← Back to all news
arXiv AI

Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models

The paper introduces Dynamic Boundary Evaluation (DBE), a method that moves beyond static benchmarks by locating the per‑prompt pass probability near 0.5 for large language models. DBE provides a calibrated item bank with difficulty labels, a Skill‑Guided Boundary Search algorithm that works with API‑level access, and an adaptive evaluation protocol that places new models on a unified ability scale. The approach is applied to safety, capability, and truthfulness tasks, expanding coverage without saturation and remaining compatible with existing datasets.

Related stories

arXiv AI
Aug 19

Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models

The paper investigates whether existing AI safety benchmarks, designed for large language models, are suitable for evaluating small language models (SLMs). By testing five benchmark suites on 26 open‑source SLMs with a unified scoring rubric, the authors find that ambiguous judgments dominate, especially for complex prompts and certain architectures. This ambiguity, linked to factors like lexical density and output perplexity, undermines the reliability of aggregate leaderboards and reveals a confound between model capability and perceived safety.

By Nyamtulla Shaik, Fengjun Li, Bo Luo
llmsbenchmarkssafety
More like this →
arXiv Machine Learning
Aug 11

When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs

arXiv:2608. 08542v1 Announce Type: new Abstract: Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math, code, or domain specialists into a safety-aligned base using task arithmetic, TIES, or DARE.

By Yu Ma, Hongli Shi, Jing Li, Xinran Xu, Weiwei Hou
llmsbenchmarkssafety
More like this →
arXiv AI
Jun 26

Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models

arXiv:2606. 26101v1 Announce Type: cross Abstract: Reliable evaluation of large language models should separate supported answering from unsupported guessing without conflating either with data contamination, prompt idiosyncrasy, or generic refusal behavior.

By Renwei Meng, Bowen Zhang, Jian Wang, Xican Wang, Haoyi Wu, Xuanyan Qiu, Shengan Yang
llmsbenchmarks
More like this →
arXiv Machine Learning
Jun 25

RAS: Measuring LLM Safety Through Refusal Alignment

arXiv:2606. 25750v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety policy.

By Chang-Chieh Huang, Yan-Lun Chen, Chia-Mu Yu, Wei-Bin Lee
llmssafety
More like this →
arXiv Computation and Language
Aug 27

Lower-Resource, Higher Scores: Language Bias in LLM Evaluators

The paper demonstrates that large language model (LLM) evaluators, whether reward‑model based or prompted LLM‑as‑a‑Judge, exhibit significant language bias in multilingual settings. Experiments with semantically identical instruction‑response pairs across 23 languages reveal that lower‑resource languages receive higher scores, a bias that persists across eight open‑weight evaluators and is not detectable by standard pairwise accuracy metrics. The authors link the bias to model uncertainty and language identity, showing it cannot be explained by content difficulty alone.

By Ej Zhou, Lucas Resck, Zheng Hui, Anna Korhonen
llmssafety
More like this →
arXiv Computation and Language
Sep 16

Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion

The paper introduces the SAST-IR framework to evaluate large language models’ robustness against persuasion attacks in a memory‑less setting, revealing a flaw called "Refusal Inertia" that masks true vulnerability. Using the CP‑Agent and a custom CounterFact‑Strict dataset, the authors demonstrate that simple, diverse attack strategies achieve a 96% success rate, while complex attacks often trigger defensive compliance. The study highlights severe brittleness in current state‑of‑the‑art models when deprived of conversation history.

By Zhuoang Cai
llmsagentsbenchmarkssafety
More like this →