Picture for Anders Søgaard

Anders Søgaard

Does Instruction Tuning Make LLMs More Consistent?

Add code
Apr 30, 2024
Viaarxiv icon

MuLan: A Study of Fact Mutability in Language Models

Add code
Apr 03, 2024
Viaarxiv icon

Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach

Add code
Mar 22, 2024
Viaarxiv icon

Word Order and World Knowledge

Add code
Mar 01, 2024
Figure 1 for Word Order and World Knowledge
Figure 2 for Word Order and World Knowledge
Figure 3 for Word Order and World Knowledge
Figure 4 for Word Order and World Knowledge
Viaarxiv icon

Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations

Add code
Feb 29, 2024
Viaarxiv icon

CreoleVal: Multilingual Multitask Benchmarks for Creoles

Add code
Oct 30, 2023
Viaarxiv icon

Copyright Violations and Large Language Models

Add code
Oct 20, 2023
Viaarxiv icon

Large language models converge toward human-like concept organization

Add code
Aug 29, 2023
Figure 1 for Large language models converge toward human-like concept organization
Figure 2 for Large language models converge toward human-like concept organization
Figure 3 for Large language models converge toward human-like concept organization
Figure 4 for Large language models converge toward human-like concept organization
Viaarxiv icon

Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models

Add code
Aug 17, 2023
Figure 1 for Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
Figure 2 for Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
Figure 3 for Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
Figure 4 for Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
Viaarxiv icon

Mapping Brains with Language Models: A Survey

Jun 08, 2023
Figure 1 for Mapping Brains with Language Models: A Survey
Figure 2 for Mapping Brains with Language Models: A Survey
Viaarxiv icon