Picture for Richard Johansson

Richard Johansson

How Well Do Large Language Models Disambiguate Swedish Words?

Add code
Oct 30, 2024
Viaarxiv icon

Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion

Add code
Oct 18, 2024
Viaarxiv icon

Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models

Add code
Oct 07, 2024
Viaarxiv icon

Can Large Language Models (or Humans) Distill Text?

Add code
Mar 25, 2024
Viaarxiv icon

What Happens to a Dataset Transformed by a Projection-based Concept Removal Method?

Add code
Mar 24, 2024
Viaarxiv icon

The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models

Add code
Nov 02, 2023
Viaarxiv icon

Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models

Add code
May 25, 2023
Viaarxiv icon

An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systems

Add code
Apr 17, 2023
Viaarxiv icon

On the Generalization Ability of Retrieval-Enhanced Transformers

Add code
Feb 23, 2023
Viaarxiv icon

Controlling for Stereotypes in Multimodal Language Model Evaluation

Add code
Feb 03, 2023
Viaarxiv icon