Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2407.03650

Reviewers of Educational Immersive and Extended Reality (XR) experiences: Who is creating these reviews and why?

Sophie McKenzie·Shaun Bangay·Maria Nicholas·Adam Cardilini·Majeet Singh
View original source ↗Read source document ↗Export metadata ↓

Abstract

This paper presents a scoping review of literature to examine who is reviewing educational immersive or extended reality - eduXR experiences and why. EduXR experiences in augmented, virtual or mixed reality take many forms, from supporting manual training, engaging learners in conservation, to provide opportunities for social connection. For users of eduXR, reviews of an experience can provide information that helps them determine whether it will meet their learning needs or not. The source of the review, that is, who they are and why they have conducted the review, is critical in helping the user judge the reviews quality and relevance. At present, there is no settled review system in place for eduXR, though relevant frameworks exist for serious games review with relevance and overlap for some, but not all, eduXR experiences. While some authors have engaged in preparing a detailed review structure for eduXR, there remains a need for a clear and simple way for users of eduXR to know details about reviewers, e.g., who and why, to help make it easier for users to identify relevant reviews and gain useful insight about eduXR experiences. To help address this issue, we conducted a scoping review asking the question; Who is creating eduXR reviews, and why? We identified 16 papers that present an academic evaluation on the review process of eduXR reviews. The 16 papers were analysed, coding for who themes and why themes over two separate cycles, using thematic analysis. An analysis looked to examine what we know regarding who is providing the reviews, and why, to help us to understand what enables, inhibits and what is yet unknown about how the eduXR community goes about making informed choices regarding the eduXR experiences they engage with.

Explore related subjects

cs.IRcs.CY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Sophie McKenzie, Shaun Bangay, Maria Nicholas, Adam Cardilini, Majeet Singh. 2024-07-04. Reviewers of Educational Immersive and Extended Reality (XR) experiences: Who is creating these reviews and why?. https://arxiv.org/abs/2407.03650

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

RankSteer: Can Pointwise LLM Rankers Be Calibrated at the Representation Level?

Large language models (LLMs) are strong zero-shot pointwise rankers, but lag behind pairwise and listwise methods. Beyond missing comparative signals, we identify a \textit{calibration gap}: ranking-relevant information encoded in hidden states is not fully captured by the scalar output head. We propose RankSteer, a post-hoc activation-steering framework that calibrates ranking via projection-based interventions along multiple directions at inference time: decision, evidence, and, optionally, role. This is achieved without updating model weights or introducing cross-document comparisons. We instantiate RankSteer on two structurally distinct pointwise variants and observe improvements over their respective baselines on most TREC DL and BEIR datasets across three backbones. This suggests that the calibration gap is a general property of pointwise rankers. Our additional geometric analysis shows that steering improves ranking by concentrating each query's document representations along an existing ranking geometry, offering new insight into how LLMs internally represent and calibrate relevance judgments.

cs.IR↗
arXiv2026

IntHQ: Task-Interactive Hierarchical Query on Dual-Stream Representations for Generative Recommendation

Multi-task learning over heterogeneous data is fundamental to modern recommendation, while generative models are emerging as the backbone of next-generation recommenders. However, the integration of multi-task learning into the generative paradigm remains largely unexplored. Existing multi-task recommenders, in both discriminative and generative paradigms, extract task-relevant features from a single task-agnostic representation and wire tasks into a predefined conversion funnel. We show that this scheme is inherently prone to a threefold collapse. Source collapse, where task-specific signals are injected late and diluted in the shared latent space. Relational collapse, where task dependencies are either implicitly absorbed by the backbone or statically fixed by predefined funnels. Hierarchical collapse, where tasks depend on features at different scales and shift across training stages. We propose IntHQ, a multi-task generative recommender with three components, each alleviating one collapse. Dual-Stream Decoupling (DSD) injects task identity into computation stream early and separates the shared context stream from the task-specific stream, alleviating signal dilution. Task-Interactive Modeling (TIM) replaces the predefined funnel with explicit cross-task interaction, letting each task condition on the realized outcomes of its predecessors with learned, input-adaptive strength. Hierarchical Querying (HQ) lets each task gather multi-scale information across different layers at different training stages. In offline evaluations, IntHQ consistently outperforms competitive encoder backbones under four representative task-head configurations. Deployed in production on Amap, serving hundreds of millions of users for travel recommendation, IntHQ yields a 1.60\% relative UVCTR lift.

cs.IR↗
arXiv2026

Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale

Large language model (LLM) agents can propose, implement, and evaluate model changes. Autoresearch loops demonstrate this capability through minutes-scale iterations on a self-contained program. Online autoresearch instead spans asynchronous systems, hours-long variants, and weeks-long campaigns that can influence a product. A completed run can still support an invalid conclusion when a code change is a no-op, data windows leak, evaluator semantics drift, or the two arms traverse different serving funnels. We present EvoPilot, a human-gated method for long-horizon online autoresearch. Role-specific agents execute each round through a versioned domain skill and typed adapter. Durable records preserve experiments and failures; deterministic checks enforce recorded lessons. We study a 37-day campaign for the retrieval system that powers Video Deep Dive (VDD), an online experience for discovering follow-on videos after a user opens a seed video. The campaign covered seven directions and used an hourly refreshed index of hundreds of millions of videos. Earlier manual experiments had not established a benefit from an interaction head. A primitive autoresearch attempt revisited the direction but incorrectly attributed an offline hit-rate decline of 22 percentage points to the head. We then introduced EvoPilot. Its human-gated verification traced the drop to a pre-existing evaluation defect that produced output depths of 3,000 and 600. After repair, a matched comparison measured an offline improvement of 3.20 percentage points. Post-study replay and mutation tests rejected invalid comparisons while admitting valid counterparts. Durable state recovered an interrupted round, and artifact reuse avoided approximately five GPU-hours. Separately, a seven-day randomized online evaluation estimated a 0.66% relative increase in the VDD slice of Good Search Result Rate for Retention (GSRR).

cs.IR↗