Anja Reusch
6 papers · 2022–2025 · 4 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
(10)
👥
Mega-Team · Squad
Venues
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(3)
Machine Learning
(3)
Architectures
(2)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Application Areas
(1)
Applications
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Reasoning
(1)
Keywords
mechanistic interpretability
(3)
transformer model
(3)
text classification
(1)
data augmentation
(1)
question answering
(1)
integer programming
(1)
hierarchical structure
(1)
circuit analysis
(1)
sparse autoencoder
(1)
model optimization
(1)
circuit discovery
(1)
causal analysis
(1)
arithmetic reasoning
(1)
embedding analysis
(1)
balanced accuracy
(1)
mathematical structure
(1)
large language model
(1)
attribution score
(1)
clickbait spoiling
(1)
structural probing
(1)
Papers
Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
ICLR 2025
BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection
EMNLP 2025
MIB: A Mechanistic Interpretability Benchmark
ICML 2025
Mr-Fosdick at SemEval-2023 Task 5: Comparing Dataset Expansion Techniques for Non-Transformer and Transformer Models: Improving Model Performance through Data Augmentation
SemEval 2023
Sabrina Spellman at SemEval-2023 Task 5: Discover the Shocking Truth Behind this Composite Approach to Clickbait Spoiling!
SemEval 2023
Extracting Operator Trees from Model Embeddings
EMNLP 2022