Call for Participation


Search and recommender systems should be supporting user tasks rather than individual queries or actions. To that end, the IR community has spent decades trying to understand user’s tasks and their contexts, and how to best support them. The recent advancements in generative AI have drastically shifted the landscape of task-focused IR. Users can now express not only their queries and questions, but actual information needs, tasks, and goals in natural language to an AI system and receive not just results, but also answers in natural language that are generated specifically for them. This new paradigm raises many interesting questions, opportunities, and challenges. We are looking to bring a group of highly motivated students and scholars in a two-day workshop on Microsoft campus in Redmond to discuss these, learn from each other, and envision a new future for task-focused IR.


Topics of interest include, but are not limited to, the following:
  • Task-focused search and recommendation
  • Generative AI
  • AI copilots and digital assistance
  • Model innovation
    • Task modeling (task representations, contexts, complexity, etc.)
    • Adaptation (model specialization, hybrid inference, etc.)
    • Alignment (application alignment, feedback loops)
    • Augmentation (retrieval augmented generation, skills/plugin retrieval/recommendation, etc.)
    • Grounding (Hallucinations, provenance, faithful reasoning, etc.)
    • Personalization (infinite memory, context compression, privacy, etc.)
  • Next-generation experiences:
    • Unified experiences (e.g., spanning search and dialog)
    • Human learning (search as learning, exploratory search, learning support, etc.)
    • Human control (control strategies, system involvement, human-AI teaming, etc.)
    • Completion (task automation, standing tasks, proactive experiences, etc.)
  • Measurement:
    • Understanding (mental models, model capabilities, user studies, etc.)
    • Evaluation (metrics, judgments, simulations, etc.)
  • Broader implications:
    • Responsibility (RAI, bias, FATE, etc.)
    • Economics (business models, advertising, content creation, cost-benefit tradeoffs, etc.)
    • Ubiquity (cross-application, cross-device, OS integrations, etc.)


  • Interest application for participation: September 6, 2023
  • Student applications for funding: September 6, 2023
  • Notifications: September 11, 2023
  • Registration: September 15, 2023
  • Final agenda: September 15, 2023
  • Workshop: September 28-29, 2023


Microsoft Research (Building 99)
14820 NE 36th St, Redmond, WA

Workshop Schedule (Tentative)

    Day 1: Thursday, September 28, 2023

    8:00 AMBreakfast
    9:00 AMOpening
    9:15 AMKeynote
    10:30 AMCoffee break
    11:00 AM 2-3 Invited talks
    12:00 PMLunch
    1:00 PMBreakout session-1     Topic: Leveraging GenAI for IR and Mitigating Risks
    2:30 PMCoffee break
    3:00 PMPanel
    4:00 PMStudent poster lightning talks
    4:30 PMPoster session
    5:30 PMAdjourn

    Day 2: Friday, September 29, 2023

    8:00 AMBreakfast
    9:00 AMBreakout session-2     Topic: GenAI and the Future of Information Access
    10:30 AMCoffee break
    11:00 AMFull group discussion to share and consolidate ideas
    12:00 PMLunch
    1:00 PMAdjourn


Registration is free and open to both students and non-students. But due to facility constraints, we can only admit a limited number of participants. Please follow the link below to express your interest in attending this workshop.

Important Registration Dates

Interest application opens: August 28, 2023
Interest application closes: September 6, 2023
Notifications: September 11, 2023

Apply to Attend the Workshop [CLOSED]

Workshop Travel Grants

Funding for the workshop is available!

We have limited funding for students to attend the workshop. Priority will be given to PhD students who are working in the relevant area or interested in pursuing their future research in one of the topics listed here *and* presenting a poster at the workshop.
Amount: Up to $1,000
Deadline: Applications will be accepted until September 6, 2023.
Eligibility: The applicant must be enrolled in a graduate program (masters or PhD) as a full-time student at a US institution of higher education. Please note that while we are not able to fund non-US students for travel due to NSF restrictions, we are looking into other ways to support them. Stay tuned for more details.

Apply to Attend the Workshop [CLOSED]


Keynote Speaker

Nick Craswell

Principal Applied Scientist

Home page

Bio: Nick Craswell is a Principal Applied Scientist at Microsoft in Redmond Washington, working on enhancing search, recommendation and other information access methods, for personal and enterprise data such as email, chat and shared files. This includes work on generative AI solutions to such problems, for example how to evaluate M365 Chat. He is a member of the SIGIR Academy. He has coauthored hundreds of papers and three books on information access and retrieval.

Title: Personalization and Conversation (and GPT-4)
Abstract: A fundamental capability in search is to retrieve the best candidates from millions or billions of candidates. That capability can be used in a simple query-driven search interface. On top of that we can add capabilities like personalization, conversational refinement and/or summarization via retrieval-augmented generation. This talk covers some work on the fundamentals (MS MARCO), personalization and conversation ("A theoretical model of conversational search" by Radlinski and Craswell). For each published work, I'll present some toy examples, to see what GPT-4 (dv3) can do. The toy examples help us speculate about the upcoming impact of LLMs on retrieval fundamentals, personalization and conversation.

Invited Talks

  • Luanne Sinnamon
    University of British Columbia
    Title: Past and Future Directions in the Design of Task-Based Information Environments

  • Grace Hui Yang
    Georgetown University
    Title: Re-classification of Information Seeking Tasks and Their Computational Solutions

  • Raman Chandrasekar
    Institute for Experiential AI, Northeastern University (Seattle Campus)
    Title: Question Answering on Irregular Tabular Data Using a Parallel Document Corpus


  • Moderator: Rob Capra
                          University of North Carolina at Chapel Hill

  • Panelists: Leif Azzopardi
                      University of Strathclyde

                      Jacek Gwizdka
                      University of Texas at Austin

                      Besmira Nushi
                      Microsoft Research


Presentation Recordings



Invited Talks

Speakers' Presentations



Workshop Venue

Microsoft Research (Building 99): 14820 NE 36th St, Redmond, WA

Note: Breakfast and lunch will be provided for both days of the workshop at no cost to attendees.


The workshop will be hosted at Microsoft Research (Building 99) in Redmond. It will be easier to commute if you find accommodation close to Building 99. There are several hotels close to the workshop venue, including the following:

There are other hotels nearby in downtown Redmond and downtown Bellevue. Also, nearby are many restaurants, coffee shops, and other spots to reconnect with colleagues and discover.

Arriving in Seattle

There are regular direct flights to Seattle-Tacoma International Airport (SEA) from other cities. SEA is located approximately 21 miles from the venue, the Microsoft Research (Building 99). You can find information about transportation options from the airport here:

RideShare Apps

You can use ride-hailing apps to move around Seattle and Redmond.

  • Lyft – You can use the Lyft app for ride-hailing.
  • Uber – Uber is available to commuters in Seattle and Redmond. You can choose from several options.
The estimated cost from SEA to the workshop venue is around $75.


If you are driving, you can park in the visitor parking spots in Building 99 Garage.

Sightseeing in Seattle


Workshop Organizers

Chirag Shah

University of Washington
Home page

Ryen W. White

General Manager and Deputy Lab Director, Microsoft Research
Home page