Sunishchal Dev
7 papers · 2025–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer π Conference Polyglot (3) π Interdisciplinary Bridge
β
Rising Star
(6)
π
Keyword Champion
(2)
β‘
Prolific Year
(6)
Conferences
AACL (2)
ACL (2)
IJCNLP (2)
ICML (1)
Top co-authors
Keywords
hallucination detection
(2)
internal state analysis
(2)
large language model
(2)
gradient projection
(2)
hidden state vector
(2)
catastrophic forgetting
(2)
benchmark evaluation
(2)
clustering analysis
(2)
continual learning
(2)
scientific methodology
(1)
methodology prediction
(1)
ai research
(1)
plasticity stability
(1)
emergent misalignment
(1)
safety objective
(1)
zero-shot learning
(1)
in-context learning
(1)
neural network optimization
(1)
model alignment
(1)
selective forgetting
(1)
Papers
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
ACL 2026
Position: Human Baselines in Model Evaluations Need Rigor and Transparency (With Recommendations & Reporting Checklist)
ICML 2025
Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering
IJCNLP 2025
FrontierScience Bench: Evaluating AI Research Capabilities in LLMs
ACL 2025
Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering
AACL 2025
Mitigating Forgetting in Continual Learning with Selective Gradient Projection
AACL 2025
Mitigating Forgetting in Continual Learning with Selective Gradient Projection
IJCNLP 2025