Related papers: EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce

EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce

URL: http://arxiv.org/abs/2604.23993v1
Date: Mon, 27 Apr 2026 03:18:00 GMT
Title: EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce
Abstract summary: We present EPM-RL, a reinforcement-learning-based framework for building an efficient on-premise e-commerce product mapping model.<n>Our central idea is to distill high-cost agentic reasoning into a trainable in-house model.<n>Preliminary results show that EPM-RL consistently improves over PEFT-only training and offers a stronger quality--cost trade-off than commercial API-based baselines.
Score: 0.0
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Abstract: Product mapping, the task of deciding whether two e-commerce listings refer to the same product, is a core problem for price monitoring and channel visibility. In real marketplaces, however, sellers frequently inject promotional keywords, platform-specific tags, and bundle descriptions into titles, causing the same product to appear under many different names. Recent LLM-based and multi-agent frameworks improve robustness and interpretability on such hard cases, but they often rely on expensive external APIs, repeated retrieval, and complex inference-time orchestration, making large-scale deployment costly and difficult in privacy-sensitive enterprise settings. To address these issues, we present EPM-RL, a reinforcement-learning-based framework for building an accurate and efficient on-premise e-commerce product mapping model. Our central idea is to distill high-cost agentic reasoning into a trainable in-house model. Starting from a curated set of product pairs with LLM-generated rationales and human verification, we first perform parameter-efficient fine-tuning (PEFT) on a small student model using structured reasoning outputs. We then further optimize the model with Reinforcement Learning (RL) using an agent-based reward that jointly evaluates output-format compliance, label correctness, reasoning--preference scores from specially designed judge models. Preliminary results show that EPM-RL consistently improves over PEFT-only training and offers a stronger quality--cost trade-off than commercial API-based baselines, while enabling private deployment and lower operational cost. These findings suggest that reinforcement learning can turn product mapping from a high-latency agentic pipeline into a scalable, inspectable, and production-ready in-house system.

Related papers

TaoSearchEmb: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search [11.893855231479717]
Retrieval-GRPO is a reinforcement learning-based dense retrieval framework.<n>It has been deployed on China's largest e-commerce platform.
arXiv Detail & Related papers (2025-11-17T20:16:52Z)
E-CARE: An Efficient LLM-based Commonsense-Augmented Framework for E-Commerce [26.230331478424517]
We propose the Efficient Commonsense-Augmented Recommendation Enhancer (E-CARE) for e-commerce tasks.<n>During inference, models augmented with E-CARE can access commonsense reasoning with only a single LLM forward pass per query.<n>Experiments on 2 downstream tasks show an improvement of up to 12.1% on precision@5.
arXiv Detail & Related papers (2025-11-06T05:57:48Z)
Thinking Augmented Pre-training [88.04395622064708]
Thinking augmented Pre-Training is a universal methodology that augments text with automatically generated thinking trajectories.<n>This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories.
arXiv Detail & Related papers (2025-09-24T14:45:13Z)
Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS [62.22644307952087]
We introduce AIRL-S, the first natural unification of RL-based and search-based TTS.<n>We leverage adversarial inverse reinforcement learning (AIRL) combined with group relative policy optimization (GRPO) to learn a dense, dynamic PRM directly from correct reasoning traces.<n>Our results show that our unified approach improves performance by 9 % on average over the base model, matching GPT-4o.
arXiv Detail & Related papers (2025-08-19T23:41:15Z)
Efficient Learning for Product Attributes with Compact Multimodal Models [2.07180164747172]
Image-based product prediction in e-commerce is a crucial task with numerous applications.<n>In this paper, we investigate label-efficient semi-supervised fine-tuning strategies that leverage unlabeled product listings.<n>Experiments demonstrate that accuracy with DPO training improves with more unlabeled data, indicating that a large pool of unlabeled samples can be effectively leveraged to improve performance.
arXiv Detail & Related papers (2025-07-25T21:12:11Z)
LREF: A Novel LLM-based Relevance Framework for E-commerce [14.217396055372053]
This paper proposes a novel framework called the LLM-based RElevance Framework (LREF) aimed at enhancing e-commerce search relevance.<n>We evaluate the performance of the framework through a series of offline experiments on large-scale real-world datasets, as well as online A/B testing.<n>The model was deployed in a well-known e-commerce application, yielding substantial commercial benefits.
arXiv Detail & Related papers (2025-03-12T10:10:30Z)
Self-Refinement Strategies for LLM-based Product Attribute Value Extraction [51.45146101802871]
This paper investigates applying two self-refinement techniques to the product attribute value extraction task.<n>The experiments show that both self-refinement techniques fail to significantly improve the extraction performance while substantially increasing processing costs.<n>For scenarios with development data, fine-tuning yields the highest performance, while the ramp-up costs of fine-tuning are balanced out as the amount of product descriptions increases.
arXiv Detail & Related papers (2025-01-02T12:55:27Z)
Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning [14.224921308101624]
We propose a novel Distribution-Aware Robust Learning framework (DaRL) for relevance modeling.<n>DaRL has been deployed online to serve the Alipay's insurance product search.
arXiv Detail & Related papers (2024-12-17T03:10:47Z)
VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
arXiv Detail & Related papers (2024-10-02T15:49:30Z)
Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
arXiv Detail & Related papers (2024-05-01T11:10:24Z)
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
arXiv Detail & Related papers (2023-08-23T09:45:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.