3 citations · 5 across the 9 of their papers we have counts for
10 papers
Multilingual GSM-Symbolic: What determines capability transfer across languages?
Kenneth Enevoldsen, Riley Herchert, Sofie Mosegaard +22
We understand little about how capabilities acquired in one language carry over to another, or what governs this transfer: evaluations rely on incomparable, saturation-prone datase…
SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models
Hoda Fakharzadehjahromy, Emil Wiman, Andreas Bueff +2
Language models for low-resource languages still make frequent grammatical errors. Alignment methods such as RLHF and DPO can correct them. However, they require human judgements,…
Curated retrieval versus open web search in public AI information services: a coverage-trust trade-off
Hafsteinn Einarsson, Hafsteinn Birgir Einarsson, Jón Gunnar Ólafsson +1
Public institutions increasingly use large language models (LLMs) to answer citizens' questions, often pairing a curated knowledge base with live web search, yet whether the source…
Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377
To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…
MazeEval: A Benchmark for Testing Sequential Decision-Making in Language Models
Hafsteinn Einarsson
As Large Language Models (LLMs) increasingly power autonomous agents in robotics and embodied AI, understanding their spatial reasoning capabilities becomes crucial for ensuring re…
Hotter and Colder: A New Approach to Annotating Sentiment, Emotions, and Bias in Icelandic Blog Comments
Steinunn Rut Friðriksdóttir, Dan Saattrup Nielsen, Hafsteinn Einarsson
This paper presents Hotter and Colder, a dataset designed to analyze various types of online behavior in Icelandic blog comments. Building on previous work, we used GPT-4o mini to…
FoQA: A Faroese Question-Answering Dataset
Annika Simonsen, Dan Saattrup Nielsen, Hafsteinn Einarsson
We present FoQA, a Faroese extractive question-answering (QA) dataset with 2,000 samples, created using a semi-automated approach combining Large Language Models (LLMs) and human v…
Cross-Lingual QA as a Stepping Stone for Monolingual Open QA in Icelandic
Vésteinn Snæbjarnarson, Hafsteinn Einarsson
It can be challenging to build effective open question answering (open QA) systems for languages other than English, mainly due to a lack of labeled data for training. We present a…
Building an Icelandic Entity Linking Corpus
Steinunn Rut Friðriksdóttir, Valdimar Ágúst Eggertsson, Benedikt Geir Jóhannesson +3
In this paper, we present the first Entity Linking corpus for Icelandic. We describe our approach of using a multilingual entity linking model (mGENRE) in combination with Wikipedi…
A Warm Start and a Clean Crawled Corpus -- A Recipe for Good Language Models
Vésteinn Snæbjarnarson, Haukur Barri Símonarson, Pétur Orri Ragnarsson +4
We train several language models for Icelandic, including IceBERT, that achieve state-of-the-art performance in a variety of downstream tasks, including part-of-speech tagging, nam…