aware Embeddings for Sign Language Generation Evaluation.
CoRR
Saki Imai, Mert Inan, Anthony Sicilia, Malihe Alikhani
2025 — conf
SignAlignLM: Integrating Multimodal Sign Language Processing into Large Language Models.
ACL (Findings)
Mert Inan, Anthony Sicilia, Malihe Alikhani
2025 J jnl
Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity.
CoRR
Jiayi Zhang, Simon Yu, Derek Chong, Anthony Sicilia, Michael R. Tomz, Christopher D. Manning, Weiyan Shi
2024 J jnl
Accounting for Sycophancy in Language Model Uncertainty Estimation.
CoRR
Anthony Sicilia, Mert Inan, Malihe Alikhani
2024 J jnl
Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios.
CoRR
Sabit Hassan, Anthony Sicilia, Malihe Alikhani
2024 J jnl
An Active Learning Framework for Inclusive Generation by Large Language Models.
CoRR
Sabit Hassan, Anthony Sicilia, Malihe Alikhani
2024 — conf
Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models.
ACL (Findings)
Anthony Sicilia, Hyunwoo Kim, Khyathi Raghavi Chandu, Malihe Alikhani, Jack Hessel
2024 J jnl
Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models.
CoRR
Anthony Sicilia, Hyunwoo Kim, Khyathi Raghavi Chandu, Malihe Alikhani, Jack Hessel
2024 J jnl
Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors.
CoRR
Anthony Sicilia, Malihe Alikhani
2024 J jnl
Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecasting.
CoRR
Anthony Sicilia, Malihe Alikhani
2024 — conf
Generating Signed Language Instructions in Large-Scale Dialogue Systems.
NAACL (Industry Track)
Mert Inan, Katherine Atwell, Anthony Sicilia, Lorna C. Quandt, Malihe Alikhani
2024 J jnl
Generating Signed Language Instructions in Large-Scale Dialogue Systems.
CoRR
Mert Inan, Katherine Atwell, Anthony Sicilia, Lorna C. Quandt, Malihe Alikhani
2024 — conf
HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations.
EACL (1)
Anthony Sicilia, Jennifer C. Gates, Malihe Alikhani
2023 J jnl
Domain adversarial neural networks for domain generalization: when it works and how to improve.
Mach. Learn.
Anthony Sicilia, Xingchen Zhao, Seong Jae Hwang
2023 J jnl
How Old is GPT?: The HumBEL Framework for Evaluating Language Models using Human Demographic Data.
CoRR
Anthony Sicilia, Jennifer C. Gates, Malihe Alikhani
2023 — conf
Learning to Generate Equitable Text in Dialogue from Biased Training Data.
ACL (1)
Anthony Sicilia, Malihe Alikhani
2023 J jnl
Learning to Generate Equitable Text in Dialogue from Biased Training Data.
CoRR
Anthony Sicilia, Malihe Alikhani
2022 — conf
LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue.
AACL/IJCNLP (Findings)
Anthony Sicilia, Malihe Alikhani
2022 J jnl
LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue.
CoRR
Anthony Sicilia, Malihe Alikhani
2022 J jnl
Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights.
CoRR
Anthony Sicilia, Tristan Maidment, Pat Healy, Malihe Alikhani
2022 J jnl
Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights.
Trans. Assoc. Comput. Linguistics
Anthony Sicilia, Tristan Maidment, Pat Healy, Malihe Alikhani
2022 J jnl
PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners.
CoRR
Anthony Sicilia, Katherine Atwell, Malihe Alikhani, Seong Jae Hwang
2022 A conf
PAC-Bayesian domain adaptation bounds for multiclass learners.
UAI
Anthony Sicilia, Katherine Atwell, Malihe Alikhani, Seong Jae Hwang
2022 A* conf
Test-time Fourier Style Calibration for Domain Generalization.
IJCAI
Xingchen Zhao, Chang Liu, Anthony Sicilia, Seong Jae Hwang, Yun Fu
2022 J jnl
Test-time Fourier Style Calibration for Domain Generalization.
CoRR
Xingchen Zhao, Chang Liu, Anthony Sicilia, Seong Jae Hwang, Yun Fu
2022 — conf
The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error.
ACL (Findings)
Katherine Atwell, Anthony Sicilia, Seong Jae Hwang, Malihe Alikhani
2022 J jnl
The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error.
CoRR
Katherine Atwell, Anthony Sicilia, Seong Jae Hwang, Malihe Alikhani
2021 J jnl
Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve.
CoRR
Anthony Sicilia, Xingchen Zhao, Seong Jae Hwang
2021 — conf
Multi-Domain Learning By Meta-Learning: Taking Optimal Steps In Multi-Domain Loss Landscapes By Inner-Loop Learning.
ISBI
Anthony Sicilia, Xingchen Zhao, Davneet S. Minhas, Erin O'Connor, Howard J. Aizenstein, William E. Klunk, Dana L. Tudorascu, Seong Jae Hwang
2021 J jnl
Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning.
CoRR
Anthony Sicilia, Xingchen Zhao, Davneet S. Minhas, Erin O'Connor, Howard Aizenstein, William E. Klunk, Dana Tudorascu, Seong Jae Hwang
2021 — conf
PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging.
MICCAI (3)
Anthony Sicilia, Xingchen Zhao, Anastasia Sosnovskikh, Seong Jae Hwang
2021 J jnl
PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging.
CoRR
Anthony Sicilia, Xingchen Zhao, Anastasia Sosnovskikh, Seong Jae Hwang
2021 — conf
Robust White Matter Hyperintensity Segmentation On Unseen Domain.
ISBI
Xingchen Zhao, Anthony Sicilia, Davneet S. Minhas, Erin O'Connor, Howard J. Aizenstein, William E. Klunk, Dana L. Tudorascu, Seong Jae Hwang
2021 J jnl
Robust White Matter Hyperintensity Segmentation on Unseen Domain.
CoRR
Xingchen Zhao, Anthony Sicilia, Davneet S. Minhas, Erin O'Connor, Howard Aizenstein, William E. Klunk, Dana Tudorascu, Seong Jae Hwang
2019 A* conf
DeepHoops: Evaluating Micro-Actions in Basketball Using Deep Feature Representations of Spatio-Temporal Data.
KDD
Anthony Sicilia, Konstantinos Pelechrinis, Kirk Goldsberry
2018 A* conf
PittGrub: A Frustration-Free System to Reduce Food Waste by Notifying Hungry College Students.
KDD
Mark Silvis, Anthony Sicilia, Alexandros Labrinidis