Our paper on measuring epistemic diversity in LLMs is accepted to #EMNLP2026! We find that diversity has improved, though LLM output is much less diverse than Web search, especially for non-English. Paper: arxiv.org/pdf/2510.04226 Code/data: github.com/dwright37/ll... #NLProc …
Who's Who of AI
Isabelle Augenstein
Why they matter
Researcher with public evidence across NLP & language, AI research.
- AI signals
- 4 past 30d
- Sources
- 2 distinct domains
- Discusiones
- 1 past 30d
- Latest signal
- 19d ago
Professor at the University of Copenhagen. Explainable AI, Natural Language Processing, ML. Head of copenlu.bsky.social lab.
#NLProc #NLP #XAI
http://isabelleaugenstein.github.io/
What they're sharing
arxiv.org
GitHub - dwright37/llm-knowledge: A package for extracting knowledge and measuring epistemic diversity in LLMs. Associated with the paper "Epistemic Diversity and Knowledge Collapse in Large Language Models" github.com
arxiv.org
View on Bluesky →
MMMMM: A Unified Taxonomy for Investigating the Mechanisms of Multilingual MultiModal Misinformation arxiv.org
View on Bluesky →
Prismodtagere - H.C. Ørsted Selskabet hcoersted.dk
View on Bluesky →
Articles & links
Our paper on measuring epistemic diversity in LLMs is accepted to #EMNLP2026! We find that diversity has improved, though LLM output is much less diverse than Web search, especially for non-English. Paper: arxiv.org/pdf/2510.04226 Code/data: github.com/dwright37/ll... #NLProc …
AI Weekly's analysis
→
- A study of 27 LLMs across 155 topics and 12 countries found every system was less epistemically diverse than a basic web search baseline.
- Larger models were counterintuitively less diverse than smaller ones, while retrieval-augmented generation improved diversity across the systems tested.
- For country-specific topics, LLM parametric knowledge systematically reflected English sources over local-language ones, the authors report.
Read full analysis →
Isabelle Augenstein reposted
Excited to share that our work, "BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection", was accepted at the EMNLP 2026 (Findings). 📄 Paper (Updated): arxiv.org/pdf/2508.08855 💻 Code: github.com/copenlu/Bias...
Isabelle Augenstein reposted
How do people use images to spread misinformation online?🖼️ We developed a taxonomy, analysed 27k posts from X in 7 languages & found: 🔹Slanted framing of real images is more common than deepfakes and doctored images 🔹Vaccine misinfo borrows credibility via news screenshots ar…
Isabelle Augenstein reposted
Last week, @apepa.bsky.social was awarded a HC Ørsted Research Talent Award! 🏆 The prize recognises her research on how AI and LLMs can be made more trustworthy, transparent and accountable. Huge congrats to Pepa from all of us at CopeNLU, extremely well-deserved! 🎉 hcoersted.…
Their network
In Isabelle Augenstein's orbit
Center = Isabelle Augenstein. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you Isabelle Augenstein? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/iaugenstein-bsky-social)