Moa Johansson
6 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (14) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15)
❓
The Questioner
(2)
Conferences
ACL (2)
EMNLP (2)
EACL (1)
NAACL (1)
Top co-authors
Keywords
large language model
(2)
causal inference
(2)
statistical inference
(1)
sentiment analysis
(1)
parameter estimation
(1)
question answering
(1)
minimum description length
(1)
label efficiency
(1)
causal effect
(1)
language model
(1)
debiasing method
(1)
semantic shift
(1)
fact recall
(1)
retrieval augmentation
(1)
bias reduction
(1)
information flow
(1)
word embedding
(1)
factual consistency
(1)
interpretability method
(1)
causal tracing
(1)
Papers
Recursive numeral systems are highly regular and easy to process
EACL 2026
Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion
ACL 2025
Benchmarking Debiasing Methods for LLM-based Parameter Estimates
EMNLP 2025
Can Large Language Models (or Humans) Disentangle Text?
NAACL 2024
Sudden Semantic Shifts in Swedish NATO discourse
ACL 2023
The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models
EMNLP 2023