Svitlana Vakulenko

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

13.10.2025 11:25 — 👍 89    🔁 26    💬 2    📌 1

SIGIR 2026 - 49th International ACM SIGIR Conference on Research and Development in Information Retrieval Join SIGIR 2026 in Sydney for cutting-edge research in information retrieval. Discover keynotes, workshops, and networking with global IR experts.

Who's excited for #SIGIR2026? 😎
www.sigir2026.org

03.10.2025 14:41 — 👍 2    🔁 2    💬 0    📌 0

America’s top companies keep talking about AI — but can’t explain the upsides FT analysis of hundreds of filings suggests the S&P 500 businesses are clearer about the risks than benefits

“When it comes to AI adoption, many companies aren’t guided by strategy but by ‘Fomo’,” said Haritha Khandabattu, senior director analyst at consultancy Gartner.

www.ft.com/content/e93e...

24.09.2025 14:40 — 👍 112    🔁 31    💬 7    📌 5

Political neutrality, for an AI model, is simply “not a thing,” Chowdhury said. “It’s not real.” For example, she said, if you ask a chatbot for its views on gun control, it could equivocate by echoing both Republican and Democratic talking points, or it might try to find the middle ground between the two. But the average AI user in Texas might see that answer as exhibiting a liberal bias, while a New Yorker might find it overly conservative. And to a user in Malaysia or France, where strict gun control laws are taken for granted, the same answer would seem radical.

One problem with an EO requiring AI models to be politically neutral: There's no such thing, says @ruchowdh.bsky.social. www.washingtonpost.com/technology/2...

24.07.2025 16:59 — 👍 66    🔁 16    💬 2    📌 1

Our paper "OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs" has been accepted to #INLG2025 conference!

You can read the preprint here: arxiv.org/abs/2503.11858

23.08.2025 16:36 — 👍 4    🔁 2    💬 1    📌 0

SCAI 2025 Online Event on Search-Oriented Conversational AI.

Check out the slides from our SCAI'2025 #convsearch workshop collocated with @ijcai.org #IJCAI2025 on LLMs, retrieval & QA, recommendations, negotiations, evaluation and transparency

scai.info/scai-2025

@patuchen.bsky.social @maik-froebe.bsky.social @tuetschek.bsky.social @mila-quebec.bsky.social

09.09.2025 10:34 — 👍 8    🔁 3    💬 0    📌 0

an aerial view of tokyo at night with lots of lights ALT: an aerial view of tokyo at night with lots of lights

Some exciting news! 🤗 After 3 amazing years at TREC, the Tip-of-the-Tongue (ToT) shared task will be a core task at NTCIR-19 in 2026. The new track will focus on tip-of-the-tongue information needs in English and East Asian languages.

More details coming soon. See you all in Tokyo next year!

01.09.2025 16:12 — 👍 5    🔁 3    💬 0    📌 0

🌟Really excited to share the fourth Strategic Workshop on Information Retrieval (SWIRL) report published in SIGIR Forum!

Paper 👉🏻 www.johannetrippas.com/papers/tripp...

More info 👉🏻 sites.google.com/view/swirl20...

#SWIRL2025 #SIGIR2026 #IR #GenAI #Research #CHIIR2026

02.09.2025 12:38 — 👍 13    🔁 10    💬 0    📌 0