New monograph surveys domain-specific IR across legal, health, academic and patent search
_reachsumit · x · 2026-11-06
Suzan Verberne, Florina Piroi, and Allan Hanbury publish a monograph (arXiv:2611.08228, Foundations and Trends in IR) on domain-specific information retrieval covering legal, health/biomedical, academic, and patent search. It surveys tasks, datasets, and applications; the defining challenges of long documents, long queries, long sessions, and specific user needs; bias and fairness; and models and methods including query handling, user models, and interactions. It concludes that many domain-specific IR advances transfer to other domains and even open-domain web search, with takeaways and future research directions.
More from Research
- Only 16% of AI benchmarks measure organizational difficulties of real jobs — ben_burtenshaw · 2026-11-06
- Skillware framework claims 97.3% cost cut as 3B-8B local models beat frontier LLMs — RossPeili · 2026-11-06
- Measured: in-process BM25 memory costs ~4.6KB RAM per entry, linear growth — Neither-Witness-6010 · 2026-11-06
- Gradient descent explained at 3 levels: from blindfolded hill-walking to non-convex dynamics — cneuralnetwork · 2026-11-06
- LLM writes 4-digit multiplication in just 355 weights, 40,000x fewer than SOTA, no training — willdepue · 2026-11-06
- Burkov proposes pretraining transformers on LLM weight files so they learn to edit model weights — burkov · 2026-11-06