Aakriti Agrawal
5 papers · 2023–2025 · 5 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
large language model
(2)
robustness
(1)
weakly supervised learning
(1)
knowledge distillation
(1)
item response theory
(1)
automatic speech recognition
(1)
expert selection
(1)
adversarial attack
(1)
benchmark dataset
(1)
language model
(1)
uncertainty estimation
(1)
teacher-student model
(1)
content generation
(1)
answer selection
(1)
difficulty estimation
(1)
copyright infringement
(1)
multi-agent system
(1)
adversarial
(1)
watermark
(1)
images
(1)
Papers
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
NAACL 2025
Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
EMNLP 2025
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
NeurIPS 2024
WAVES: Benchmarking the Robustness of Image Watermarks
ICML 2024
Learning When to Trust Which Teacher for Weakly Supervised ASR
Interspeech 2023