Domain-specific information retrieval
arXiv:2611.08228 · doi:10.1108/FTINR-09-2025-0088
Abstract
Information Retrieval (IR) is much more than ad hoc web search: a large portion of the information seeking activities takes place in specific domains, often addressing work-related tasks. Examples are lawyers finding relevant prior cases for a legal case and academic researchers studying the background material for a paper. In Chapter 2 we outline the most common domain-specific tasks, datasets and applications. Domain-specific IR has a number of challenges that make set it apart from simple web search tasks: they often deal with long documents, long queries and long sessions with specific user needs. We discuss these in Chapter 3. We also address issues related to bias and fairness of models. In Chapter 4, we describe the models and methods developed for domain-specific tasks and data, addressing the specific challenges, including user aspects related to domain-specific IR tasks, dealing with queries, user models, and user interactions. We show that many of the methodological advances in domain-specific IR are transferable to other domains and even to open-domain web search. We conclude with the main takeaways and propose research directions for the near future.
arXiv commentPublished in Foundations and Trends in Information Retrieval
References in corpus (39)
- Survey of Hallucination in Natural Language Generation
- Longformer: The Long-Document Transformer
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
- Google Scholar, Microsoft Academic, Scopus, Dimensions, Web of Science, and OpenCitations' COCI: a multidisciplinary comparison of coverage via citations
- Passage Re-ranking with BERT
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Simple Applications of BERT for Ad Hoc Document Retrieval
- Better by you, better than me, chatgpt3 as writing assistance in students essays
- Is ChatGPT the Ultimate Programming Assistant -- How far is it?
- Patent Retrieval: A Literature Review
- PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model
- Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
- In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT
- TripClick: The Log Files of a Large Health Web Search Engine
- CAIL2019-SCM: A Dataset of Similar Case Matching in Legal Domain
- Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery
- Localising In-Domain Adaptation of Transformer-Based Biomedical Language Models
- InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval
- BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
- Zero-Shot Listwise Document Reranking with a Large Language Model
- Information search in a professional context - exploring a collection of professional search tasks
- Usability Evaluation for Online Professional Search in the Dutch Archaeology Domain
- Summarization, Simplification, and Generation: The Case of Patents
- Biomedical and Clinical Language Models for Spanish: On the Benefits of Domain-Specific Pretraining in a Mid-Resource Scenario
- Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search
- Can ChatGPT-like Generative Models Guarantee Factual Accuracy? On the Mistakes of New Generation Search Engines
- FAIR: Fairness-Aware Information Retrieval Evaluation
- Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature
- Case law retrieval: problems, methods, challenges and evaluations in the last 20 years
- LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain
- THUIR@COLIEE 2023: Incorporating Structural Knowledge into Pre-trained Language Models for Legal Case Retrieval
- Outcome-based Evaluation of Systematic Review Automation
- Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
- Reproducible Hybrid Time-Travel Retrieval in Evolving Corpora
- A Retrieval-Augmented Generation Framework for Academic Literature Navigation in Data Science
- From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants
- High Recall, Small Data: The Challenges of Within-System Evaluation in a Live Legal Search System
- Efficient course recommendations with T5-based ranking and summarization
- EnronQA: Towards Personalized RAG over Private Documents