Menu Close

Industry Day

ECIR 2025 Industry Day Schedule

9.00 – 9.15 | Opening remarks – 15 minutes

9.15 – 10.00 | Invited talk – Elizabeth Lingg, Contextual AI, The DNA of Enterprise AI: Architecting Systems for Agentic RAG through Specialization.

10:00 – 10:40 | Paper session

  • 10.00 Combining Knowledge Graphs and Retrieval Augmented Generation for Enterprise Resource Planning, Amar Viswanathan and Felix Sasaki, SAP
  • 10.20 RURAGE: Robust Universal RAG Evaluator for Fast and Affordable QA Performance Testing, Nikita Krayko, Ivan Sidorov, Fedor Laputin, Daria Galimzianova, Vasily Konovalov, MTS AI

10.40 – 11.00 | Coffee break

11.00 – 11.45| Invited talk – Mevan Babakar, Google, Can I Trust This? Tools to empower users to determine information trustworthiness in the age of AI

11.45 – 12.45 | Paper Session

  • 11.45 Contextualizing Spotify’s Audiobook List Recommendations with Descriptive Shelves, Gustavo Penha, Alice Wang, Martin Achenbach, Kristen Sheets, Sahitya Mantravadi, Remi Galvez, Nico Guetta-Jeanrenaud, Divya Narayanan, Ofeliya Kalaydzhyan, and Hugues Bouchard, Spotify
  • 12.05 Text2Playlist: Generating Personalized Playlists from Text on Deezer, Mathieu Delcluze, Antoine Khoury, Clemence Vast, Valerio Arnaudo, Léa Briand, Walid Bendada, and Thomas Bouabça, Deezer Research

12.25 – 14.00 | Lunch break

14.00 – 14.45 | Invited talk – Carlos Lassance, Cohere, Going from industry lab to a startup, the differences between applied research and deriving products from research

14.45 – 15.25 | Paper Session 

    • 14.45 Personalizing Enterprise Search with LLM Populated Attributes in Graph Models, Christopher Liu and Varsha Embar, Cisco Systems
    • 15.05 Jina Embeddings V3: Multilingual Text Encoder with Low-Rank Adaptations, Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael Günther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, and Han Xiao, Jina AI GmbH

15.25 – 15.45 | PlotEdit: Natural Language-Driven Accessible Chart Editing in PDFs via Multimodal LLM Agents, Kanika Goswami, Puneet Mathur, Ryan Rossi, and Franck Dernoncourt, Adobe Research

15.45 – 16.15 | Coffee break

16.15 – 17.00| Invited talk – Antonio Mallia & Cesare Campagnano, Pinecone, Neural Retrieval Meets Cascading Architectures

17.00 – 17.40 | Paper Session

  • 17.00 Leveraging LLMs for Energy Forecasting: The AcegasApsAmga Case Study, Kevin Roitero, Andrea Zancola,, Vincenzo Della Mea, and Stefano Mizzaro, AcegasApsAmga SpA, Hera Group
  • 17.20 Adapting LLMs for Domain-Specific Retrieval: A Case Study in Nuclear Safety, Federico Borazio, Danilo Croce, and Roberto Basili, University of Rome

17.40 – 17.50 | Closing remarks – 10 minutes

Invited Speakers

Elizabeth Lingg, Contextual AI

Elizabeth Lingg is the Director of Applied Research at Contextual.AI. She is passionate about AI, Machine Learning, Research, and Data Science as well as E2E development of innovative products using Software Engineering, Big Data, and Distributed Systems. She holds a B.S in Computer Science with a Minor in Mathematics from Carnegie Mellon, a B.S. in Policy and Management from Carnegie Mellon, and a M.S. in Computer Science with a Specialization in Artificial Intelligence from Stanford University where she studied under Andrew Ng, founder of DeepLearning.AI and Founding Lead of the Google brain, as her Research Advisor. Most recently, she was a Principal Software Engineering Manager at Microsoft working on Applied Research on the Copilot team where she led the Natural Language Understanding team, working on LM and NLP such as Intent Detection and Entity Extraction. Previously, she worked as a Software Engineer, Data Scientist, and Engineering Manager at large companies such as Apple and Oracle as well as startups. She holds a number of patents and publications in the fields of AI and Machine Learning.

Mevan Babakar, Google

Mevan Babakar works on information quality and integrity in Google Knowledge and Information. Before Google, Mevan was deputy CEO of Full Fact, the UK’s independent fact checking charity. She founded Full Fact’s automated fact checking team which built AI technologies to help scale the work of fact checkers. This work went on to win the Google AI Impact Challenge. The tools that were developed are now being used by fact checkers around the world. She serves as chair of the board for Democracy Club which empowers voters and everyday democracy in the UK, in 2024 it served 20m voters their polling station and candidate data. In 2023 she was selected by the Obama Foundation as an Obama Leader for Europe.

Carlos Lassance, Cohere

Carlos Lassance is a Member of Technical Staff at Cohere, who spends more time than he should thinking about neural retrievers, their training dynamics and how to actually make them useful. Prior to Cohere he was a research scientist at Naver Labs Europe where he mostly worked on improving the efficiency and effectiveness of neural sparse retrievers, most notably of SPLADE. Over the past 4 years he has published many papers and patents on IR, been a programme committee member at ECIR, SIGIR and IEEE, and participated in many TREC tasks.

Antonio Mallia, Pinecone

Antonio Mallia is a Senior Research Scientist at Pinecone, leading research on scalable retrieval systems and models. Previously, he was an Applied Scientist on Amazon’s Artificial General Intelligence (AGI) team, working on large-scale web search. He holds a Ph.D. in Computer Science from New York University, where he studied under Professor Torsten Suel, focusing on enhancing the effectiveness and efficiency of Information Retrieval systems. Antonio has published extensively in top-tier conferences, including SIGIR, ECIR, EMNLP, CIKM, and WSDM. He also serves as a program committee member and reviewer for major IR and NLP conferences.

Cesare Campagnano, Pinecone

Cesare Campagnano is a Senior Research Scientist at Pinecone. He earned his Ph.D. from Sapienza University of Rome, focusing on the intersection between Large Language Models and Information Retrieval, later continuing his research as a PostDoc. His contributions have been published in top-tier conferences such as SIGIR, ACL, AISTATS, COLING, and ECIR. Cesare interned at Amazon as an Applied Scientist II in the Community Shopping Science team before joining Pinecone, where he started as a research intern and later transitioned to a full-time role.