🧵 4/4 The shared task continues the research on LLM-based advertising. Participants can submit systems for two sub-tasks: First, generate responses with and without ads. Second, classify whether a response contains an ad. Submissions are open until May 10th and we look forward to your contributions.

🧵 3/4 In a lot of cases, survey participants did not notice brand or product placements in the responses. As a first step towards ad-blockers for LLMs, we created a dataset of responses with and without ads and trained classifiers on the task of identifying the ads. dl.acm.org/doi/10.1145/...

🧵 2/4 Given the high operating costs of LLMs, they require a business model to sustain them and advertising is a natural candidate. Hence, we have analyzed how well LLMs can blend product placements with "organic" responses and whether users are able to identify the ads. dl.acm.org/doi/10.1145/...

Can LLM-generated ads be blocked? With OpenAI adding shopping options to ChatGPT, this question gains further importance. If you are interested in contributing to the research on LLM-based advertising, please check out our shared task: touche.webis.de/clef25/touch... More details below.

The Workshop on Open Web Search just finished #WOWS2025 #ECIR2025. It was a very cool experience with many interesting talks. Lets hope we can do it again next year at #ECIR2026 in Delft :)

Today I had the pleasure to talk about child-safe search at #ECIR2025. We created an cranfield-style evaluation dataset to contrast relevance with harm in web search scenarios.

Details: https://webis.de/publications.html#froebe_2025d

The Workshop on Open Web Search just finished #WOWS2025 #ECIR2025.

It was a very cool experience with many interesting talks. Lets hope we can do it again next year at #ECIR2026 in Delft :)

The Workshop on Open Web Search at #ECIR2025 just starts with a keynote by Charlie Clarke on Annotative Indexing. #WOWS25 #WOWS2025 #ECIR25

Now we have Ferdinand Schlatt on the #ECIR2025 stage predenting the research on the Set-Encoder.

The paper is online at: https://webis.de/publications.html#schlatt_2025b

I was very happy to talk about corpus subsampling at #ECIR2025 today.

Please find the paper at https://webis.de/publications.html#froebe_2025c

And lat bur not least, here are some of my favorite impressions of the first day of ECIR :)

Current status:

#IRRJ followers on #bluesky: 37 🦋
#IRRJ followers on #fediverse: 91 🐘

We need people on #BlueSky that advertise us. Who can help?
Reposts welcome to reach those people

Now its time for me to leave Washington. I had a super cool week at #SIGIR2024! I look already forward to next year in Italy 🍕

🙌 Wow! The #wows24 proceedings showcase 8 relevant research papers + one Keynote topic on #OpenWebSearch

The information + retrieval & OpenWebSearch community met in Glasgow in March at the first International Workshop on Open Web Search #wows2024, co-located with #ecir2024

The proceedings are now available to the public:
https://ceur-ws.org/Vol-3689/

Thank you to the editors:
Sheikh Mastura Farzana
@maik_froebe Fröbe
@gijs Hendriksen
@grani Granitzer
@djoerd
@potthast Potthast
Saber Zerhoudi

Matti Wiegman discusses Mastodon at #WOWS2024!

🔥 Happening today in Glasgow: #wows2024
The 1st “International Workshop on Open Web Search“ takes place as a side event of #ECIR24.
Organized by a team of researchers of the OWS.EU consortium, the hybrid workshop welcomes over 30 participants to discuss & workshop ideas for the future of #OpenWebSearch. A Keynote by Negar Arabzadeh from the University of Waterloo on “Evaluation of Information Access Systems in the Generative Era“ kicked off this day full of discussions.
Happy workshopping!

If you're in Glasgow at #ECIR2024, come join us at the first IR4Good session, where we'll be talking about @openwebsearcheu! Alternatively, come talk with us at the 1st International Workshop on Open Web Search #WOWS2024!

We will mostly discuss new ways to evaluate web search engines. There will be a keynote "Evaluation of Information Access Systems in the Generative Era" by Negar Arabzadeh (hear about the stuff that Charlie Clarke could not talks about!) and @maik_froebe will discuss how we used TIREx to evaluate web search components developed by other #WOWS2024 speakers and participants. (and we may have goodies)

The draft #WOWS2024 proceedings are now online at: https://www.cs.ru.nl/~hiemstra/wows2024/

If you are at #ECIR2024, please come to the 1st International Workshop on Open Web Search #WOWS2024 on Thursday. We may have goodies.

https://opensearchfoundation.org/wows2024/

We just finished an #OWSome hackathon at the TU Dresden to prepare the Workshop on Open Web Search #WOWS at #ECIR2024 in Glasgow. In the last week, we brainstormed, implemented, and evaluated a diverse set of retrieval components. This was so much fun! https://opensearchfoundation.org/wows2024