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
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!
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. 🧵
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/.
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👇
Happy to share that our paper "Generative Retrieval with Few-shot Indexing" has been accepted at #ECIR2026, with @arian_ask, @maliannejadi, @zhaochun_ren, Evangelos Kanoulas and @suzan.
A training-free generative retrieval method with strong performance and much faster indexing
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…
Huge congratulations to @macavaney on receiving the prestigious ACM SIGIR Early Career Researcher Award in the research category! This well-deserved recognition highlights the excellence & impact of his work in the IR community 👏🎉#sigir2025
Cc @GlasgowCS@UofGlasgow@ACMSIGIR
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😅😅
📢 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!
Wow, honored to be named an Excellent PC Member at @SIGIRConf!
Glad my obsessive... I mean detailed... reviewing style paid off. 🤓✨
Huge thanks to the chairs for the recognition and congrats to all the other reviewers!
#SIGIR#SIGIR2025#Award#BestReviewer
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.
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