RPTune：面向 LLM 商品目录搜索的学习式上下文整理框架
RPTune: Learned Context Curation for LLM Catalog Search
RPTune 是一个端到端框架，将学习式目录整理与 LLM 后训练结合，用自动生成的目录监督信号提升小商家场景下的上下文商品搜索。其编码器-重组器整理器依据下游 LLM 反馈对商品排序和剪枝，整理后的目录再以上下文相对奖励改进后训练。在 7 个真实商家的 100 条复杂对话查询上，上下文整理最高带来 31.4 个百分点提升，后训练平均再增 10.3 个百分点。
Published on Oct 1
Authors:
,
,
,
,
Abstract
For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage retrieval designed primarily for large marketplaces with millions of items. However, fitting the full catalog into the context window does not ensure that the model can use it effectively, since LLMs do not exploit long contexts uniformly. We therefore study in-context catalog search through two complementary questions: (1) how to curate and present catalogs to the LLM, and (2) how to adapt the LLM for product selection on curated contexts. We propose RPTune, an end-to-end framework that couples learned catalog curation with LLM post-training using automatically generated, catalog-grounded supervision. An encoder-reorganizer curator orders and prunes products guided by downstream LLM feedback, while the resulting curated catalogs in turn improve the effectiveness of LLM post-training with a context-relative reward. We evaluate RPTune on 7 real merchants spanning distinct retail verticals, using 100 complex conversational queries per merchant. RPTune consistently improves search accuracy across both proprietary and open-weight LLMs, with context curation yielding gains of up to 31.4 percentage points and post-training adding a further 10.3 points on average.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.00964
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.00964 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.00964 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.00964 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
来源：HuggingFace Daily Papers（社区热门论文） · huggingface.co