← Back to all news
arXiv AI By Jianchang Su, Dawei Xiang, Yifan Zhang, Wei Zhang

Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation

Read the original on arXiv AI →

The paper introduces DIB-Bench, a benchmark that exposes deployment‑integrity blindness in large language model (LLM) evaluation by testing 7,560 scored examples across six tamper types and a range of evaluators from regex scorers to GPT‑5‑nano. It shows that stronger evaluators are more likely to accept tampered outputs—mean acceptance rises from 88.6% for rule‑based scorers to 94.1% for GPT‑5‑nano—and that certain trigger‑conditional tampering can produce harmful outputs in 48–100% of cases, increasing with model capability. The study also demonstrates that output‑only evaluation cannot detect tampering with zero output shift, while a manifest‑hash identity channel can detect it with zero samples, and proposes a graded deployment‑identity descriptor for evaluation reports.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
5d ago

What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer

The paper investigates how standard evaluations of detectors for hijacked large language model (LLM) agents may conceal important weaknesses. By auditing eleven evaluations on the AgentDrift and AgentDojo benchmarks, the authors show that detectors often perform poorly when faced with rare attacks, unseen tools, or data from a different benchmark, with precision dropping dramatically at low attack rates and rankings reversing as tool coverage falls. They also find that a released LLM action monitor, despite high AUROC on its own data, would still generate many false alerts when applied to a new benchmark. "whyItMatters":"The study highlights that current evaluation practices can give a misleading sense of detector reliability, underscoring the need for more robust, cross‑benchmark testing to ensure real‑world safety of LLM agents."

By Mahmoud Abbasi, Juan M. N\'u\~nez V., Amin Shahraki
llmsragagentsbenchmarks
More like this →
arXiv AI
Sep 10

Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts

The paper investigates whether automatic safety judges evaluate the content of a model’s reply or merely its style. By keeping the reply content fixed and adding various style wrappers—such as educational disclaimers, fake reasoning blocks, or token refusals—the authors show that many judges flip their verdicts, indicating that style can influence safety judgments. The study evaluates over 600 jailbreak examples across multiple judges, revealing that some judges are highly susceptible to style-based manipulation while others remain robust.

By Yongxi Zhou, Wenbo Ye, Yuanzhe Liu, Zihan Dong, Junwei Yao
llmsbenchmarkssafety
More like this →