Translating internal information needs into textual queries poses challenges for information retrieval, particularly for users with physical impairments or ill-defined search intentions. Brain Passage Retrieval (BPR) approaches map EEG signals directly to dense passage representations, bypassing text translation. Whilst recent work reports superior performance with auditory versus visual EEG, these findings emerge from unbalanced experimental conditions where sample sizes, vocabularies, and corpus characteristics differ substantially between modalities, making it unclear whether observed differences reflect genuine neural processing advantages or dataset artefacts. We investigate EEG-based retrieval performance comparing auditory and visual modalities under controlled dataset conditions. Using the Brennan (auditory, 49 subjects) and Nieuwland (visual, 51 subjects) datasets, balanced for vocabulary overlap and sample distributions, we train BPR models with transformer EEG encoders and BERT text encoders via contrastive learning. Under controlled conditions, we observe complementary performance characteristics: audio EEG demonstrates stronger recall (Hit@5: +74%, Hit@10: +140%) whilst visual EEG achieves better precision (Hit@1: +100%). These findings suggest that modality-specific strengths could inform the design of brain-computer interfaces for information retrieval.

Query Performance Prediction (QPP) enables information retrieval systems to estimate search effectiveness without requiring explicit relevance judgements. While traditional QPP research has focused exclusively on textual features, we investigate on enhancing QPP through the multimodal integration of electroencephalography (EEG) and eye-tracking signals captured during listening and reading. We utilise a specialised dataset where queries are represented as text alongside corresponding neurophysiological recordings, with graded relevance judgements for multiple documents. Our methodology employs an ensemble architecture with dedicated models for each modality, followed by a meta-learner that produces final predictions. Experimental evaluation across reading and listening tasks demonstrates that generalised models trained across subjects achieve consistent improvements over text-only baselines, with the trimodal configuration (EEG+eye-tracking+text) reaching Pearson correlation of 0.458 for the ZuCo reading dataset and bimodal EEG+text models achieving 0.417 for the Narrative listening dataset, representing 50–80% higher performance than personalised single-subject models. Query-level analysis reveals that neurophysiological signals substantially improve predictions for fragmentary or semantically ambiguous query cases, while the majority show neutral effects. These findings establish the feasibility of neurophysiological QPP under specific conditions and provide design principles for integrating brain–computer interfaces in information retrieval systems. Our code can be found here .

Information Retrieval (IR) systems primarily rely on users' ability to translate their internal information needs into (text) queries.However, this translation process is often uncertain and cognitively demanding, leading to queries that incompletely or inaccurately represent users' true needs.This challenge is particularly acute for users with ill-defined information needs or physical impairments that limit traditional text input, where the gap between cognitive intent and query expression becomes even more pronounced.Recent neuroscientific studies have explored Brain-Machine Interfaces (BMIs) as a potential solution, aiming to bridge the gap between users' cognitive semantics and their search intentions.However, current approaches attempting to decode explicit text queries from brain signals have shown limited effectiveness in learning robust brain-to-text representations, often failing to capture the nuanced semantic information present in brain patterns.To address these limitations, we propose BPR (Brain Passage Retrieval), a novel framework that eliminates the need for intermediate query translation by enabling direct retrieval of relevant passages from users' brain signals.Our approach leverages dense retrieval architectures to map EEG signals and text passages into a shared semantic space.Through comprehensive experiments on the ZuCo dataset, we demonstrate that BPR achieves up to 8.81% improvement in precision@5 over existing EEG-to-text baselines, while maintaining effectiveness across 30 participants.Our ablation studies reveal the critical role of hard negative sampling and specialised brain encoders in achieving robust cross-modal alignment.These results establish the viability of direct brain-to-passage retrieval and provide a foundation for developing more natural interfaces between users' cognitive states and IR systems.

The fundamental goal of Information Retrieval (IR) systems lies in their capacity to effectively satisfy human information needs -a challenge that encompasses not just the technical delivery of information, but the nuanced understanding of human cognition during information seeking.Contemporary IR platforms rely primarily on observable interaction signals, creating a fundamental gap between system capabilities and users' cognitive processes.Brain-Machine Interface (BMI) technologies now offer unprecedented potential to bridge this gap through direct measurement of previously inaccessible aspects of information-seeking behaviour.This perspective paper offers a broad examination of the IR landscape, providing a comprehensive analysis of how BMI technology could transform IR systems, drawing from advances at the intersection of both neuroscience and IR research.We present our analysis through three identified fundamental vertices: (1) understanding the neural correlates of core IR concepts to advance theoretical models of search behaviour, (2) enhancing existing IR systems through contextual integration of neurophysiological signals, and (3) developing proactive IR capabilities through direct neurophysiological measurement.

One of the foundational goals of Information Retrieval (IR) is to satisfy searchers ' Information Needs (IN).Understanding how INs physically manifest has long been a complex and elusive process.However, recent studies utilising Electroencephalography (EEG) data have provided real-time insights into the neural processes associated with INs.Unfortunately, they have yet to demonstrate how this insight can practically benefit the search experience.As such, within this study, we explore the ability to predict the realisation of IN within EEG data across 14 subjects whilst partaking in a Question-Answering (Q/A) task.Furthermore, we investigate the combinations of EEG features that yield optimal predictive performance, as well as identify regions within the Q/A queries where a subject's realisation of IN is more pronounced.The findings from this work demonstrate that EEG data is sufficient for the real-time prediction of the realisation of an IN across all subjects with an accuracy of 73.5% (SD 2.6%) and on a per-subject basis with an accuracy of 90.1% (SD 22.1%).This work helps to close the gap by bridging theoretical neuroscientific advancements with tangible improvements in information retrieval practices, paving the way for real-time prediction of the realisation of IN.