Science AI Journal
Computer Science · Research topic

Open research questions in Information Retrieval and Search Behavior

193 gap statements mined from Information Retrieval and Search Behavior papers in our 7.9M-paper local library, which holds 2,506 papers on the topic — drawn mostly from each paper's own stated research gap, future-work, challenge and limitation notes, and its abstract. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one.

Choosing where to publish on Information Retrieval and Search Behavior? See the ranked Computer Science journals.

What the literature leaves open

  • The out-of-vocabulary problem is not effectively addressed by existing text-to-video retrieval methods. Existing methods are not able to handle complex queries with logical and spatial constraints. There is a need for a more effective and scalable approach to text-to-video retrieval.

    Multimodal LLM-based Query Paraphrasing for Video Search · 2026 · DOI

  • Each update, however, can invalidate search paths already learned by the retriever, and the quantitative relationship between mapping change and retrieval quality has not been systematically characterized.

    Don't Rewrite the SID Map: Topology Preservation for Generative Retrieval in Dynamic E-Commerce Search · 2026

  • The previous research disjointly discusses the factors supporting information exploration and discovery, which remain limited to theoretical discussion and have limited applicability to existing search engines.

    Discovery work-space design to explore semantically aggregated graph-cluster spaces of multimedia document results · 2025 · DOI

  • The study suggests that future research should focus on empirical studies of generative search, information authority, and information practices shaped by artificial intelligence. The study highlights the need for further research on the implications of generative engine optimisation for content producers and information seekers.

    From the click race to the citation game: a conceptual exploration of the shift from search engine optimisation to generative engine optimisation · 2026 · DOI

  • The study suggests that future research should examine internal information behaviours in more detail. The paper acknowledges that other disciplines, such as psychology, will also have contributions that can be made.

    Information behaviours and the inner life · 2026 · DOI

  • Balancing the need for inclusion and the necessity to legally empower service providers.

    Metadiscourse in Online Terms of Service · 2026 · DOI

  • There is a lack of studies on metadiscourse in contracts and agreements. Prior studies have focused on metadiscursive strategies in judicial materials.

    Metadiscourse in Online Terms of Service · 2026 · DOI

  • The team faced the challenge of addressing user needs and preferences.

    From Card Catalogs to Semantic Search · 2026 · DOI

  • The project's findings can inform future research on the development of AI-powered library discovery systems.

    From Card Catalogs to Semantic Search · 2026 · DOI

  • Further research is needed to explore the use of AI in DNA testing services. The development of new media and genetic research can lead to the emergence of new services and applications. The paper's findings can inform the development of new policies and regulations for the use of AI in DNA testing services.

    New media and genetic revolution: AI in DNA testing websites Ancestry and MyHeritage · 2026 · DOI

  • The paper highlights the need for a comparative analysis of DNA testing services. The paper identifies the need for further research on the use of AI in DNA testing services.

    New media and genetic revolution: AI in DNA testing websites Ancestry and MyHeritage · 2026 · DOI

  • Future studies could explore indicator use enabling open-ended search tasks outside laboratory settings, with larger and more diverse participant samples both in terms of scientific discipline and scientometric literacy, or incorporating complementary quantitative methods and inferential statistics.

    How scientometric indicators shape relevance: an exploratory experimental user study · 2026 · DOI

  • While a total of 50 participants provides a robust basis for qualitative analysis, it is insufficient for inferential statistical testing.

    How scientometric indicators shape relevance: an exploratory experimental user study · 2026 · DOI

  • While discovering unknown, yet relevant scientific resources is of paramount importance for knowledge making, little is known about how researchers deploy specific informational practices on, usually ill-equipped, digital scholarly platforms to turn search engines, designed for findability, into discovery engines.

    Venturing into the noise: Discoverability practices of open scholarly resources on a national digital library · 2026 · DOI

  • Hallucinations can contaminate semantic representations and degrade retrieval quality. Evaluating the quality of LLM-generated content remains a fundamental challenge in NLP. Disentangling hallucination severity from retrieval degradation is a critical challenge.

    Contrastive hallucination impact mitigation and evaluation for zero-shot dense retrieval systems · 2026 · DOI

  • There is no ground truth for the network of education pathways. Not all programs are officially regulated by the state or federal government. Chambers do not always publish relevant data, and not all education pathways are formalized.

    Web Mining of Online Resources for German Labor Market Research and Education: Finding the Ground Truth? · 2024 · DOI

  • Deeper improvements include support for the visually impaired.

