Bhaktipriya Radharapu
4 papers · 2023–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(14)
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
large language model
(2)
preference alignment
(1)
confidence calibration
(1)
human judgment
(1)
bias mitigation
(1)
scalable oversight
(1)
uncertainty estimation
(1)
safety evaluation
(1)
counterfactual fairness
(1)
ai alignment
(1)
adversarial testing
(1)
human disagreement
(1)
model debiasing
(1)
brier score
(1)
data generation
(1)
data reweighting
(1)
large language model alignment
(1)
no-consensus task
(1)
judge model
(1)
linear probe
(1)
Papers
Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
ACL 2026
Arbiters of Ambivalence: Challenges of using LLMs in No-Consensus tasks
ACL 2025
Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble
EMNLP 2024
AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications
EMNLP 2023