Get started
Author

Bhaktipriya Radharapu

Observed name: Radharapu, Bhaktipriya
ORCID: 0009-0003-4774-6651
Observed ORCID: 0009-0003-4774-6651
OpenAlex ID: A5092160641
AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications
2023 · Bhaktipriya Radharapu, Kevin Robinson, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 21
PDF
Safety and Fairness for Content Moderation in Generative Models
2023 · Hao, Susan, Kumar, Piyush, et al. · arXiv (Cornell University) · 4
PDF
ShieldGemma: Generative AI Content Moderation Based on Gemma
2024 · Zeng, Wenjun, Liu, Yuchi, et al. · arXiv (Cornell University) · 3
PDF
Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble
2024 · Olivia Sturman, Aparna R Joshi, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 3
PDF
Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset
2025 · Zhang, Lily Hong, Milli, Smitha, et al. · arXiv (Cornell University) · 1
PDF
Arbiters of Ambivalence: Challenges of using LLMs in No-Consensus tasks
2025 · Bhaktipriya Radharapu, Manon Revel, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 1
PDF
RealSeal: Revolutionizing Media Authentication with Real-Time Realism Scoring
2024 · Bhaktipriya Radharapu, Harish Krishna · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · 1
Taxonomy of Adversarial Attacks on Text-to-Image Generative Models
2023 · Bhaktipriya Radharapu, Harish Krishna · IEEE Conference on Artificial Intelligence (CAI) · 1
Jagged Judges: Epistemic Stability Under Perturbation, Pressure, and Persistence
2026 · Zhao, Justin, Bhattacharjee, Himaghna, et al. · arXiv (Cornell University)
PDF
Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
2026 · Association for Computational Linguistics 2026, Cancedda, Nicola, et al. · Underline Science Inc.
Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
2026 · Bhaktipriya Radharapu, Eshika Saxena, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
2025 · Radharapu, Bhaktipriya, Saxena, Eshika, et al. · arXiv (Cornell University)
PDF
Chained Tuning Leads to Biased Forgetting
2024 · Ung, Megan, Sun, Alicia, et al. · arXiv (Cornell University)
PDF
RealSeal: Revolutionizing Media Authentication with Real-Time Realism Scoring
2024 · Radharapu, Bhaktipriya, Krishna, Harish · arXiv (Cornell University)
PDF
Works count: 17
Citation count: 40
H-index: 3
I10-index: 1
Year
Topic
Type