Runpeng Geng
Source-listed: Informatics Ph.D. Student · The Pennsylvania State University (Penn State)
- Language models
- Information retrieval
- Evaluation
Selected work
5- PIArena: A Platform for Prompt Injection EvaluationFirst author · 2026
- PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt SanitizationFirst author · 2026
- PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language ModelsFirst author · 2025
- TracLLM: A Generic Framework for Attributing Long Context LLMsContributor · 2025
- Formalizing and Benchmarking Prompt Injection Attacks and DefensesContributor · 2024