Anton Korznikov
4 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
❓
The Questioner
Conferences
EACL (2)
AACL (1)
IJCNLP (1)
Top co-authors
Keywords
hallucination detection
(2)
sparse autoencoder
(2)
uncertainty estimation
(2)
reasoning model
(1)
causal intervention
(1)
reward estimation
(1)
multilingual natural language processing
(1)
process reward model
(1)
scientific question answering
(1)
large language model
(1)
linear probe
(1)
instruction-tuned language model
(1)
formatting artifact
(1)
multilingual modern bert
(1)
factual accuracy
(1)
decoder-based judge
(1)
feature representation
(1)
language model
(1)
Papers
Out of Distribution, Out of Luck: Process Rewards Misguide Reasoning Models
EACL 2026
Feature Drift: How Fine-Tuning Repurposes Representations in LLMs
EACL 2026
SmurfCat at SHROOM-CAP: Factual but Awkward? Fluent but Wrong? Tackling Both in LLM Scientific QA
IJCNLP 2025
SmurfCat at SHROOM-CAP: Factual but Awkward? Fluent but Wrong? Tackling Both in LLM Scientific QA
AACL 2025