Papers by Moa Johansson
Sudden Semantic Shifts in Swedish NATO discourse (2023.acl-srw)
Copied to clipboard
| Challenge: | Using word embeddings, we study sudden semantic shifts that occur when a sudden event radically changes public opinion on a topic. |
| Approach: | They use word embeddings to study how Twitter associations evolve . they find domain knowledge and data selection are of prime importance when using word embeds to understand semantic shifts. |
| Outcome: | The proposed method validates associations on Twitter with NATO in real-world events but is difficult to distinguish between noise and real-time signals. |
Benchmarking Debiasing Methods for LLM-based Parameter Estimates (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are expensive yet powerful ways to annotate text, and can be inconsistent when compared with experts. |
| Approach: | They propose to combine LLM annotations with a limited number of expensive expert annotations to produce valid estimates. |
| Outcome: | The proposed methods produce consistent estimates under theoretical assumptions, but they are not comparable across finite datasets. |
The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are useful interfaces to factual knowledge, but their usefulness is limited by their tendency to deliver inconsistent answers to semantically equivalent questions. |
| Approach: | They evaluate the effectiveness of up-scaling and augmenting the LM with a passage retrieval database to reduce inconsistency. |
| Outcome: | The proposed models reduce inconsistency but retrieval augmentation is more efficient. |
Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion (2025.findings-acl)
Copied to clipboard
| Challenge: | Language models (LMs) can make a correct prediction based on many possible signals in a prompt, but not all corresponding to recall of factual associations. |
| Approach: | They propose a model-specific recipe for constructing datasets with examples of four different prediction scenarios: generic language modeling, guesswork, heuristics recall and exact fact recall. |
| Outcome: | The proposed model-specific recipe yields distinct results for each scenario. |
Recursive numeral systems are highly regular and easy to process (2026.eacl-long)
Copied to clipboard
Ponrawee Prasertsom, Andrea Silvi, Jennifer Culbertson, Devdatt Dubhashi, Moa Johansson, Kenny Smith
| Challenge: | Existing studies on linguistic efficiency have focused on the systematicity of forms, a key property of natural language. |
| Approach: | They propose to incorporate regularity across sets of forms in studies of efficiency in language . they use the Minimum Description Length approach to measure regularity and processing complexity . |
| Outcome: | The proposed method shows that recursive numeral systems are more efficient with respect to regularity and processing complexity. |