←
Suzan Verberne 🤹‍♀️17,370 posts
Suzan Verberne 🤹‍♀️ avatar

Suzan Verberne 🤹‍♀️

@suzan

1980 | Full Professor of Natural Language Processing (@TMLeiden), @LIACS @UniLeiden | Lives in #Nijmegen | Mother of 2 | 👩🏻‍💻👩🏻‍🏫🤹‍♀️🌱 🎼

◷ Joined March 2007▧ 1,840 Photos and videos
Sumit avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
Sumit@_reachsumit·Nov 6

Domain-specific Information Retrieval @suzan et al. present a monograph on search in the legal, health and biomedical, academic, and patent domains, covering tasks, datasets, long-document challenges, retrieval methods, and the role of LLMs. 📝 arxiv.org/abs/2611.08228

James Zou avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
James Zou@james_y_zou·Nov 2

How long does a finding about LLMs stay true? We re-tested 50 widely cited findings about LLM behavior (various biases, hallucination, etc). Within 15 months, most no longer held or had substantially reduced effects. LLM findings has short shelf life zou-group.github.io/llm-clai… Great job by @oq_35!

Post attachment

1/n Within 15 months of publication, most of the LLM claims we tested either no longer held or showed substantially diminished effects. How long does our knowledge of AI hold up? In our new study, we revisit 50 findings to see what fades, what persists, and what gets stronger. 🧵

Post attachment
ACL Anthology avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
ACL Anthology@aclanthology·Aug 25

In the first step of a roadmap to bring Anthology search in-house, we have implemented an author index, accessible both from the main page navigation bar and from the people page: aclanthology.org/people/.

Post attachment
Alex Cui avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
Alex Cui@alexcdot·Jan 21

Okay so, we just found that over 50 papers published at @Neurips 2025 have AI hallucinations I don't think people realize how bad the slop is right now It's not just that researchers from @GoogleDeepMind, @Meta, @MIT, @Cambridge_Uni are using AI - they allowed LLMs to generate hallucinations in their papers and didn't notice at all. It's insane that these made it through peer review👇

Post attachment
Toon Beemsterboer avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
Toon Beemsterboer@beemsterbuma·26 Jul 2025

Ik wilde weten waarom Elon Musks chatbot Grok onlangs compleet ontspoorde, allerhande antisemitische stereotypen begon uit te braken, en zichzelf MechaHitler begon te noemen. Wat blijkt: het rabiate buitenbeentje onder de chatbots is gewoon zo getraind. nrc.nl/nieuws/2025/07/25/het…

Omar Khattab avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
Omar Khattab@lateinteraction·15 Jul 2025

The #SIGIR2025 Best Paper just awarded to the WARP engine for fast late interaction! Congrats to Luca Scheerer🎉 WARP was his @ETH_en MS thesis, completed while visiting us at @StanfordNLP. Incidentally, it's the fifth Paper Award for a ColBERT paper since 2020!* Luca did an incredible job leading and executing this. See the thread below for some relevant links. *Though it's notable that this is actually the first among these awards with ColBERT(v1/v2) authors😅😅

Post attachment

📢 If you’re at #SIGIR2025 this week, make sure to be at Luca Scheerer’s paper talk: “WARP: An Efficient Engine for Multi-Vector Retrieval” (Wednesday 11am) WARP makes PLAID, the famous ludicrously fast ColBERT engine, another 3x faster on CPUs. With the usual ColBERT quality!

Post attachment
Peter Brusilovsky avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
Peter Brusilovsky@peterpaws·14 Jul 2025

A good thought-provoking panel at the start of @SIGIRConf 2025 #SIGIR2025 "Is Search Dead? The Rise or Demise of Search in the Era of LLMs". Many valuable points on the topic from an excellent team of panelists.

Post attachment
Iadh Ounis avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
Iadh Ounis@iadh·14 Jul 2025

At the opening of #sigir2025; @frrncl opened the conference with also an address from ACM President Yannis Ioannidis.

Post attachmentPost attachmentPost attachmentPost attachment
Dawn Anderson avatar
⟳ Suzan Verberne 🤹‍♀️ retweeted
Dawn Anderson@dawnieando·1 Jul 2025

Suspect some of this has now been implemented with AI Overviews. Looking forward to more thoughts from IR professors at this year's European Summer School for Information Retrieval next week.

LLMs for IR lecture delivered by @suzan at ESSIR 2024. Highlights the recent AI Overviews debacle. Suggests search engines need to pre-qualify the documents which are returned for reliability / credibility for AI Overviews

Post attachment