Skip to main content

🏢 University of Copenhagen

Unstructured Evidence Attribution for Long Context Query Focused Summarization
·3830 words·18 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Text Summarization 🏢 University of Copenhagen
LLMs struggle with positional bias and lack transparency when summarizing long contexts. This paper introduces SUnsET dataset and fine-tuning methods to improve unstructured evidence citation and summ…
Presumed Cultural Identity: How Names Shape LLM Responses
·2724 words·13 mins· loading · loading
AI Generated 🤗 Daily Papers AI Theory Fairness 🏢 University of Copenhagen
LLMs personalize based on user names, but this study reveals that cultural presumptions in LLM responses risk reinforcing stereotypes.
Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
·1354 words·7 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Question Answering 🏢 University of Copenhagen
Fact-checkers need explainable AI: This study reveals how AI tools can better support fact-checkers by providing explanations tailored to their workflows, addressing unmet needs, and improving the eff…