This paper proposes a unified multi-task framework for handling six different entity pair relationship types in e-commerce with a shared relevance model.
The paper combines three novel ideas to address the problem of building a single relevance model for multiple tasks with different data volumes and semantic requirements.
Before reading this…
Applications
To understand this paper, make sure you know these concepts first:
How can we build a single relevance model that handles six different entity pair relationship types in e commerce from query product matching to product type similarity when each task has different data volumes, different semantic requirements, and potentially conflicting learning signals? This question is important because current industry practice relies on separate models for each task, preventing knowledge transfer and producing inconsistent relevance signals. Our work is driven by the following insight: encoder based and decoder only models encode task identity through different mechanisms, so the choice of task routing architecture how task identity is communicated to the shared model affects these two families in asymmetric ways. As our key novelty, we combine three ideas: (a) a unified multi task framework that jointly trains on six entity pair tasks under a shared three point relevance scale, (b) a systematic comparison of three task routing architectures (text prefix routing, multi head classification, and multihead with private transformer layers) across both LoRA adapted LLMs and fully finetuned cross encoders, and (c) a majority vote ensemble that exploits the diversity induced by private layer routing. First, we show that the MHP Ensemble (multi head with private layers) achieves 89.96% accuracy on 453K test examples the highest across all configurations . Second, we show that removing text prefixes without private layers causes severe degradation for decoder only LLMs while cross encoders remain robust , suggesting an encoder decoder asymmetry in task identity encoding. Third, we show that multi task training yields up to 14% improvement on low resource tasks over single task baselines.
How BERT-based Cross-Encoders Model Relevance in Information Retrieval?
This paper investigates the behavior of cross-encoders in information retrieval…
Robot-Task Suitability in Heterogeneous Multi-Robot Task Allocation
This paper compares ten deterministic and two LLM-based methods for estimating r…
DiffRouter: A Differentiable Routing Framework for UltraScale FPGAs
Introduces DiffRouter, a differentiable, gradient-based FPGA routing framework w…
CertMoE: Robustness Certification for Mixture-of-Experts LLMs via Routing-Aware Smoothing
This paper presents a new certification framework for Mixture-of-Experts Large L…
Mobile Embodied Agent Network (MEAN): Integrated Framework, Enabling Technologies, and Task-Driven D…
This paper proposes a new networking paradigm called MEAN, which integrates perc…
KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation
This paper introduces KuaiRecV2, a benchmark for recommender systems that addres…
Robustness Analysis of Pareto-based Joint Evaluation of Fairness and Relevance in Recommender System…
A new approach to jointly evaluate fairness and relevance in recommender systems…
Task Offloading and Resource Allocation for Deterministic Service Provisioning in the IoT-Edge-Cloud…
This paper proposes a deterministic task offloading and resource allocation sche…