Xi Wang
University of Sheffield · NLP Group · xi.wang@sheffield.ac.uk
COM135 Regent Court
School of Computer Science
University of Sheffield, S1 4DT
I am a Lecturer (≈ Assistant Professor) in Natural Language Processing at the University of Sheffield, affiliated with the NLP Group. My research sits at the intersection of Conversational AI, Information Retrieval, Personalisation, and AI for Mental Health.
Before joining Sheffield, I completed my PhD at the University of Glasgow under the supervision of Prof. Iadh Ounis and Prof. Craig Macdonald, where I developed review-based recommender systems. I then joined University College London (UCL) as a Postdoctoral Research Associate in the Web Intelligence Group, working with Prof. Emine Yilmaz on task-oriented dialogue systems — work supported by a Google Research Workshop Grant.
My work has appeared at top-tier venues including ACL, EMNLP, NAACL, AAAI, SIGIR, CIKM, WWW, and ECIR. For a full list of publications, see my Google Scholar profile.
Research Areas
Task-oriented dialogue, proactive information seeking, clarification questions, user simulation
Retrieval-augmented generation (RAG), neural IR, evaluation & simulation frameworks
Review-based & multimodal recommendation, conversational recommendation, cold-start
LLM-based depression screening, early risk prediction (eRisk), clinically-grounded agents
PhD Opportunities
I am actively looking for PhD students (2026 entry) to work on topics related to:
- Proactive conversational information seeking
- Deep Research & Retrieval Augmented Generation
- User simulation for IR and dialogue
- Automatic Conversational Support for Mental Health
If you are interested, please email xi.wang@sheffield.ac.uk with the subject line starting with [PhD 26/27].
news
- Apr 14, 2026 — Two paper accepted to ACL 2026!
- Apr 2, 2026 — Three papers accepted to SIGIR 2026!
- Dec 20, 2025 — Received funding from the Going Global Partnerships UK-Spain Springboard Programme to support collaboration with the information retrieval lab at University of A Coruña.
- Nov 1, 2025 — Papers “Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation” and “eRisk 2026” accepted to ECIR 2026.
- Jul 1, 2025 — Two papers accepted to CIKM 2025: “TalkDep: Clinically Grounded LLM Personas for Depression Screening”, and “+VeriRel: Verification Feedback to Enhance Document Retrieval”. We are also organising the workshop “ProActLLM: Proactive Conversational Information Seeking”
- Jan 25, 2025 — Paper “SynDL: A Large-Scale Synthetic Test Collection for Passage Retrieval” accepted to The Web Conference (WWW) 2025.
- Jan 20, 2025 — Paper “Adaptive Retrieval-Augmented Generation for Conversational Systems” accepted to NAACL 2025.
- Jan 20, 2024 — Paper “Clarifying the Path to User Satisfaction: An Investigation into Clarification Usefulness” accepted to EACL 2024 (Findings).
- Jan 15, 2024 — Paper “Simulated Task Oriented Dialogues for Developing Versatile Conversational Agents” accepted to ECIR 2024.
- Dec 1, 2023 — Paper “A Social-aware Gaussian Pre-trained Model for Effective Cold-start Recommendation” accepted to the journal of Information Processing & Management (IP&M).
- Oct 7, 2023 — Paper “Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation” accepted to EMNLP 2023 (Findings).
- Jan 7, 2023 — Co-first authored paper “A Survey on Asking Clarification Questions Datasets in Conversational Systems” accepted to ACL 2023 (main).
- Nov 1, 2022 — Received Google research workshop grant on Action, Task and User Journey ($20,000) as Co-recipient with Prof. Emine Yilmaz.
- Oct 1, 2022 — Co-first authored paper “Task2KB: A Public Task-Oriented Knowledge Base” accepted to AAAI 2023.