Relevance
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments
arXiv:2602.23234v4 Announce Type: replace Abstract: Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for. To maximize relevance, we leverage two complementary objectives: behavioral relevance (results users tend to click or download) and textual relevance (a result's semantic fit to the query). A persistent challenge is the scarcity of expert-provided textual relevance labels relative to abundant behavioral...
Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments
arXiv:2602.23234v5 Announce Type: replace Abstract: Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for. To maximize relevance, we leverage two complementary objectives: behavioral relevance (results users tend to click or download) and textual relevance (a result's semantic fit to the query). A persistent challenge is the scarcity of expert-provided textual relevance labels relative to abundant behavioral...
Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors
Announce Type: new Abstract: Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflect relevance: they select only a subset of documents for labeling, and this selection can favor certain document types over others. We investigate whether supervised bi-encoder retrievers implicitly learn a document-level relevance prior: a query-independent signal encoded in their representation space as a side...
Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance
arXiv:2605.31003v1 Announce Type: new Abstract: Search relevance modeling is a core task in e-commerce search systems, assessing how well a user query matches candidate products. Rather than relying on a single holistic matching signal, relevance judgment often requires structured reasoning over query understanding, product understanding, and facet-level matching. With large language models (LLMs), this process is increasingly formulated as chain-of-thought (CoT) reasoning and optimized with...
DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance Modeling
Announce Type: new Abstract: Despite rapid progress of continuous embeddings for e-commerce search relevance, a long-standing open problem is the difficulty in capturing fine-grained attribute distinctions. While discrete Semantic Identifiers (SIDs) have been widely adopted as a promising alternative, existing SID generation methods rely heavily on unsupervised quantization. In realistic scenarios, the lack of explicit supervision often makes it more difficult to dictate which items should...
AI-guided catalyst turns CO₂ and waste into fertilizer at industrially relevant rates
AI-guided catalyst turns CO₂ and waste into fertilizer at industrially relevant rates Sadie Harley Scientific Editor Robert Egan Associate Editor Researchers from the National University of Singapore (NUS) have developed a computation-guided strategy to produce urea more efficiently from carbon dioxide and nitrate. By combining large language models, density functional theory calculations and experiments, the approach identified a cadmium-modified iron oxide catalyst that maintains high urea...
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
Announce Type: replace Abstract: Vision-Language-Action (VLA) models aim for general robot learning by aligning action as a modality within powerful Vision-Language Models (VLMs). Existing VLAs rely on end-to-end supervision to implicitly enable the action decoding process to learn task-relevant features. However, without explicit guidance, these models often overfit to spurious correlations, such as visual shortcuts or environmental noise, limiting their generalization.
CURE-like, not cure-all: Varying broad relevance in experimentation labs produces similar student outcomes
Announce Type: new Abstract: Physics labs that engage students in practices authentic to experimental physics (experimentation-based labs) are being implemented to modernize the undergraduate physics curriculum and broaden participation in physics. Accordingly, prior research has positioned Course-Based Undergraduate Research Experiences (CUREs) as a means to extend the benefits of authentic undergraduate research experiences to more students. However, CUREs are resource-intensive and...
DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification
arXiv:2606.09466v1 Announce Type: new Abstract: Classification tasks require annotated data, which can often be expensive, time-consuming, or even unfeasible to collect. This is the case of the medical domain, where large datasets often have few annotated examples. To address this, we propose DecSelfMask (Decoder Self-learning by Masking), an approach to enhance decoder-only performance on classification tasks.
SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics
Announce Type: new Abstract: Scalable information retrieval testing needs corpora that are large enough to stress index construction, ranking latency, query routing, and evaluation tooling, yet human-judged test collections remain expensive and may be unavailable when documents are private or still under design. This paper introduces SPECTRA, a reproducible framework for generating synthetic text corpora and retrieval test collections through a separation of latent topical structure, surface...