Abhilasha Ravichander

The project that started my whitespace obsession... #EMNLP2025

While we've all been worrying about tokenizers, lurking in the background has been the preprocessing *before* tokenization. Poems break standard HTML-to-text linearization systems, and we find that multimodal models aren't a solution.

𝙒𝙚'𝙧𝙚 𝙝𝙞𝙧𝙞𝙣𝙜 𝙣𝙚𝙬 𝙛𝙖𝙘𝙪𝙡𝙩𝙮 𝙢𝙚𝙢𝙗𝙚𝙧𝙨!

KSoC: utah.peopleadmin.com/postings/190... (AI broadly)

Education + AI:
- utah.peopleadmin.com/postings/189...
- utah.peopleadmin.com/postings/190...

Computer Vision:
- utah.peopleadmin.com/postings/183...

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

Go check Alex's poster today (Wed) in Suzhou! #EMNLP2025

I'm still so proud of our work (led by @lasha.bsky.social) on CondaQA, so we had to ask what would happen if we tried to create high-quality reasoning-over-text benchmarks now that LLMs are available. Turns out, we'd make an easier benchmark!

I'll be in Suzhou 🇨🇳 at #EMNLP this week presenting "What has been Lost with Synthetic Evaluation?" done with @anamarasovic.bsky.social & @lasha.bsky.social! 🎉

📍Findings Session 1 - Hall C
📅 Wed, November 5, 13:00 - 14:00

arxiv.org/abs/2505.22830

Screenshot of paper title: Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence

AI always calling your ideas “fantastic” can feel inauthentic, but what are sycophancy’s deeper harms? We find that in the common use case of seeking AI advice on interpersonal situations—specifically conflicts—sycophancy makes people feel more right & less willing to apologize.

Paper title: Language models align with brain regions that represent concepts across modalities. Authors: Maria Ryskina, Greta Tuckute, Alexander Fung, Ashley Malkin, Evelina Fedorenko. Affiliations: Maria is affiliated with the Vector Institute for AI, but the work was done at MIT. All other authors are affiliated with MIT. Email address: maria.ryskina@vectorinstitute.ai.

Interested in language models, brains, and concepts? Check out our COLM 2025 🔦 Spotlight paper!

(And if you’re at COLM, come hear about it on Tuesday – sessions Spotlight 2 & Poster 2)!

Figure showing the four phases of convergence in LM training

LLMs are trained to mimic a “true” distribution—their reducing cross-entropy then confirms they get closer to this target while training. Do similar models approach this target distribution in similar ways, though? 🤔 Not really! Our new paper studies this, finding 4-convergence phases in training 🧵

My group at the Max Planck Institute for Software Systems will be recruiting PhD students. The application deadline is December 31, 2025 (see lasharavichander.github.io/contact.html).

Please feel free to advertise other opportunities or add resources in this thread!

4. Some universities run graduate application support programs.

UW: cs.washington.edu/academics/gr...
CMU: cs.cmu.edu/academics/ph... [4/4]

GitHub - KaiserWhoLearns/CS-PhD-Application-fee-waivers: Collections of CS PhD Application Fee Waivers of schools in North America Collections of CS PhD Application Fee Waivers of schools in North America - GitHub - KaiserWhoLearns/CS-PhD-Application-fee-waivers: Collections of CS PhD Application Fee Waivers of schools in Nor...

3. Some US universities may waive your application fees. You can find leads on these programs here (from 2023, compiled by @kaiserwholearns.bsky.social
): github.com/KaiserWhoLea...

Many European universities will not charge application fees at all. [3/4]

GitHub - shaily99/advice: A repository of links with advice related to grad school applications, research, phd etc A repository of links with advice related to grad school applications, research, phd etc - shaily99/advice

2. A fairly comprehensive compilation of advice by
@shaily99.bsky.social , about graduate school: github.com/shaily99/adv... [2/4]

CS PhD Statements of Purpose cs-sop.org is a platform intended to help CS PhD applicants. It hosts a database of example statements of purpose (SoP) shared by previous applicants to Computer Science PhD programs.

It is PhD application season again 🍂 For those looking to do a PhD in AI, these are some useful resources 🤖:

1. Examples of statements of purpose (SOPs) for computer science PhD programs: cs-sop.org [1/4]

Happy to see this work accepted to #EMNLP2025! 🎉🎉🎉

I am recruiting emergency reviewers for *SEM 2025 (The 14th Joint Conference on Lexical and Computational Semantics). Please DM me if you might be able to contribute a review within the next few days 🙏

We’re thrilled to congratulate Dr. Abhilasha Ravichander (@lasha.bsky.social) and her team for receiving the Outstanding Paper Award at #acl2025 for their work titled "HALoGEN: Fantastic LLM Hallucinations and Where to Find Them"! 🏆✨

#ACL #LLMs #Hallucination #WiAIR #WomenInAI

See you soon on the other side!! Best of luck with wrapping up

Status Update: I'm in the middle of my move from Denmark to Colorado! If I seem to be missing for the 1-2 weeks, that is the main reason. Picture me lost amidst suitcases, boxes, moving pods, and far too many books.

Copenhagen friends, I'm here for a couple more days! Please stop by P1 to say bye 🥺

Speaker announcement: the new episode of the Women in AI Research WiAIR podcast is out on August 6th. Our guest is Dr. Abhilasha Ravichander, a postdoc at University of Washington and Assistant Professor at Max Planck Institute for Software Systems.

🎙️ New Women in AI Research #WiAIR episode coming Aug 6!

We talk to @lasha.bsky.social about LLM Hallucination, her award-winning HALoGEN benchmark, and how we can better evaluate hallucinations in language models.
👇 What’s inside:
1/

Open Call for Expressions of Interest in Max Planck Directorships: Expressions of interest can be submitted until 31 October 2025.

Director at Max Planck - a unique position! The Open Call for Expressions of Interest in Max Planck Directorships is open now and can be submitted by the 31st of October 2025. ➡️ mpg.de/directors - Please share the Open Call among potential candidates.

Thank you so much, excited to move to Germany! I will be based in Kaiserslautern.

Super super thrilled that HALoGEN, our study of LLM hallucinations and their potential origins in training data, received an ✨Outstanding Paper Award✨ at ACL!

Joint work w/i Shrusti Ghela*, David Wadden, and Yejin Choi

bsky.app/profile/lash...

Thank you Asia, super looking forward to collaborating!!

Thank you Lucy!!

Thank you Ana, and thank you again for your generous and thoughtful mentorship!🫶

Join Abhilasha's lab, she is an awesome researcher and mentor! I can attest, being her collaborator was great fun 🤩

People applying for NLP PhDs, work with Abhilasha -- she is awesome!!

Thank you so much Chenhao!!

Thank you so much, Leonie!! Excited for life in Germany (and thanks also for being a duolingo buddy for my German 🤣)

Thank you so much Marzena!!