Julian J. McAuley

Large Language Models (LLMs) are susceptible to indirect prompt injection attack, where the model inadvertently responds to instructions injected into the prompt context. This vulnerability stems from LLMs’ inability to distinguish between data and instructions within a prompt. We propose CachePr...

Feature engineering has long been central to recommender systems, yet effectively leveraging textual item features remains challenging. Recent advances in large language models (LLMs) have enabled their use as semantic encoders for recommendation, but their roles and behaviors in this setting are...

Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as hallucinated entities, mis-grounded relations, skipped step...

When answering subjective questions, an ideal LLM should surface diverse plausible perspectives rather than favoring a single viewpoint, a characteristic known as pluralism. Recent studies show that modern LLMs optimized through preference alignment systematically favor certain positions on subje...

In this paper, we present ZoRRO (Zero-Weight Personalized Recommender System), a zero-weight and training-free framework for personalized news recommendation designed for scalable real-world deployment. We show that ZoRRO outperforms strong neural baselines in offline ranking evaluations and deli...

Natural language information needs over symbolic music scores rarely reduce to a single-step lookup. Many queries require compositional Music Information Retrieval (MIR) that extracts multiple pieces of evidence from structured notation and aggregates them to answer the question. This setting rem...