Aakriti Agrawal
Scholar

Aakriti Agrawal

Google Scholar ID: 2RRnCRMAAAAJ
University of Maryland, College Park
LLM SuperalignmentLLM alignmentGenerative AIReinforcement LearningMulti-Agent Systems
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
292
 
H-index
6
 
i10-index
6
 
Publications
14
 
Co-authors
18
list available
Contact
No contact links provided.
Publications
8 items
The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning
2026
Cited
0
VeriGate: Verifier-Gated Step-Level Supervision for GRPO
2026
Cited
0
Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings
2025
Cited
0
Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
2025
Cited
0
EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
2025
Cited
0
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
2025
Cited
0
EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?
arXiv.org · 2024
Cited
7
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
Neural Information Processing Systems · 2024
Cited
7
Resume (English only)
Co-authors
18 total
Furong Huang
Furong Huang
Associate Professor of Computer Science, University of Maryland
Mucong Ding
Mucong Ding
Department of Computer Science, University of Maryland
Bang An
Bang An
University of Maryland, College Park
Tom Goldstein
Tom Goldstein
Volpi-Cupal Professor of Computer Science, University of Maryland
Sicheng Zhu
Sicheng Zhu
Member of Technical Staff, OpenAI
Jordan K Terry
Jordan K Terry
CEO, Farama Foundation
Co-author 7
Co-author 7
Yuxin Wen
Yuxin Wen
University of Maryland