Carsten Eickhoff
32 papers · 2020–2026 · 8 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 ↓+9 more ↓ Show less ↑
🗺️ Taxonomy Completionist (59) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(11)
🧬
Topic Evolution
🏆
Keyword Champion
(4)
⚡
Prolific Year · Prolific
🗃️
Keyword Collector
(151)
❓
The Questioner
(2)
🔥
Unstoppable · Bronze
🌈
Renaissance Researcher
(6)
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(22)
Natural Language Processing
(20)
Artificial Intelligence
(19)
Core AI
(19)
Deep Learning
(13)
Resources & Methods
(13)
Core Methods
(12)
Learning Types · Machine Learning
(11)
Generation
(7)
Learning Types · Deep Learning
(6)
Applications
(5)
Architectures
(4)
Application Areas
(3)
Models
(3)
Optimization & Theory
(3)
Keywords
mechanistic interpretability
(6)
large language model
(6)
information retrieval
(5)
representation learning
(4)
vision-language model
(4)
text generation
(4)
attention head
(4)
text summarization
(3)
contrastive learning
(3)
neural network
(3)
word embedding
(3)
embedding space
(2)
abstractive summarization
(2)
transformer language model
(2)
in-context learning
(2)
cosine similarity
(2)
embedding analysis
(2)
circuit analysis
(2)
dense retrieval
(2)
text simplification
(2)
Papers
Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
EACL 2026
Mechanisms of Prompt-Induced Hallucination in Vision–Language Models
ACL 2026
A Survey on LLM-Assisted Clinical Trial Recruitment
IJCNLP 2025
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance
EMNLP 2025
Enhancing Retrieval-Augmented Generation: A Study of Best Practices
COLING 2025
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
ACL 2025
Interpretability Analysis of Arithmetic In-Context Learning in Large Language Models
EMNLP 2025
Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline
EMNLP 2025
Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25
EMNLP 2025
Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts
EMNLP 2025
The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling
ICLR 2025
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
NAACL 2025
Circuit Component Reuse Across Tasks in Transformer Language Models
ICLR 2024
CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization
COLING 2024
Language Models Implement Simple Word2Vec-style Vector Arithmetic
NAACL 2024
Re-Evaluating Evaluation for Multilingual Summarization
EMNLP 2024
Stable Anisotropic Regularization
ICLR 2024
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
NeurIPS 2024
Text Simplification via Adaptive Teaching
ACL 2024
Enhancing the Ranking Context of Dense Retrieval through Reciprocal Nearest Neighbors
EMNLP 2023
Linearly Mapping from Image to Text Space
ICLR 2023
Outlier Dimensions Encode Task Specific Knowledge
EMNLP 2023
Parameter-efficient Modularised Bias Mitigation via AdapterFusion
EACL 2023
SIMSUM: Document-level Text Simplification via Simultaneous Summarization
ACL 2023
CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking
EMNLP 2022
Garden Path Traversal in GPT-2
EMNLP 2022
IsoScore: Measuring the Uniformity of Embedding Space Utilization
ACL 2022
NEWTS: A Corpus for News Topic-Focused Summarization
ACL 2022
Pretraining on Interactions for Learning Grounded Affordance Representations
NAACL 2022
Self-Supervised Neural Topic Modeling
EMNLP 2021
SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domain
NAACL 2021
Are “Undocumented Workers” the Same as “Illegal Aliens”? Disentangling Denotation and Connotation in Vector Spaces
EMNLP 2020