Projects
Publications (33)
2026
7 publications- Starbucks: Improved Training for 2D Matryoshka Embeddings
European Conference on Information Retrieval, 67-82 · 2026
- AutoBool: Reinforcement-Learned LLM for Effective Automatic Systematic Reviews Boolean Query Generation
Proceedings of the 19th Conference of the European Chapter of the · 2026
- Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval
arXiv preprint arXiv:2602.16974 · 2026
- The Vulnerability of LLM Rankers to Prompt Injection Attacks
arXiv preprint arXiv:2602.16752 · 2026
- Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
arXiv preprint arXiv:2605.28017 · 2026
- DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
arXiv preprint arXiv:2605.07210 · 2026
- Evalugator —Rapid, Agile Development and Evaluation of Retrieval Augmented Generation Systems Without Labels
European Conference on Information Retrieval, 63-67 · 2026
2025
8 publications- An Investigation of Prompt Variations for Zero-Shot LLM-Based Rankers
Lecture notes in computer science · 2025
- Context Embeddings for Efficient Answer Generation in Retrieval-Augmented Generation
2025
- Corpus Subsampling: Estimating the Effectiveness of Neural Retrieval Models on Large Corpora
Lecture notes in computer science · 2025
- ReSLLM: Large Language Models are Strong Resource Selectors for Federated Search
2025
- Reassessing Large Language Model Boolean Query Generation for Systematic Reviews
2025
- 2D Matryoshka Training for Information Retrieval
2025
- AI-driven automated systematic reviews
2025
- Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition
2025
2024
6 publications- Evaluating Generative Ad Hoc Information Retrieval
2024
- FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation
2024
- Zero-Shot Generative Large Language Models for Systematic Review Screening Automation
Lecture notes in computer science · 2024
- BERGEN: A Benchmarking Library for Retrieval-Augmented Generation
2024
- Large Language Models Based Stemming for Information Retrieval: Promises, Pitfalls and Failures
2024
- Report on the Collab-a-Thon at ECIR 2024
ACM SIGIR Forum 58 (1), 1-11 · 2024
2023
4 publications- Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?
2023
- Generating Natural Language Queries for More Effective Systematic Review Screening Prioritisation
2023
- Balanced Topic Aware Sampling for Effective Dense Retriever: A Reproducibility Study
2023
- MeSH Suggester: A Library and System for MeSH Term Suggestion for Systematic Review Boolean Query Construction
2023
2022
5 publications- To interpolate or not to interpolate: Prf, dense and sparse retrievers
Proceedings of the 45th International ACM SIGIR Conference on Research and · 2022
- From little things big things grow: A collection with seed studies for medical systematic review literature search
Proceedings of the 45th International ACM SIGIR Conference on Research and · 2022
- Automated MeSH term suggestion for effective query formulation in systematic reviews literature search
Intelligent Systems with Applications · 2022
- Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search
2022
- Seed-Driven Document Ranking for Systematic Reviews: A Reproducibility Study
Lecture notes in computer science · 2022
2021
3 publications- BERT-based Dense Retrievers Require Interpolation with BM25 for Effective Passage Retrieval
2021
- MeSH Term Suggestion for Systematic Review Literature Search
ADCS '21: Proceedings of the 25th Australasian Document Computing Symposium · 2021
- IELAB at TREC Deep Learning Track 2021
2021