Isabelle Augenstein

Why they matter

Researcher with public evidence across NLP & language, AI research.

AI signals
2
past 30d
Sources
2
distinct domains
Discussions
0
past 30d
Latest signal
22d ago
View every signal from Isabelle Augenstein →
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/

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 …

arxiv.org
View on Bluesky · ♥ 24 ↻ 3 ↩ 1 · 3 from the directory shared this · 80d ago

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 …

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
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 →
View on Bluesky · ♥ 24 ↻ 3 ↩ 1 · 3 from the directory shared this · 80d ago
↻ Isabelle Augenstein reposted
@sekh-copenlu.bsky.social

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...

arxiv.org View on Bluesky →
↻ Isabelle Augenstein reposted
Alexandra Olteanu @aolteanu.bsky.social

I'm in Europe, and next week I'll be in Malmö (for #AIES until Weds) & Copenhagen speaking at the Pioneer Center for AI on Thurs www.aicentre.dk/events/20261... Thank you @gretawarren.bsky.social & @iaugenstein.bsky.social for hosting me! If you are around and want to chat/cat…

P1 guest talk by Responsible AI researcher Alexandra Olteanu | Event | Pioneer Centre for Artificial Intelligence aicentre.dk View on Bluesky →
↻ Isabelle Augenstein reposted
CopeNLU @copenlu.bsky.social

Highlights from a busy week at #EMNLP2026 in Budapest! 📸 CopeNLU et al. presented 7 papers on epistemic diversity, explanations and cultural alignment, 3 workshop papers and a keynote on human-centred fact-checking ✨ 📄 www.copenlu.com/news/7-paper... #NLProc

copenlu.com View on Bluesky →

At #EMNLP2026 LUHME today, I spoke about Explainable & Robust Automatic Fact Checking. AI-assisted fact-checking needs more than accurate verdicts: it needs evidence, faithful explanations, and effective uncertainty communication. isabelleaugenstein.github.io/slides/2026_... #…

isabelleaugenstein.github.io
View on Bluesky · ♥ 10 ↻ 1 ↩ 1 · 2 from the directory shared this · 24d ago
↻ Isabelle Augenstein reposted
CopeNLU @copenlu.bsky.social

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.…

Prismodtagere - H.C. Ørsted Selskabet hcoersted.dk View on Bluesky →

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.

Listed in AI Weekly's Who's Who of AI

Markdown: [![Listed in AI Weekly's Who's Who of AI](https://aiweekly.co/modules/custom/aiweekly_whoswho/images/whoswho-badge.svg)](https://aiweekly.co/whos-who/person/iaugenstein-bsky-social)