Petr Sojka
7 papers · 2021–2025 · 3 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(23)
🐣
Hot Topic Early Bird
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(5)
Natural Language Processing
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Application Areas
(3)
Applications
(3)
Learning Types · Machine Learning
(3)
Core AI
(2)
Learning Paradigms
(2)
Learning Types · Deep Learning
(2)
Resources & Methods
(2)
Architectures
(1)
Core Methods
(1)
Keywords
in-context learning
(2)
domain adaptation
(2)
language model
(2)
few-shot learning
(2)
ensemble learning
(1)
machine translation
(1)
natural language inference
(1)
cross-lingual transfer
(1)
question answering
(1)
model adaptation
(1)
instruction tuning
(1)
regression analysis
(1)
concept learning
(1)
semantic similarity
(1)
spurious correlation
(1)
debiasing method
(1)
instruction fine-tuning
(1)
model scaling
(1)
zero-shot evaluation
(1)
textual entailment
(1)
Papers
Towards the Roots of the Negation Problem: A Multilingual NLI Dataset and Model Scaling Analysis
EMNLP 2025
Concept-aware Data Construction Improves In-context Learning of Language Models
ACL 2024
Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models
EACL 2024
Resources and Few-shot Learners for In-context Learning in Slavic Languages
EACL 2023
Soft Alignment Objectives for Robust Adaptation of Language Generation
ACL 2023
Adaptor: Objective-Centric Adaptation Framework for Language Models
ACL 2022
Regressive Ensemble for Machine Translation Quality Evaluation
EMNLP 2021