Dustin Wright
@dustin_wright37
Postdoc @uni_copenhagen @CopeNLU | Making the world's knowledge reliable and accessible w/ ML + NLP | Former @umsi @allen_ai @IBMResearch @ucsd_cse
Excited to announce that I was granted a 2-year postdoc fellowship from @DataScienceDK to work on faithful lay summarization, with application to science communication!
The Better Place update for last week: - at least 2.5K new #NLProc people, judging by the number of those who used Maria's starter pack - ACL, COLM, FAccT, ICLR have joined - much better engagement with content you post, external links aren't penalized See you there!
The only piece of good news this morning is that in the bluer place, Maria Antoniak made a starter pack of #NLProc people already there. It's pinned in her profile. Feels surreal to have real engagement on posts and see real conversations.
🥳 The party in the bluer place goes on, join if you haven't! It's even hard to believe - at least 1K NLP researchers seem to have joined in the past few days. This is just one of many cool starter packs.
The only piece of good news this morning is that in the bluer place, Maria Antoniak made a starter pack of #NLProc people already there. It's pinned in her profile. Feels surreal to have real engagement on posts and see real conversations.
Looking forward to catching up with old and new friends at #EMNLP2024! I’m on the academic job market so please reach out if you would like to chat 🙏 And come talk to me, @rnav_arora @_srishtiyadav and @IAugenstein on Thu (Nov 14) at poster session G from 2-3:30PM about LLM…
At #EMNLP2024 we will present our paper on LLM values and opinions! We introduce tropes: repeated and consistent phrases which LLMs generate to argue for political stances. Read the paper to learn more! arxiv.org/abs/2406.19238 Work done @CopeNLU & @AiCentreDK
Join the #NLProc party in the other place if you haven't yet! I've never seen a network to grow so fast, at least two hundred new people in the last couple of days. Maria's starter pack has also grown.
The only piece of good news this morning is that in the bluer place, Maria Antoniak made a starter pack of #NLProc people already there. It's pinned in her profile. Feels surreal to have real engagement on posts and see real conversations.
At #EMNLP2024 we will present our paper on LLM values and opinions! We introduce tropes: repeated and consistent phrases which LLMs generate to argue for political stances. Read the paper to learn more! arxiv.org/abs/2406.19238 Work done @CopeNLU & @AiCentreDK
Happening now @NeurIPSConf #NeurIPS2024 !!! Come to poster 4003 in East Hall to learn about Bayesian model reduction for structured pruning!
I’m at #NeurIPS2024! I’m also on the faculty job market! Come talk to me about neural network efficiency, reliable NLP, open positions, and come to my spotlight poster on Friday from 11a — 2p in East Exhibit Hall A — C, poster number 4003
Trying out the blu3 🦋place for now. You can find me there using my website as the handle [at]dustinbwright[dot]com
CopeNLU @ #EMNLP2024 — hope you all enjoyed the conference as much as we did 😊🌴 See you again at #ACL2025NLP and #EMNLP2025! #NLProc
Presenting this today at 2pm in the Jasmine hall. #emnlp2024
I’ll be at #EMNLP2024 presenting work on investigating political biases in LLMs! Would love to chat with folks about analysis of models, LLM safety, Computational Social Science x NLP, embedding Culture in models, PhD life and more. I’m on the lookout for internship positions!
Podcasts are a popular medium, but data for computational research is limited! We introduce the Structured Podcast Research Corpus (SPoRC - huggingface.co/datasets/blitt…), a large, multimodal dataset of English podcasts 🧵 arxiv.org/abs/2411.07892
Happening now at #EMNLP2024 ! Come to poster 34 in Jasmine to talk to me, @rnav_arora and @_srishtiyadav about LLM political values!
🌴Good morning, #EMNLP2024! Want to learn more about our research? This is what we're presenting. 📜 Also, @IAugenstein is chairing the business meeting and has the honour of revealing the #EMNLP2025 location in the closing session. Don't miss it! 🤩 #NLProc @emnlpmeeting
I’ll be at #EMNLP2024 presenting work on investigating political biases in LLMs! Would love to chat with folks about analysis of models, LLM safety, Computational Social Science x NLP, embedding Culture in models, PhD life and more. I’m on the lookout for internship positions!
🚨 @IAugenstein and I are offering a fully funded PhD Fellowship in Interpretable NLP at @UCPH_Research (@DIKU_Institut) & @AiCentreDK! 📆 Application Deadline: Jan 15, 2025 Full call and application link: employment.ku.dk/phd/?show=1628… Feel free to reach out! 😊 #XAI #NLProc
📜Excited to share our comprehensive survey on cultural awareness in #LLMs! 🗺️ We reviewed 300+ papers across diverse modalities (language, vision-language, etc.) @whoSiddheshp @jjjunyeong @jin__jiho @rnav_arora @JunhoMyung_ @_inhwa_song @aliceoh #NLProc openreview.net/forum?id=3gg6G…
[1/12] Optimizing prompts for specific tasks has been key to improving LLM performance, but what if we optimize prompts on system level to work well on *all* tasks? Check out 🌱SPRIG, a genetic system prompt optimizer that help unlock LLMs' full potential: arxiv.org/abs/2410.14826
🌿I am on the faculty job market this year!🌿 I work on reliable natural language processing, including: ✅ Factuality 💪 Robustness 🌿 Sustainability Feel free to reach out and DM! I will also be at #EMNLP2024 and #NeurIPS2024 and would love to chat in person!