大模型
arxiv.org ·
迈向由 LLM 驱动的暗物质约束存储库自动化
该论文提出一条 LLM 流水线，自动监控 arXiv、抽取暗物质限制曲线、以代码形式整合并提交 pull request 供人工审核。在 329 篇论文基准上，对 98.1% 可分级论文识别出耦合类型；81% 得到可比抽取，中位残差 0.17 dex，51% 全部论文落在策展人曲线两倍以内。LLM 仅负责感知，算术、单位换算与拒错守卫为确定性可测代码。实际部署已生成限制提案，但尚无一条被合并，作者指出 AI 生成科学数据的治理本身仍未解决。
AI推荐理由 arXiv hep-ex 论文（v2，2026-09-09 修订），提出用 LLM 流水线监控 arXiv、抽取暗物质限制曲线并生成 pull request 供人工审核。给出可验证的量化结果：329 篇基准中 98.1% 可分级论文识别出耦合类型，81% 得到可比抽取、中位残差 0.17 dex，51% 落在策展人曲线两倍以内；LLM 仅用于感知，算术、单位换算与拒错守卫为确定性代码。局限明确：已部署并生成限制提案，但无一被合并，AI 生成科学数据的治理问题未解决。对 AI 在科学基础设施自动化与 human-in-the-loop 流程有参考价值，但属领域专用，非通用模型能力突破。
72
正文
High Energy Physics - Experiment
arXiv:2606.21658 (hep-ex)
[Submitted on 19 Jun 2026 (v1), last revised 9 Sep 2026 (this version, v2)]
Title:Towards LLM-Powered Automation of a Dark Matter Constraint Repository
Authors:Lanqing Yuan, Karthik Ramanathan
View a PDF of the paper titled Towards LLM-Powered Automation of a Dark Matter Constraint Repository, by Lanqing Yuan and 1 other authors
View PDF
HTML (experimental)
Abstract:Dark matter constraint repositories are critical community infrastructure, yet the most widely-used are volunteer-maintained, a sustainability risk as results accelerate. Limits are typically published as figures rather than machine-readable records, compounding the burden. We present a large language model (LLM) pipeline that monitors arXiv, extracts limit curves, integrates them as code, and opens pull requests for human review. On a 329-paper benchmark of measured limits graded against the upstream-curated repository, it identifies the coupling type for 98.1% of gradable papers. The 81% yielding a comparable extraction reach a median residual of 0.17 dex from a single model read, and 51% of all papers land within a factor of two of the curator's curve. The LLM is confined to perception; arithmetic, unit conversion, and the guards that reject mis-extractions are deterministic, testable code. Deployed, the pipeline has generated limit proposals, but none have merged: governance of AI-generated scientific data is itself unsolved.
Subjects:
High Energy Physics - Experiment (hep-ex); Instrumentation and Methods for Astrophysics (astro-ph.IM); High Energy Physics - Phenomenology (hep-ph)
Cite as:
arXiv:2606.21658 [hep-ex]
(or
arXiv:2606.21658v2 [hep-ex] for this version)
https://doi.org/10.48550/arXiv.2606.21658
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Lanqing Yuan [view email]
[v1]
Fri, 19 Jun 2026 18:01:38 UTC (95 KB)
[v2]
Wed, 9 Sep 2026 16:46:26 UTC (1,101 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Towards LLM-Powered Automation of a Dark Matter Constraint Repository, by Lanqing Yuan and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
hep-ex
new
|
recent
| 2026-06
Change to browse by:
astro-ph
astro-ph.IM
hep-ph
References & Citations
INSPIRE HEP
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?)