Philip S. Yu

The paper introduces PromptFuzz-SC, a novel semantic-character dual-space mutation framework, demonstrating that combining both semantic and character-level attacks significantly improves the robustness evaluation of LLMs like DeepSeek against prompt injection.

SAMark introduces a self-anchored text watermarking framework that achieves high robustness (up to 90.2% TP@FP1%) against challenging paragraph-level paraphrasing attacks by establishing a step-independent green region in semantic space.

The paper advocates for integrating explicit contextual feedback (like reviews and comments) into LLM-based recommender systems to achieve more personalized, transparent, and semantically aligned recommendations.

The paper proposes MERIT, a dual-level, multi-horizon memory retrieval framework that significantly improves the performance of interactive text-to-SQL agents by providing both global and local memory guidance.