Picture for Marius Mosbach

Marius Mosbach

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Add code
Apr 09, 2024
Viaarxiv icon

What explains the success of cross-modal fine-tuning with ORCA?

Add code
Mar 20, 2024
Figure 1 for What explains the success of cross-modal fine-tuning with ORCA?
Figure 2 for What explains the success of cross-modal fine-tuning with ORCA?
Figure 3 for What explains the success of cross-modal fine-tuning with ORCA?
Figure 4 for What explains the success of cross-modal fine-tuning with ORCA?
Viaarxiv icon

The Hidden Space of Transformer Language Adapters

Feb 20, 2024
Figure 1 for The Hidden Space of Transformer Language Adapters
Figure 2 for The Hidden Space of Transformer Language Adapters
Figure 3 for The Hidden Space of Transformer Language Adapters
Figure 4 for The Hidden Space of Transformer Language Adapters
Viaarxiv icon

The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis

Feb 20, 2024
Viaarxiv icon

Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures

Add code
Nov 08, 2023
Viaarxiv icon

Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation

Add code
May 30, 2023
Figure 1 for Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation
Figure 2 for Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation
Figure 3 for Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation
Figure 4 for Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation
Viaarxiv icon

Weaker Than You Think: A Critical Look atWeakly Supervised Learning

Add code
May 27, 2023
Figure 1 for Weaker Than You Think: A Critical Look atWeakly Supervised Learning
Figure 2 for Weaker Than You Think: A Critical Look atWeakly Supervised Learning
Figure 3 for Weaker Than You Think: A Critical Look atWeakly Supervised Learning
Figure 4 for Weaker Than You Think: A Critical Look atWeakly Supervised Learning
Viaarxiv icon

Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models

Add code
Aug 05, 2022
Figure 1 for Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models
Figure 2 for Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models
Figure 3 for Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models
Figure 4 for Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models
Viaarxiv icon

Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions

Jul 28, 2022
Figure 1 for Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions
Figure 2 for Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions
Figure 3 for Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions
Figure 4 for Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions
Viaarxiv icon

StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypes

Add code
May 27, 2022
Figure 1 for StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypes
Figure 2 for StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypes
Figure 3 for StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypes
Figure 4 for StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypes
Viaarxiv icon