paper-with-me

Papers

WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models

2024-08-07 · Prannaya Gupta, Le Qi Yau, Hao Han Low, I-Shiang Lee, Hugo Maximus Lim, Yu Xin Teoh, Jia Hng Koh, Dar Win Liew, Rishabh Bhardwaj, Rajat Bhardwaj, Soujanya Poria

WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models (LLMs). It accommodates a diverse range of models, including both open-weight and API-based ones, and features over 35 safety benchmarks covering areas such as multilingual safety, exaggerated safety, and prompt injections. The framework supports both LLM and judge benchmarking and incorporates custom mutators to test safety against various text-style mutations, such as future tense and paraphrasing. Additionally, WalledEval introduces WalledGuard, a new, small, and performant content moderation tool, and two datasets: SGXSTest and HIXSTest, which serve as benchmarks for assessing the exaggerated safety of LLMs and judges in cultural contexts. We make WalledEval publicly available at https://github.com/walledai/walledeval.

📄 PDF Abstract BibTeX arXiv:2408.03837

Code (1)

walledai/walledeval 공식 구현 pytorch

Tasks

AI and SafetyBenchmarkingInstruction FollowingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

DeepSight: An All-in-One LM Safety Toolkit

2026-02-12 · Bo Zhang, Jiaxuan Guo, Lijun Li, Dongrui Liu 외 arxiv

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, a…

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement

2025-02-24 · Zhexin Zhang, Leqi Lei, Junxiao Yang, Xijie Huang 외

As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge. While substantial efforts have been made to evaluate and enhance AI safety…

Is Your VLM for Autonomous Driving Safety-Ready? A Comprehensive Benchmark for Evaluating External and In-Cabin Risks

2025-11-18 · Xianhui Meng, Yuchen Zhang, Zhijian Huang, Zheng Lu 외 arxiv

Vision-Language Models (VLMs) show great promise for autonomous driving, but their suitability for safety-critical scenarios is largely unexplored, raising safety concerns. This issue arises from the lack of comprehensiv…

Autonomous Driving

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models

2025-07-08 · Ann-Kathrin Dombrowski, Dillon Bowen, Adam Gleave, Chris Cundy arxiv

Open-weight large language models (LLMs) unlock huge benefits in innovation, personalization, privacy, and democratization. However, their core advantage - modifiability - opens the door to systemic risks: bad actors can…

VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models

2024-07-16 · Haodong Duan, Junming Yang, Yuxuan Qiao, Xinyu Fang 외

We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friendly and comprehensive framework for researchers and developers to evaluat…