Retrieval-Augmented Generation (RAG) exposes large language models to knowledge-poisoning attacks, where misinformation injected into retrieved documents can influence model outputs. Prior work has shown that models may detect contradictory evidence yet still allow it to influence their responses, revealing a gap betwe...
Mehrdad Ghassabi, Audrina Ebrahimi, Sadra Hakim et al.· 0 citations
Hallucination detection is particularly important for medical language models, but repeated-sampling approaches are computationally expensive. A faster alternative is a single-pass uncertainty head that predicts hallucination risk from a frozen generator's internal signals. Existing uncertainty heads consume backbone-s...
Retrieval-Augmented Generation (RAG) improves large language models by grounding them in external evidence, but this exposes them to knowledge-poisoning attacks, where misinformation injected into retrieved documents influences model outputs. We investigate whether deliberative reasoning reduces susceptibility to poiso...
Mehrdad Ghassabi, Audrina Ebrahimi, Sadra Hakim et al.· 0 citations
Retrieval-Augmented Generation (RAG) improves large language models by grounding them in external evidence, but this exposes them to knowledge-poisoning attacks, where misinformation injected into retrieved documents influences model outputs. We investigate whether deliberative reasoning reduces susceptibility to poiso...
Mehrdad Ghassabi, Audrina Ebrahimi, Sadra Hakim et al.· 0 citations
Gaokerena, a novel family of compact Persian medical language models optimized for deployment on consumer grade hardware, and Gaokerena-R, a novel family of compact Persian medical language models optimized for deployment on consumer grade hardware, are presented.
