Advertisement · 728 × 90
#
Hashtag
#sigir2025
Advertisement · 728 × 90
Evaluating Personalized AI Agents for Adaptive Search

Evaluating Personalized AI Agents for Adaptive Search

A SIGIR 2025 paper proposes a three‑part framework to evaluate personalized AI agents with evolving personas, showing agents improve relevance over time on the PersonalWAB e‑commerce dataset. Read more: getnews.me/evaluating-personalized-... #sigir2025 #personalwab

0 0 0 0

#SIGIR2025 had 1071 full submissions across all tracks. Considering that a large number of those are on search and IR, this track may very well be the largest outlet for #recsys research. (although, given recent numbers at @neuripsconf.bsky.social and @aaai.org, this may be very well be contested).

0 0 0 0
Learnable Fully‑Interacted Two‑Tower Model Boosts Pre‑Ranking Efficiency

Learnable Fully‑Interacted Two‑Tower Model Boosts Pre‑Ranking Efficiency

FIT adds a Meta Query Module and a Lightweight Similarity Scorer, improving pre‑ranking recall and precision; it was presented at SIGIR 2025, according to the authors. Read more: getnews.me/learnable-fully-interact... #recsys #sigir2025

0 0 0 0

This year's TREC Tip of the Tongue (ToT) track will be amazing! Based on our rigorous experiments on synthetic ToT query generation presented at #SIGIR2025, we extended the track to open domain ToT queries.
We provide codes for baseline systems, and submissions are due by August 27th!

1 1 0 0
Preview
Two contributions to the international reference forum reinforce CiTIUS' leadership in information search and verification systems The prestigious ACM SIGIR 2025 conference, considered the world's leading forum in information retrieval and recommendation systems, selects and hosts the presentation of two works from the center.

📚 Two new contributions focused on #LLMs for health-related search and #FakeNews detection presented at #SIGIR2025, the CORE A* top forum on search systems, reinforce the centre's leadership in AI-powered information retrieval and verification

📰 s.citius.gal/sigir2025

#RedeCiGUS #FondosEuropeos

0 0 0 0
Post image

From July 14-18 @scadsai.bsky.social researchers presented several papers at #SIGIR2025 and #ICTIR2025 in Padua. 
👏 Congratulations for receiving two Best Paper Honourable Mention Awards at these conferences.
Find more info here:
👉 scads.ai/scads-ai-dresden-leipzig...

0 0 0 0
Post image Post image Post image Post image

Back from 2 1/2 weeks of intense travels to Wolverhampton (OMINO workshop and ELLIS ESSIR summer school) and then to Padua for SIGIR/ICTIR.

One of the main SIGIR/ICTIR takeaways – users of search engines will be more and more non-human. We need to consider this!

#sigir2025

0 0 0 0
Post image Post image Post image Post image

Back from 2 1/2 weeks of intense travels to Wolverhampton (OMINO workshop and ELLIS ESSIR summer school) and then to Padua for SIGIR/ICTIR.

One of the main SIGIR/ICTIR takeaways – users of search engines will be more and more non-human. We need to consider this!

#sigir2025

0 0 0 0

Congratulations on receiving the Best Paper Honourable Mention at #SIGIR2025 👏

4 0 0 0
Post image Post image Post image Post image

Here are some impressions from our ReNeuIR workshop on "Reaching Efficiency in Neural IR" that we had yesterday at #SIGIR2025.

8 1 1 0
On the Neural Hype and Improving Efficiency of Sparse Retrieval “The Neural Hype, Justified!” exclaimed Jimmy Lin in an opinion paper in the SIGIR Forum of December 2019. But is it really? Effectiveness-wise, maybe not: I will share some recent examples that show that neural rankers on new data do not even significantly improve a weak sparse baseline. If they do improve on old data, some neural rankers have been pre-trained on the test data – the ultimate sin of the machine learning professional – convincingly shown for the MovieLens data in the SIGIR 2025 poster of Dario Di Palma and colleagues: “Do LLMs Memorize Recommendation Datasets?” Efficiency-wise, neural rankers are no match to sparse rankers. The standard BERT (re-)ranker hailed by Lin’s SIGIR Forum paper may be as much as 10 million times as inefficient as a sparse ranker (Yes, you read that right). I will show some recent innovations for improving the efficiency of sparse rankers: The score-fitted index and the constant-length index (a SIGIR 2025 poster too!) which are implemented in Zoekeend, a new experimental search engine based on the relational database engine DuckDB and available from: https://gitlab.science.ru.nl/informagus/zoekeend/ _Presented at the SIGIR Workshop on Reaching Efficiency in Neural Information Retrieval (ReNeuIR 2025)_ [download slides]

My slides for the #ReNeuIR workshop at #SIGIR2025 are now at: djoerdhiemstra.com/2025/on-the-neural-hype-...

4 0 0 0
Post image

Heading back from #SIGIR2025!

