Dustin Wright
LightNews LightNews
banner
dustinbwright.com
Dustin Wright
@dustinbwright.com
3.8K followers 1K following 53 posts
TT Assistant Professor @ Aalborg University Copenhagen | Making the world's knowledge reliable and accessible w/ ML + NLP | Former UCPH, UMSI, AI2, IBM Research, UCSD | https://dustinbwright.com
Posts Replies Media Videos
Pinned
dustinbwright.com
Dustin Wright @dustinbwright.com · Oct 13
Which, whose, and how much knowledge do LLMs represent?

I'm excited to share our preprint answering these questions:

"Epistemic Diversity and Knowledge Collapse in Large Language Models"

📄Paper: arxiv.org/pdf/2510.04226
💻Code: github.com/dwright37/ll...

1/10
Reposted by Dustin Wright
copenlu.bsky.social
🗣️ CopeNLU will be presenting papers on Explainable AI, Factuality, RAG & more at #ACL2026NLP

📍 Here's where to find us ⤵️

@apepa.bsky.social @rnv.bsky.social @dustinbwright.com @zainmujahid.me @gretawarren.bsky.social @lovhag.bsky.social @saravera.bsky.social @iaugenstein.bsky.social

#NLProc #AI
July 3, 2026 at 2:12 PM
Reposted by Dustin Wright
milanlp.bsky.social
🗣️ Last Friday, we had the pleasure of hosting @dustinbwright.com for an insightful talk on “LLMs Lack Perspective and Epistemic Diversity.”
The talk explored how diverse are the information and perspectives that people are being exposed to in this new era.

#NLProc
March 24, 2026 at 10:54 AM
dustinbwright.com
We updated our LLM epistemic diversity study with a stronger search baseline closer to true search diversity.

It beats every model, even though it is underestimated.

In other words, one can expect less information from an LLM vs Google searching.

See the new results here! arxiv.org/pdf/2510.04226
arxiv.org
February 3, 2026 at 10:42 AM
dustinbwright.com
News about our epistemic diversity paper!

💻 The code is now a python package! Installation instructions here: github.com/dwright37/ll...

🤗 All 1.6M model responses and 70M clustered claims are now available on HuggingFace! huggingface.co/datasets/dwr...

📄 Paper: arxiv.org/pdf/2510.04226
November 20, 2025 at 11:04 AM
Reposted by Dustin Wright
copenlu.bsky.social
Attending EMNLP 2025 this week? So is CopeNLU -- come find us there! ⤵️

www.copenlu.com/news/8-paper...

@apepa.bsky.social @rnv.bsky.social @kirekara.bsky.social @shoejoe.bsky.social @dustinbwright.com @zainmujahid.me @lucasresck.bsky.social @iaugenstein.bsky.social

#NLProc #AI #EMNLP2025
November 4, 2025 at 1:22 PM
dustinbwright.com
Heading to #EMNLP2025? Interested in automatic summarization? Then come to our poster for "Unstructured Evidence Attribution for Long Context Query Focused Summarization" !

⏰ When: Fri. Nov 7 14:00-15:30
🗺️ Where: Hall C

I'm unable to attend but @iaugenstein.bsky.social will present our work!
November 3, 2025 at 3:25 PM
dustinbwright.com
Which, whose, and how much knowledge do LLMs represent?

I'm excited to share our preprint answering these questions:

"Epistemic Diversity and Knowledge Collapse in Large Language Models"

📄Paper: arxiv.org/pdf/2510.04226
💻Code: github.com/dwright37/ll...

1/10
October 13, 2025 at 11:25 AM
dustinbwright.com
🎉 Our work on attribution in summarization is now accepted to #EMNLP2025 main! 🎉

"Unstructured Evidence Attribution for Long Context Query Focused Summarization"

w/ @zainmujahid.me , Lu Wang, @iaugenstein.bsky.social , and @davidjurgens.bsky.social
August 25, 2025 at 11:42 AM
dustinbwright.com
There’s something really special about seeing a physical print copy of our work 🤩

You can read “Efficiency is Not Enough: A Critical Perspective on Environmentally Sustainable AI” now in CACM!!!

dl.acm.org/doi/10.1145/...
July 26, 2025 at 7:51 PM
Reposted by Dustin Wright
handle.invalid
No fewer than three people were needed to cover all the aspects of our dialogue simulation paper. Thanks for the interest — check out the preprint. Link in Dustin’s post.
@dustinbwright.com @ic2s2.bsky.social #ic2s2
July 24, 2025 at 3:01 PM
dustinbwright.com
We had a great time talking about dialogue simulation with LLMs at @ic2s2.bsky.social !!! Amazing work by all of our colleagues at UMich.

