Bhaktipriya Radharapu
4 papers · 2023–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (2) π Cross-Pollinator (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12)
π£
Hot Topic Early Bird
Conferences
ACL (2)
EMNLP (2)
Top co-authors
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