It was a pleasure to spend this week in the beautiful Padova meeting and discussing with the community, alongside my PhD students Riccardo Pellini and Michael Benigni

5 0 0 0
Slide with last nice logo

Slide with last nice logo

And now: The #SIGIR2025 workshop on Reaching Efficiency in Neural Information Retrieval

4 0 0 0
Post image

Happy to share that our paper "The Viability of Crowdsourcing for RAG Evaluation" received the Best Paper Honourable Mention at #SIGIR2025! Very grateful to the community for recognizing our work on improving RAG evaluation.

 📄 webis.de/publications...

27 10 2 1
Sole Pera presents work with Theo Huibers, Emiliana Murgia, and Monica Landoni

Sole Pera presents work with Theo Huibers, Emiliana Murgia, and Monica Landoni

The Fab Four of Information Retrieval for Children! #SIGIR2025

4 1 0 0
Post image Post image

Now @fschlatt.bsky.social presents "TITE: Token-Independent Text Encoder for Information Retrieval" at #SIGIR2025

Paper: webis.de/publications...

8 3 0 0
Post image

Want to know how to make bi-encoders more than 3x faster with a new backbone encoder model? Check out our talk on the Token-Independent Text Encoder (TITE) #SIGIR2025 in the efficiency track. It pools vectors within the model to improve efficiency dl.acm.org/doi/10.1145/...

10 5 0 0
Iryna on stage

Iryna on stage

This is horrible: Iryna Gurevych discusses the role of "AI scientists" that execute the full scientific workflow. #SIGIR2025

12 4 3 1
Post image

I will present our paper “Breaking the lens of the Telescope: Online Relevance Estimation over Large Retrieval Sets” at #SIGIR2025
🕰️ 10:30 AM (16.07.2025)
📍Location: GIOTTO (Floor 0)
Full Paper: dl.acm.org/doi/10.1145/...
Slides: sigir2025.dei.unipd.it/detailed-pro...

2 0 0 0
Preview
Bridging the Gap: From Ad-hoc to Proactive Search in Conversations | Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval

I’ll present our full paper "Bridging the Gap: From Ad-hoc to Proactive Search in Conversations" tomorrow morning (16 July) at #SIGIR2025, in the Conversational IR and Intelligent Agents session, MANTEGNA Platea, Floor 1, 10:30–12:30.
Paper: dl.acm.org/doi/10.1145/...

2 0 1 0
Post image Post image Post image

To Eun Kim just presented the work on "Tip of the Tongue Query Elicitation for Simulated Evaluation" at #SIGIR2025. The approach will be used in the #TREC2025 Tip-of-the-Tongue track, and we had some sweets at the poster :)

The paper is available online: dl.acm.org/doi/10.1145/...

12 3 0 0
Yubao in front of screen QR code and conclusion with a kitten asking for questions

Yubao in front of screen QR code and conclusion with a kitten asking for questions

Yubao Tang from University of Amsterdam presenting MINT RAG; and is hiring! (with Maarten de Rijke) #SIGIR2025

2 0 0 0
Post image Post image

Lukas Gienapp presents "The Viability of Crowdsourcing for RAG Evaluation" at #SIGIR2025

The paper is available at: webis.de/publications...

10 6 0 0
Post image

Lucky to witness #IRRJ editor-in-chief @djoerd.idf.social.ap.brid.gy signing a copy of the first edition of @irrj.sigmoid.social.ap.brid.gy for Ian Soboroff, author of the paper “Don’t Use LLMs to Make Relevance Judgments” in the volume.

#SIGIR2025

irrj.org/article/view...

11 3 0 0
Post image Post image

Join us at the #SIGIR2025 poster session today and check out Jiaman He’s poster #10 on “Characterising Topic Familiarity and Query Specificity Using Eye-Tracking Data”

@rmitcomputing.bsky.social
@admscentre.org.au
@jtrippas.bsky.social
@danachatter.bsky.social
@gtresearchnews.bsky.social

5 1 0 0
Smiling guy with rainbow sun glasses vaguely pointing at a poster

Smiling guy with rainbow sun glasses vaguely pointing at a poster

Me, BEFORE giving my poster presentation. #SIGIR2025

4 0 0 0
Smiling guy with rainbow sun glasses vaguely pointing at a poster

Smiling guy with rainbow sun glasses vaguely pointing at a poster

Me, BEFORE giving my poster presentation. #SIGIR2025

1 0 0 0
Linda on stage

Linda on stage

Linda Zeng presents at #SIGIR2025 while still a high school student(!), supervised by Yi Zhang: for the paper: Knowing You Don’t Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing

https://github.com/ucscirkm/SIM-RAG

2 0 0 0
Post image

A good, thought-provoking panel at the start of
#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.

3 0 0 0
Post image Post image Post image Post image

Here are some of the statistics that I found very interesting from the #SIGIR2025 opening session. (Over 1000 attendees!)

5 1 1 0