arXiv subjects

Zerui Huang

Publications and source records attributed to Zerui Huang.

6 recordsLinked to original sources

arXiv2025

Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevance

Accurately estimating query-item relevance is vital for e-commerce ranking and conversion. While Large Language Models (LLMs) excel at reasoning, they often lack specialized knowledge required for long-tail or fast-evolving queries, necessitating Retrieval-Augmented Generation (RAG). However, production environments face three critical challenges: (1) external context is inherently noisy and inconsistent; (2) extreme latency budgets prohibit multi-stage processing or refinement; and (3) the model must simultaneously assess relevance and context-trust within a unified inference pass. We propose DyKnow-RAG, a reinforcement learning framework that teaches LLMs to learn to trust through dynamic utilization of external knowledge. Built on Group Relative Policy Optimization (GRPO), DyKnow-RAG utilizes a dual-group rollout strategy (parametric-only vs. with-context) and a posterior-driven inter-group advantage scaling mechanism. This enables the model to optimize context utilization without human process labels or extra inference overhead. Our pipeline further integrates structured Chain-of-Thought (CoT) and an uncertainty-prioritized RL pool to stabilize training.Offline evaluations show significant Macro-F1 and Accuracy gains, particularly on noise-sensitive query slices. Importantly, DyKnow-RAG has been deployed in Taobao's production system, serving hundreds of millions of active users and billions of daily search requests. Controlled A/B tests demonstrate consistent lifts in key business metrics, including GSB and Item Goodrate, while maintaining a p99 latency under 400ms. This work provides a scalable and deployable paradigm for operationalizing noisy RAG under extreme efficiency constraints of large-scale industrial search.

cs.IR↗

arXiv2025

SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance

Query-product relevance prediction is vital for AI-driven e-commerce, yet current LLM-based approaches face a dilemma: SFT and DPO struggle with long-tail generalization due to coarse supervision, while traditional RLVR suffers from sparse feedback that fails to correct intermediate reasoning errors. We propose Stepwise Hybrid Examination (SHE), an RL framework that ensures logical consistency through Stepwise Reward Policy Optimization (SRPO). SRPO utilizes a hybrid reward mechanism-combining generative reward models with human-annotated verifiers-to provide fine-grained, step-level signals. To further enhance stability, SHE incorporates diversified data filtering to maintain policy entropy and a multi-stage curriculum learning protocol for progressive skill acquisition. Extensive experiments on real-world search benchmarks show that SHE improves both reasoning quality and relevance-prediction accuracy in large-scale e-commerce settings, outperforming SFT, DPO, GRPO, and other baselines, while also enhancing interpretability and robustness.

cs.AI↗

arXiv2025

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance

Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference optimization methods like Direct Preference Optimization (DPO). However, the increasing complexity of business rules and user queries exposes the inability of existing methods to endow models with robust reasoning capacity for long-tail and challenging cases. Efforts to address this via reinforcement learning strategies like Group Relative Policy Optimization (GRPO) often suffer from sparse terminal rewards, offering insufficient guidance for multi-step reasoning and slowing convergence. To address these challenges, we propose TaoSR-AGRL, an Adaptive Guided Reinforcement Learning framework for LLM-based relevance prediction in Taobao Search Relevance. TaoSR-AGRL introduces two key innovations: (1) Rule-aware Reward Shaping, which decomposes the final relevance judgment into dense, structured rewards aligned with domain-specific relevance criteria; and (2) Adaptive Guided Replay, which identifies low-accuracy rollouts during training and injects targeted ground-truth guidance to steer the policy away from stagnant, rule-violating reasoning patterns toward compliant trajectories. TaoSR-AGRL was evaluated on large-scale real-world datasets and through online side-by-side human evaluations on Taobao Search. It consistently outperforms DPO and standard GRPO baselines in offline experiments, improving relevance accuracy, rule adherence, and training stability. The model trained with TaoSR-AGRL has been successfully deployed in the main search scenario on Taobao, serving hundreds of millions of users.

cs.IR↗

arXiv2025

TaoSR1: The Thinking Model for E-commerce Relevance Search

Query-product relevance prediction is a core task in e-commerce search. BERT-based models excel at semantic matching but lack complex reasoning capabilities. While Large Language Models (LLMs) are explored, most still use discriminative fine-tuning or distill to smaller models for deployment. We propose a framework to directly deploy LLMs for this task, addressing key challenges: Chain-of-Thought (CoT) error accumulation, discriminative hallucination, and deployment feasibility. Our framework, TaoSR1, involves three stages: (1) Supervised Fine-Tuning (SFT) with CoT to instill reasoning; (2) Offline sampling with a pass@N strategy and Direct Preference Optimization (DPO) to improve generation quality; and (3) Difficulty-based dynamic sampling with Group Relative Policy Optimization (GRPO) to mitigate discriminative hallucination. Additionally, post-CoT processing and a cumulative probability-based partitioning method enable efficient online deployment. TaoSR1 significantly outperforms baselines on offline datasets and achieves substantial gains in online side-by-side human evaluations, introducing a novel paradigm for applying CoT reasoning to relevance classification.

cs.IR↗

arXiv2024

Intention Knowledge Graph Construction for User Intention Relation Modeling

Understanding user intentions is challenging for online platforms. Recent work on intention knowledge graphs addresses this but often lacks focus on connecting intentions, which is crucial for modeling user behavior and predicting future actions. This paper introduces a framework to automatically generate an intention knowledge graph, capturing connections between user intentions. Using the Amazon m2 dataset, we construct an intention graph with 351 million edges, demonstrating high plausibility and acceptance. Our model effectively predicts new session intentions and enhances product recommendations, outperforming previous state-of-the-art methods and showcasing the approach's practical utility.

cs.CL↗

arXiv2024

Image enhancement algorithm for absorption imaging

The noise in absorption imaging of cold atoms significantly impacts measurement accuracy across a range of applications with ultracold atoms. It is crucial to adopt an approach that offers effective denoising capabilities without compromising the unique structure of the atoms. Here we introduce a novel image enhancement algorithm for cold atomic absorption imaging. The algorithm successfully suppresses background noise, enhancing image contrast significantly. Experimental results showcase that this approach can enhance the accuracy of cold atom particle number measurements by approximately tenfold, all while preserving essential information. Moreover, the method exhibits exceptional performance and robustness when confronted with fringe noise and multi-component imaging scenarios, offering high stability. Importantly, the optimization process is entirely automated, eliminating the need for manual parameter selection. The method is both compatible and practical, making it applicable across various absorption imaging fields.

quant-ph↗