12 citations · 12 across the 5 of their papers we have counts for
6 papers
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…
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…
FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data
Deren Lei, Yaxi Li, Siyao Li +6
Prior research on training grounded factuality classification models to detect hallucinations in large language models (LLMs) has relied on public natural language inference (NLI)…
InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance
Rui Xu, Mengya Hu, Deren Lei +6
The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-…
SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection
Mengya Hu, Rui Xu, Deren Lei +5
Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we…
Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations
Deren Lei, Yaxi Li, Mengya Hu +4
Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in dev…