Carsten Eickhoff
33 papers · 2020–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🏃 Academic Marathon (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) 🐝 Cross-Pollinator (4)
🌍
Conference Polyglot
(9)
🏃
Academic Marathon
(5)
🧭
Keyword Pioneer
🧬
Topic Evolution
🔥
Unstoppable
(6)
⚡
Prolific Year
(7)
💎
Century Club
(31)
❓
The Questioner
(2)
🗃️
Keyword Collector
(143)
Conferences
EMNLP (12)
ACL (6)
ICLR (4)
NAACL (4)
COLING (2)
EACL (2)
AACL (1)
IJCNLP (1)
NIPS (1)
Top co-authors
Keywords
information retrieval
(5)
large language model
(5)
mechanistic interpretability
(4)
text generation
(4)
representation learning
(3)
word embedding
(3)
vision-language model
(3)
neural network
(3)
text summarization
(3)
attention head
(3)
contrastive learning
(3)
abstractive summarization
(2)
embedding analysis
(2)
knowledge aggregation
(2)
in-context learning
(2)
patient matching
(2)
clinical trial recruitment
(2)
text simplification
(2)
dense retrieval
(2)
language model
(2)
Papers
Mechanisms of Prompt-Induced Hallucination in Vision–Language Models
ACL 2026
Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
EACL 2026
Interpretability Analysis of Arithmetic In-Context Learning in Large Language Models
EMNLP 2025
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
NAACL 2025
A Survey on LLM-Assisted Clinical Trial Recruitment
AACL 2025
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
ACL 2025
Enhancing Retrieval-Augmented Generation: A Study of Best Practices
COLING 2025
A Survey on LLM-Assisted Clinical Trial Recruitment
IJCNLP 2025
The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling
ICLR 2025
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance
EMNLP 2025
Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts
EMNLP 2025
Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25
EMNLP 2025
Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline
EMNLP 2025
Re-Evaluating Evaluation for Multilingual Summarization
EMNLP 2024
Text Simplification via Adaptive Teaching
ACL 2024
CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization
COLING 2024
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
NIPS 2024
Circuit Component Reuse Across Tasks in Transformer Language Models
ICLR 2024
Stable Anisotropic Regularization
ICLR 2024
Language Models Implement Simple Word2Vec-style Vector Arithmetic
NAACL 2024
Outlier Dimensions Encode Task Specific Knowledge
EMNLP 2023
Parameter-efficient Modularised Bias Mitigation via AdapterFusion
EACL 2023
Linearly Mapping from Image to Text Space
ICLR 2023
SIMSUM: Document-level Text Simplification via Simultaneous Summarization
ACL 2023
Enhancing the Ranking Context of Dense Retrieval through Reciprocal Nearest Neighbors
EMNLP 2023
Garden Path Traversal in GPT-2
EMNLP 2022
IsoScore: Measuring the Uniformity of Embedding Space Utilization
ACL 2022
Pretraining on Interactions for Learning Grounded Affordance Representations
NAACL 2022
NEWTS: A Corpus for News Topic-Focused Summarization
ACL 2022
CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking
EMNLP 2022
SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domain
NAACL 2021
Self-Supervised Neural Topic Modeling
EMNLP 2021
Are “Undocumented Workers” the Same as “Illegal Aliens”? Disentangling Denotation and Connotation in Vector Spaces
EMNLP 2020