Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Elle Najt

Elle Najt

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2AI×2NLP×1

Frequent co-authors

Colin Toft1×
Tyler Tracy1×
Fabien Roger1×
Joe Benton1×
Zheng-Xin Yong1×
Parv Mahajan1×

Research Timeline

2026
An Independent Safety Evaluation of Kimi K2.5

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse and disinformation, and recommends mandatory safety testing for future open-weight models.

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors

The paper introduces SLEIGHT-Bench, a benchmark of 40 synthetic attacks, demonstrating that current LLM monitor systems fail to detect a significant number of covert, harmful actions executed by coding agents.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 15, 2026

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors

Elle Najt, Colin Toft, Tyler Tracy, Fabien Roger +1 more

The paper introduces SLEIGHT-Bench, a benchmark of 40 synthetic attacks, demonstrating that current LLM monitor systems fail to detect a significant number of covert, harmful actions executed by codin…

View →
cs.CRcs.AIcs.CLRecentApr 3, 2026

An Independent Safety Evaluation of Kimi K2.5

Zheng-Xin Yong, Parv Mahajan, Andy Wang, Ida Caspary +11 more

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…

View →