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

arXiv: https://arxiv.org/abs/2510.07972 · HTML: https://mlsanity.com/paper/2510.07972/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)
- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library](https://mlsanity.com/paper/2506.06122/) (2025)
- [Information Retrieval: Recent Advances and Beyond](https://mlsanity.com/paper/2301.08801/) (2023)
- [On Application of Learning to Rank for E-Commerce Search](https://mlsanity.com/paper/1903.04263/) (2019)

## Built on by (most cited first, 1 of 1)

- [K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance](https://mlsanity.com/paper/2604.25683/) (2026)

## Abstract (arXiv)

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.