大模型
arxiv.org ·
基于 LLM 的列表推荐系统离线 A/B 测试：减少对预收集用户交互数据的依赖
该论文研究 LLM 能否对列表推荐（如播放列表）的成对偏好进行判断，以用于合成 A/B 测试。作者提出验证协议，衡量合成偏好与经典推荐指标的吻合度及其对偏好公理的遵循情况，并据此刻画 LLM 预训练与配置对列表偏好表达的影响。结合广义 Rao-Kupper 模型后，基于 LLM 的合成 A/B 测试所得排序在不同效用权重下保持稳定，而 off-policy 估计器仅在目标效用与日志行为一致时可靠。作者将其定位为 off-policy 评估与线上实验之间的筛选阶段，用于把真实 A/B 测试成本留给最有希望的候选方案，而非替代 A/B 测试。
AI推荐理由 arXiv 正式论文（v2，2026-09-23 修订），作者与摘要明确，信息密度高。核心新信息：提出用 LLM 生成 slate 推荐系统成对偏好做合成 A/B 测试，并设计验证协议衡量合成偏好与经典 RecSys 指标的一致性及偏好公理合规性；结合广义 Rao-Kupper 模型后，合成 A/B 测试得到的排序在不同效用权重下保持稳定，而 off-policy 估计器仅在目标效用与日志行为匹配时可靠。作者明确将其定位为 off-policy 评估与线上实验之间的筛选环节，而非替代 A/B 测试，未声称已上线验证。局限：仅摘要层面，缺少实验规模与数据集细节，实际收益需看全文。
72
正文
Computer Science > Information Retrieval
arXiv:2511.04541 (cs)
[Submitted on 6 Nov 2025 (v1), last revised 23 Sep 2026 (this version, v2)]
Title:Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data
Authors:Baptiste Bonin, Maxime Heuillet, Audrey Durand
View a PDF of the paper titled Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data, by Baptiste Bonin and 2 other authors
View PDF
HTML (experimental)
Abstract:Slate recommender systems (RecSys) present users with ordered sets of interacting items (e.g., playlists). We investigate whether large language models (LLMs) can articulate pairwise preferences between slates for synthetic A/B testing of slate RecSys. We introduce a validation protocol measuring the alignment of synthetic preferences with classical RecSys metrics and their compliance with preference axioms, and use it to characterise how LLM pre-training and configuration affect slate preference articulation. Combined with the generalized Rao-Kupper model, synthetic LLM-based A/B testing recovers rankings that remain stable across utility weightings, whereas off-policy estimators are reliable only when the target utility matches the logged behavior. We position it as a screening stage between off-policy evaluation and live experiments: not a replacement for A/B testing, but a way to reserve its cost for the most promising candidates.
Subjects:
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2511.04541 [cs.IR]
(or
arXiv:2511.04541v2 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2511.04541
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Baptiste Bonin [view email]
[v1]
Thu, 6 Nov 2025 16:54:54 UTC (670 KB)
[v2]
Wed, 23 Sep 2026 09:11:31 UTC (817 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data, by Baptiste Bonin and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Additional Features
Audio Summary
Current browse context:
cs.IR
new
|
recent
| 2025-11
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)