Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×2

Frequent co-authors

Krishnapriya Vishnubhotla2×
Soumya Vajjala2×
Akriti Vij2×

Research Timeline

2026
LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories

The paper evaluates the inconsistency of using LLMs as automated judges for multi-dimensional safety evaluations, finding that LLMs are unreliable for nuanced safety issues like financial advice but more reliable for overt harmful content.

LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories

The paper evaluates the inconsistency of using LLMs as automated judges for multi-dimensional safety evaluations, finding that LLMs are unreliable for nuanced safety issues like financial advice but more reliable for overt harmful content.

Highlighted terms show continued research focus across papers

Papers