7 papers
ASSERT: A Measurement Pipeline for GenAI Audits
Riccardo Fogliato, Abhinav Palia, Xiawei Wang +11
Audits of generative AI (GenAI) systems often summarize behavior as a reported rate: how often the audited system complies with policy. Researchers and stakeholders use that rate t…
Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting
Mengya Hu, Susie Park, Suzana Ilic +5
Content-moderation classifiers are usually evaluated in isolation, but deployment requires choosing where to intervene and what follows a flag. We evaluate these choices using two…
AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models
Tanmay Gautam, Alireza Bahramali, Sandeep Atluri
Automated red-teaming methods for large language models typically optimize attack prompts within a fixed, human-designed strategy, leaving the attack strategy itself unchanged. We…
From Prompt Risk to Response Risk: Paired Analysis of Safety Behavior of Large Language Models
Mengya Hu, Qiong Wei, Sandeep Atluri
Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide…
PLAtE: A Large-scale Dataset for List Page Web Extraction
Aidan San, Yuan Zhuang, Jan Bakus +6
Recently, neural models have been leveraged to significantly improve the performance of information extraction from semi-structured websites. However, a barrier for continued progr…
Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning
Li Zhou, Kevin Small, Yong Zhang +1
Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, su…
Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization
Markus Dreyer, Mengwen Liu, Feng Nan +2
Neural models for abstractive summarization tend to generate output that is fluent and well-formed but lacks semantic faithfulness, or factuality, with respect to the input documen…