本文にスキップ
AI News HubLIVE
サイト内リライト2 分で読了

翻訳待ち:Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline

記事の要約

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。ソース概要:arXiv:2609.30290v1 Announce Type: new Abstract: Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measured. When we checked ours, the deployed gpt-4o-mini judge agreed with two-author gold at only Cohen's kappa = 0.04 on a disagreement-enriched set and 0.42 on a uniform-random spot-check, over-flagging 77.1% of the human-FAITHFUL cases in the enriched set. Most of its over-flags trace back to a single mechanism we call GRADE-HALLUCINATION. A self-hosted Qwen3.6-27B replacement (kappa = 0.72) lands in the same range as Claude Opus 4.7 (kappa = 0.71); the head-to-head is underpowered at n = 96, but for the deployment decision that hardly matters, since Qwen costs roughly 1/300…

ソースarXiv Computational Linguistics著者: Haowei Liu, Hsin-Tai Wu, Yi Fang
翻訳待ち:Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline
誤りを報告

訂正窓口はまだ利用できません。記事情報をコピーして保存できます。

訂正案内
本文へ

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。

[Submitted on 9 Sep 2026] Title:Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline View a PDF of the paper titled Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline, by Haowei Liu and 2 other authors View PDF HTML (experimental) Abstract:Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measured. When we checked ours, the deployed gpt-4o-mini judge agreed with two-author gold at only Cohen's kappa = 0.04 on a disagreement-enriched set and 0.42 on a uniform-random spot-check, over-flagging 77.1% of the human-FAITHFUL cases in the enriched set. Most of its over-flags trace back to a single mechanism we call GRADE-HALLUCINATION. A self-hosted Qwen3.6-27B replacement (kappa = 0.72) lands in the same range as Claude Opus 4.7 (kappa = 0.71); the head-to-head is underpowered at n = 96, but for the deployment decision that hardly matters, since Qwen costs roughly 1/300 as much per call. Ensembling does not help for free. Pairing the weak judge with a stronger one degrades agreement, whereas three strong judges under unanimity routing reach kappa = 0.79 at 89.7% auto-coverage. Applied out-of-domain, the same audit recipe flags 25.5% of BIRD-financial's expert-authored gold SQLs as candidate gold-SQL issues under our annotation protocol. Code and pre-registration are at this https URL. Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2609.30290 [cs.CL] (or arXiv:2609.30290v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2609.30290 arXiv-issued DOI via DataCite Submission history From: Haowei Liu [view email] [v1] Wed, 9 Sep 2026 20:17:57 UTC (111 KB) Full-text links: Access Paper: View a PDF of the paper titled Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline, by Haowei Liu and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-09 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: 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?)

要点と分析を開く

記事インテリジェンス

エンジニア上級

要点

  • AI 生成が一時的に利用できないため、ソース内容とフォールバックメタデータを保存しました。
  • arXiv:2609.30290v1 Announce Type: new Abstract: Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measu…

要点と分析は自動生成され、誤りを含む場合があります。原典をご確認ください。