Mikhail Seleznyov
4 papers · 2024–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🐝
Cross-Pollinator
(15)
Conferences
ACL (2)
EMNLP (2)
Top co-authors
Keywords
large language model
(3)
in-context learning
(2)
metric learning
(1)
uncertainty quantification
(1)
knowledge distillation
(1)
parameter efficient
(1)
model alignment
(1)
model pruning
(1)
distribution shift
(1)
parameter efficiency
(1)
hallucination detection
(1)
evolutionary search
(1)
machine translation evaluation
(1)
prompt robustness
(1)
emergent misalignment
(1)
safety objective
(1)
model compression
(1)
atomic claim verification
(1)
model quantization
(1)
Papers
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
ACL 2026
Evolutionary Search for Automated Design of Uncertainty Quantification Methods
ACL 2026
When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs
EMNLP 2025
xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics
EMNLP 2024