大模型
arxiv.org ·
大型语言模型偏好近期内容吗？基于LLM的重排序中的近因偏差研究
该 arXiv 论文研究 LLM 作为信息检索第二阶段重排序器时的近因偏差。作者在 TREC Deep Learning 2021/2022 段落检索集合中为段落前置人工发布日期，测试 GPT-3.5-turbo、GPT-4o、GPT-4、LLaMA-3 8B/70B 与 Qwen-2.5 7B/72B 共 7 个模型。结果显示“新鲜”段落被系统性提升：Top-10 平均出版年份前移最多 4.78 年，单项排名最多移动 95 位；在成对偏好实验中，同等相关度段落的偏好因日期注入平均最多反转 25%。更大模型可减弱但无法消除该效应。
AI推荐理由 arXiv 论文（v2，2026-09-21 修订），研究 LLM 作为检索重排序器时的近因偏差：在 TREC DL21/DL22 段落上人工注入发布日期，测试 GPT-3.5-turbo、GPT-4o、GPT-4、LLaMA-3 8B/70B、Qwen-2.5 7B/72B 共 7 个模型。摘要给出具体量化结果：Top-10 平均出版年份前移最多 4.78 年、单项排名最多移动 95 位、同等相关度下成对偏好平均最多反转 25%，且更大模型只能减弱不能消除该偏差。对 RAG、搜索排序和 LLM 评测有直接参考价值，属可验证的实验证据而非传闻；局限是仅基于摘要，未提供数据集规模、显著性检验等细节，且偏差结论限于 TREC 段落检索场景。
78
正文
Computer Science > Information Retrieval
arXiv:2509.11353 (cs)
[Submitted on 14 Sep 2025 (v1), last revised 21 Sep 2026 (this version, v2)]
Title:Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking
Authors:Hanpei Fang, Sijie Tao, Nuo Chen, Kai-Xin Chang, Tetsuya Sakai
View a PDF of the paper titled Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking, by Hanpei Fang and 3 other authors
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) are increasingly deployed in information systems, including being used as second-stage rerankers in information retrieval pipelines, yet their susceptibility to recency bias has received little attention. We investigate whether LLMs implicitly favour newer documents by prepending artificial publication dates to passages in the TREC Deep Learning passage retrieval collections in 2021 (DL21) and 2022 (DL22). Across seven models, GPT-3.5-turbo, GPT-4o, GPT-4, LLaMA-3 8B/70B, and Qwen-2.5 7B/72B, "fresh" passages are consistently promoted, shifting the Top-10's mean publication year forward by up to 4.78 years and moving individual items by as many as 95 ranks in our listwise reranking experiments. Although larger models attenuate the effect, none eliminate it. We also observe that the preference of LLMs between two passages with an identical relevance level can be reversed by up to 25% on average after date injection in our pairwise preference experiments. These findings provide quantitative evidence of a pervasive recency bias in LLMs and highlight the importance of effective bias-mitigation strategies.
Subjects:
Information Retrieval (cs.IR)
Cite as:
arXiv:2509.11353 [cs.IR]
(or
arXiv:2509.11353v2 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2509.11353
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Hanpei Fang [view email]
[v1]
Sun, 14 Sep 2025 17:11:07 UTC (251 KB)
[v2]
Mon, 21 Sep 2026 16:59:30 UTC (238 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking, by Hanpei Fang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Additional Features
Audio Summary
Current browse context:
cs.IR
new
|
recent
| 2025-09
Change to browse by:
cs
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?)