    Dynamic Decision Trees · 2024 · DOI

  • Expert systems are challenging to author for non-programmers. Modern systems require dedicated technical support. State-of-the-art knowledge-based systems are primarily used for customer support and ticket tracking rather than complex decision-making.

    Dynamic Decision Trees · 2024 · DOI

  • Internal information behaviours have not been a focus in information science research. The traditional focus in information science on the tangibility of information has underplayed the importance of what we do with internal information.

    Information behaviours and the inner life · 2026 · DOI

  • The study provides a novel interdisciplinary application of contemporary IB theories to the Quranic narrative, an area rarely investigated in information science research.

    Information behaviour in the Holy Quran: a textual analysis study of patterns and classifications in Surat Yusuf · 2026 · DOI

  • Further investigation into educational pathways and linked data for labor market research, - Extension to other languages such…

    Web Mining of Online Resources for German Labor Market Research and Education: Finding the Ground Truth? · 2024 · DOI

  • Google’s AI Overviews (AIOs) − AI-generated summaries − mark a shift from information retrieval to AI-driven curation, raising underexplored questions about political and news exposure and algorithmic gatekeeping.

    A search changer: auditing Google’s AI overviews interface in political and news search · 2026 · DOI

  • The study identifies a gap in understanding the relationship between keyword length, search volume, and estimated organic traffic in the context of SEO for hotels.

    A hossz számít? – A kulcsszóhossz és a keresési volumen hatása a seo teljesítményre egy szálloda példáján · 2026 · DOI

  • It is that the unconditioned rating, in the form that is shipped, has not been separated from the architecture it sits in by any work this run could find, that the nearest thing to a separation ranks it fourth of five and behind a rule requiring no model call, and that one survey of the area lists the problem it would solve - "how to estimate memory importance without future-sight" - among its open questions rather…

    Scored Before the Question Exists: What a Write-Time Importance Value in LLM Agent Memory Predicts, Why an Additive Term Is Not a Prior, and the Ablation the Canonical Architecture Did Not Run · 2026 · DOI

  • Existing evaluation frameworks lack mechanisms to disentangle hallucination severity from retrieval degradation, - Existing frameworks provide aggregate quality scores without diagnostic insights, - The study focuses on retrieval-oriented generation, - The study does not provide a comprehensive comparison with other state-of-the-art…

    Contrastive hallucination impact mitigation and evaluation for zero-shot dense retrieval systems · 2026 · DOI

Most-cited papers in Information Retrieval and Search Behavior

Most recent work

Find a gap in your own Information Retrieval and Search Behavior sub-topic

This page shows what the Information Retrieval and Search Behavior literature already flags as unresolved. To narrow it to your specific question, search the Research Gap Finder: the search is free with a free account and lists the papers closest to your topic first. Unlocking that topic (50 credits, charged once) fills the comparison table from our 7.9M-paper local library and writes the gaps from its rows.

Open the Research Gap Finder →

Related topics in Computer Science

Online Learning and Analytics
1,253 open questions
Advanced Neural Network Applications
1,236 open questions
AI in Service Interactions
1,161 open questions
Virtual Reality Applications and Impacts
1,060 open questions
Computational Drug Discovery Methods
1,019 open questions
Quantum Computing Algorithms and Architecture
877 open questions
AI in cancer detection
835 open questions
Topic Modeling
780 open questions
Open questions raised by papers listed on this page include: (1) There is a need for a more effective and scalable approach to text-to-video retrieval (“Multimodal LLM-based Query Paraphrasing for Video Search”, 2026); (2) The study suggests that future research should focus on empirical studies of generative search, information authority, and information practices shaped by artificial intelligence (“From the click race to the citation game: a conceptual exploration of the shift…”, 2026); (3) The study suggests that future research should examine internal information behaviours in more detail (“Information behaviours and the inner life”, 2026); (4) There is a lack of studies on metadiscourse in contracts and agreements (“Metadiscourse in Online Terms of Service”, 2026); (5) Further research is needed to explore the use of AI in DNA testing services (“New media and genetic revolution: AI in DNA testing websites Ancestry and…”, 2026). 193 gap statements have been mined from Information Retrieval and Search Behavior papers in our 7.9M-paper local library, which holds 2,506 papers on the topic; the gaps come from whichever of those papers state one. They are mostly the research gaps the authors state and the papers' abstracts, plus future-work, limitations and challenges passages. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 1,100,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? Acceptance odds for top, mid and open/emerging journals, in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck for prior publication across 7 sources and our local library.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

How Pre-Check worksHow AI Review works

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.