AI News HubLIVE
Original source2 min read

Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations

This paper challenges the assumption that setting LLM-as-judge temperature to 0 ensures deterministic grading, showing flips occur due to default temperature and residual non-reproducibility even under greedy decoding.

SourcearXiv Machine LearningAuthor: Hiroki Tamba

[2606.26185] Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations

[Submitted on 24 Jun 2026]

Title:Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations

View a PDF of the paper titled Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations, by Hiroki Tamba

View PDF HTML (experimental)

Abstract:LLM-as-judge ("grader") components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream deployment decisions. A widespread assumption is that setting the grader's sampling temperature to 0 makes grading deterministic. We test this assumption against a real safety-evaluation codebase (Japan AISI's open-source aisev) and show it fails on two levels. First, the harness invokes its grader without setting temperature or seed; the underlying provider silently applies its default of 1.0, so items near the decision boundary flip pass/fail across identical runs (per-item disagreement up to ~50% over 20 runs). Second, pinning temperature=0 reduces but does not eliminate flips: across 690 API calls spanning two providers, three model tiers, and five sampling configurations, 1-2 of 7 borderline items remain non-reproducible even under forced greedy decoding (top_k=1). Claude Opus 4.7/4.8 has since deprecated temperature entirely, rendering the primary mitigation inapplicable to newer model generations. These findings expose a structural gap: evaluation harnesses that report single-run verdicts without variance or grader-disagreement metrics can present noise as a safety property. We release a reproduction harness (690 calls, 7 conditions) and recommend that harnesses treat grader disagreement as a first-class health metric alongside the scores themselves.

Comments: 7 pages, 2 tables

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2606.26185 [cs.LG]

(or arXiv:2606.26185v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.26185

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hiroki Tamba [view email] [v1] Wed, 24 Jun 2026 13:24:40 UTC (11 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations, by Hiroki Tamba

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs

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?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

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?)