30 papers
DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
Yuyang Gong, Miaokun Chen, Jiawei Liu +5
Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new security risks from poisoned retri…
Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition
Rujing Yao, Yufei Shi, Yang Wu +5
Cloud-hosted Large Language Models (LLMs) offer unmatched reasoning capabilities and dynamic knowledge, yet submitting raw queries to these external services risks exposing sensiti…
"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations
Yang Wu, Jinhong Yu, Jingwei Xiong +2
The integration of Large Language Models (LLMs) into scientific workflows presents exciting opportunities to accelerate biomedical discovery. However, the reactive nature of LLMs,…
Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning
Xiaotian Zhou, Di Tang, Xiaofeng Wang +1
Large Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorr…
PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering
Yiqing Zhang, Xiaozhong Liu, Fabricio Murai
Trustworthy biomedical question answering (QA) systems must not only provide accurate answers but also justify them with current, verifiable evidence. Retrieval-augmented approache…
P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering
Wenlin Zhong, Chengyuan Liu, Yiquan Wu +5
While reinforcement learning with verifiable rewards (RLVR) has advanced LLM reasoning in structured domains like mathematics and programming, its application to general-domain rea…