Jul 2026· Annual International ACM SIGIR Conference on Research and Development in Information Retrieval· pp. 2708-2720· 0 citations· 90 references
Computer Science
TL;DR
Functional requirements for RAG systems serving cognitively diverse populations, including temporal user modelling that tracks cognitive trajectories over time, caregiver-in-the-loop retrieval that enables verification and oversight, consent-aware evidence access that respects fluctuating capacity, and cognitive-load-aware presentation that adapts complexity to comprehension level are outlined.
Abstract
Current Information Retrieval (IR) systems, including conversational IR paradigms enhanced by Retrieval-Augmented Generation (RAG), assume that users can formulate coherent queries and reliably interpret retrieved information. In dementia care contexts, these assumptions fail: queries are unstable, feedback signals are unreliable, relevance fluctuates with cognitive state, and multi-user interaction is essential. Dementia impacts over 50 million people globally, yet current RAG research has yet to consider use cases where users have dementia or Mild Cognitive Impairment (MCI), and so RAG systems continue to be designed without considering people with dementia, MCI, or their caregivers as users, creating a fundamental mismatch between system capabilities and this population's needs. Our perspective outlines functional requirements, not optional features, for RAG systems serving cognitively diverse populations, including temporal user modelling that tracks cognitive trajectories over time, caregiver-in-the-loop retrieval that enables verification and oversight, consent-aware evidence access that respects fluctuating capacity, and cognitive-load-aware presentation that adapts complexity to comprehension level. These requirements would collectively transform RAG from a cognitively-stable user paradigm into a cognitively-adaptive one. Drawing on participatory workshops with 41 members of the public and dementia-care community, our perspective was shaped through empirical evidence from those with lived experience of dementia or MCI. We advocate for inclusive IR through our cognitively-adaptive RAG that supports cognitive independence in dementia care, and call on the IR community to advance accessibility and equity through inclusive retrieval system design.
Virtual Humans enhanced with Large Language Models can hold broad conversations, but their answers may sound convincing while still being factually incorrect. Such hallucinations can mislead users and reduce trust, especially because research shows that people often overestimate LLM accuracy and may remain distrustful after errors occur. This loss of trust is particularly concerning in medical contexts, where reliable information is essential. Retrieval-augmented generation (RAG) addresses this issue by grounding LLM responses in external knowledge sources that were not part of the model's training data. The described Virtual Human demonstration system uses RAG with 14 geriatrics patient brochures from the Canisius Wilhelmina Hospital, which were converted into question-answer chunks and embedded. At runtime they were retrieved based on similarity to user queries. The system allows for comparison of four RAG approaches, i.e. Basic RAG, HyDE RAG, Reranking RAG, and Cognitive RAG, each using different strategies to improve retrieval and response quality. Users can choose among these RAG options in the application menu, as well as set some other user preferences. Response quality can be evaluated using RAGAS metrics and latency related data. User experience data can also be collected for correlation to RAG performance data.
Roel Boumans· Proceedings of the 26th ACM...· 0 citations
Findings support RAG as a promising approach to improve the accuracy, consistency and safety of LLM-driven DMHIs through a controlled comparison of RAG-enabled versus RAG-disabled modes.
A. Gupta, Akshat Surolia, Shubham Mishra et al.· arXiv.org· 0 citations
The Agent and Incremental Learning-based Multimodal Information Retrieval (AILMIR) framework is introduced, shifting the paradigm toward a dynamic Plan-Execute-Reflect cognitive loop, and a Non-Parametric Case-Based Memory is proposed that sediments successful reasoning trajectories, enabling efficient Domain Incremental Learning without destructive gradient updates.
Yichen Fan, Zihan Yang, Haitao Qin et al.· International Journal of Mul...· 0 citations
Retrieval-augmented generation (RAG) can improve the specificity and grounding of large language model responses, but its effect is not uniformly beneficial in single-turn mental-health question answering, where user queries often combine emotional distress, treatment concerns, and safety-sensitive needs. We study when retrieval helps or hurts mental-health QA, and whether a lightweight selective retrieval policy can better control this trade-off. We operationalize retrieval need using three draft-conditioned utility dimensions: psychoeducational need, coping need, and response specificity, together with a rule-based safety trigger. Following psychotherapy-grounded RAG systems such as coTherapist, we construct a compact and controllable guideline corpus comprising coping-strategy, psychoeducational, and safety resources. We fine-tune an instruction-tuned generator on MentalChat16K using QLoRA and compare Closed-book, Always Retrieval, and Selective Retrieval settings on CounselBench-Eval and CounselBench-Adv. Experiments show that retrieval is not uniformly beneficial in this domain. Always Retrieval improves specificity but lowers overall quality and introduces additional safety-sensitive failures. Selective Retrieval preserves closed-book behavior for low-need cases while avoiding the additional degradation caused by unconditional retrieval, supporting the view that retrieval activation is a safety-sensitive control decision.
As the global population ages, older adults increasingly rely on AI-assisted systems to support independent living. However, current multimodal systems do not account for the wide range of cognitive abilities among older adults, often either overwhelming them with redundant information or over-automating decisions in ways that reduce autonomy. This scoping review maps current research on multimodal AI systems for older adults in home environments, focusing on balancing information richness with cognitive load. Following the PRISMA framework, we searched IEEE Xplore, ACM Digital Library, and Scopus, identifying 681 records, of which 5 studies met the inclusion criteria after screening. Our findings highlight four key design strategies: modality distribution based on information criticality, contextual automation to reduce query formulation burden, single-result confidence versus multi-option exploration, and context-dependent information delivery. Based on these insights, we propose the Context-Adaptive Information Layering framework, which organizes information into Essential, Contextual, and Exploratory layers that adapt based on learned user patterns, task criticality, and cognitive state indicators.
Unknown authors· Proceedings of the Human Fac...· 0 citations
This workshop aims to gather a multidisciplinary community to reflect on pressing challenges and uncertainties and explore risk analysis and mitigation strategies in CUI design and deployment and build an international network of scholars and practitioners to promote responsible and human-centred conversational AI.
Manveer Kalirai, C. Wei, Thomas Essmeyer et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
