9 papers
Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
Wenda Wei, Yu-An Liu, Ruqing Zhang +6
Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step…
LLMs as Sparse Retrievers:A Framework for First-Stage Product Search
Hongru Song, Yu-an Liu, Ruqing Zhang +6
Product search is a crucial component of modern e-commerce platforms, with billions of user queries every day. In product search systems, first-stage retrieval should achieve high…
A Generative Framework for Personalized Sticker Retrieval
Changjiang Zhou, Ruqing Zhang, Jiafeng Guo +4
Formulating information retrieval as a variant of generative modeling, specifically using autoregressive models to generate relevant identifiers for a given query, has recently att…
On the Scaling of Robustness and Effectiveness in Dense Retrieval
Yu-An Liu, Ruqing Zhang, Jiafeng Guo +3
Robustness and Effectiveness are critical aspects of developing dense retrieval models for real-world applications. It is known that there is a trade-off between the two. Recent wo…
The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems
Hongru Song, Yu-an Liu, Ruqing Zhang +4
We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities. We focus on generating human-imperceptible adversarial exampl…
Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems
Hongru Song, Yu-an Liu, Ruqing Zhang +2
Retrieval-augmented generation (RAG) systems can effectively mitigate the hallucination problem of large language models (LLMs),but they also possess inherent vulnerabilities. Iden…