See the preprint of this work here: arxiv.org/abs/2409.08330
July 24, 2025 at 1:54 PM
Reposted by Dustin Wright
ariannapera.bsky.social
The work “Extracting Participation in Collective Action from Social Media”, in collaboration with @lajello.bsky.social, at @ic2s2.bsky.social today!

Check out the paper ojs.aaai.org/index.php/IC... and models huggingface.co/ariannap22

Feat. poster and research buddy @alessianetwork.bsky.social ♥️
July 23, 2025 at 3:25 PM
dustinbwright.com
Open PhD positions in Denmark! daracademy.dk/fellowship/f...

If you want to apply to work with me and Johannes Bjerva at @aau.dk Copenhagen, I'll be at @ic2s2.bsky.social this week and @aclmeeting.bsky.social next week! DM me if you'd like to meet :)
Dara
daracademy.dk
July 21, 2025 at 1:26 PM
dustinbwright.com
Our critical perspective of AI efficiency is now online in Communications of the ACM!

cacm.acm.org/sustainabili...
Efficiency Is Not Enough: A Critical Perspective of Environmentally Sustainable AI – Communications of the ACM
cacm.acm.org
June 26, 2025 at 7:57 PM
dustinbwright.com
Join us for the Pre-ACL 2025 Workshop in Copenhagen, 26 July, 2025!
🇩🇰 With international NLP experts from Columbia, UCLA, University of Michigan, and more to Copenhagen to meet with the Danish NLP community. 🇩🇰
📅 Poster submission deadline: June 16, 2025
🔗 Register: www.aicentre.dk/events/pre-a...
Pre-ACL 2025 Workshop | Event | Pioneer Centre for Artificial Intelligence
www.aicentre.dk
June 16, 2025 at 2:08 PM
Reposted by Dustin Wright
aicentre.dk
Thanks to @dustinbwright.com (@copenlu.bsky.social) and @mxij.me (@itu.dk) for sharing insights on your research within the collaboratory of Speech & Language, at the Last Fridays Talks!
April 25, 2025 at 1:56 PM
dustinbwright.com
This work on fact checking with summarized evidence was accepted to #SIGIR 2025!
April 6, 2025 at 5:54 PM
Reposted by Dustin Wright
nicolang.bsky.social
Latest newsletter featuring a perspective paper by @dustinbwright.com et al. on "Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI"
@aicentre.dk
climateainordics.com Climate AI Nordics @climateainordics.com · Mar 28
📝🌍🍃Our latest newsletter is out! Read about coming webinars, and about why it is crucial to look at the impact of machine learning (ML) using systems thinking, i.e. across the entire life cycle of models, from development to deployment.
climateainordics.com/newsletter/2...
Climate AI Nordics Newsletter, March 2025
Welcome to the Climate AI Nordics Newsletter March 2025.Since the launch in October, the network has grown to 129 people spread over the Nordic countries (166 including international supporting affili...
climateainordics.com
March 29, 2025 at 12:02 AM
dustinbwright.com
I am still in need of emergency reviewers for ARR this cycle for the computational social science track, please DM me if you have capacity 🙏
March 25, 2025 at 3:18 PM
dustinbwright.com
Our long context summarization dataset is now on 🤗 Huggingface!

huggingface.co/datasets/dwr...

Use it as a training or a test set for long context query focused summarization! It includes evidence attribution of free-form text spans from the context, making summaries more transparent and reliable!
February 24, 2025 at 2:06 PM
dustinbwright.com
New preprint: "Unstructured Evidence Attribution for Long Context Query Focused Summarization"

We propose *unstructured* evidence attribution for long context summarization and a synthetic dataset called SUnsET which can help models perform this task.

Paper link: arxiv.org/abs/2502.14409

Thread ⬇️
February 21, 2025 at 1:43 PM
dustinbwright.com
📄 New preprint: "Collecting Cost-Effective, High-Quality Truthfulness Assessments with LLM Summarized Evidence"

We show: fact checking w/ crowd workers is more efficient when using LLM summaries, quality doesn't suffer.

arxiv.org/abs/2501.18265
Collecting Cost-Effective, High-Quality Truthfulness Assessments with LLM Summarized Evidence
With the degradation of guardrails against mis- and disinformation online, it is more critical than ever to be able to effectively combat it. In this paper, we explore the efficiency and effectiveness...
arxiv.org
January 31, 2025 at 1:18 PM