SIGIR ’25 contributions

I’m happy to share that I’ll be attending SIGIR ’25, which is shaping up to be a busy and exciting event.

Accepted papers:

  • “Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation” — perspectives paper with Don Metzler and Zhen Qin [PDF]
  • “GINGER: Grounded Information Nugget-Based Generation of Responses” — short paper with W. Łajewska [PDF]
  • “MultiConAD: A Unified Multilingual Conversational Dataset for Early Alzheimer’s Detection” — resource paper with Arezo Shakeri and Mina Farmanbar [PDF]

In addition to the papers, I’ll also be giving a tutorial, together with Nolwenn Bernard, Saber Zerhoudi, and ChengXiang Zhai, on “Theory and Toolkits for User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation” [website]. The tutorial covers key simulation methodologies, with a particular focus on recent advancements leveraging LLMs. Crucially, we will also provide practical guidance, highlighting relevant toolkits, libraries, and datasets available to researchers and practitioners.

Finally, I’m co-organizing the Second SIGIR Workshop on Simulations for Information Access (Sim4IA 2025) together with Philipp Schaer, Christin Katharina Kreutz, Timo Breuer, and Andreas Konstantin Kruff [website]. The workshop features a keynote, invited tech talks, a panel discussion, and (micro) shared tasks for simulating interactions with a traditional search engine or a conversational assistant.

If you’re attending the conference, please come say hello, drop into the tutorial or workshop, or reach out ahead of time—I’d love to connect.

PhD position in Large Language Models for Recommendation

I have a PhD position in Large Language Models for Recommendation, funded by the NorwAI research-based innovation center.

The proposed PhD project aims to advance the field of personalized recommender systems by harnessing the natural language reasoning capabilities of large language models (LLMs). The research will focus on three key areas:

  1. developing methods to construct natural language user interest profiles that enhance transparency and provide user control over recommendations; 
  2. designing conversational recommendation systems that utilize LLMs to effectively elicit user preferences and generate tailored responses, including both recommendations and explanations; and
  3. developing approaches to mitigate limitations of LLMs through retrieval-augmented generation (RAG) and tool use.

Overall, this project seeks to push the boundaries of how LLMs can be applied to create more intuitive, responsive, and user-centered recommendation systems.


See the details on jobbnorge. Application deadline is Oct 31.

User Simulation book published

I’m thrilled to announce that our book with ChengXiang Zhai “User Simulation for Evaluating Information Access Systems” has been published (a preprint is available on arXiv). This comprehensive monograph delves into the pivotal role of user simulation in assessing the effectiveness of information access systems, such as search engines, recommender systems, and conversational assistants. Addressing the intricate challenges of evaluating these systems, our book explores user simulation techniques that account for the diverse behaviours and preferences of users. It offers a detailed examination of general frameworks, models, and algorithms designed to simulate user interactions, and establishes connections with related fields, including machine learning, dialogue systems, user modeling, and economics. We also discuss future research directions that extend beyond the evaluation of information access systems and are expected to have broader impact on how to evaluate interactive intelligent systems in general.

Highlights from 2023

Another year has passed, and it’s now time for the usual annual highlights post. Here are some of the notable events and achievements from 2023:

Looking forward to what 2024 has in store!

User Simulation tutorial at AAAI’24 and WWW’24

Together with ChengXiang Zhai, we will be giving our user simulation tutorial at AAAI’24 and WWW’24, customized to the respective audiences. The AAAI’24 edition adopts a broader perspective of user simulation for evaluating an interactive AI system and focuses more on simulation algorithms and techniques that are well connected with various sub-fields of AI, such as machine learning and agent-based systems. In contrast, the WWW’24 edition emphasizes more on applications of user simulation for evaluating Web information access systems, including click modeling and the application of simulation techniques in e-commerce.