Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Language Models Show Conformity Bias in RAG: When the Majority Endorses a Poisoned Claim
Mehrdad Ghassabi, Audrina Ebrahimi, Zahra Zojaji +1
Retrieval-augmented generation (RAG) can expose language models to misleading evidence in retrieved documents. We investigate whether increasing the number of mutually agreeing poi…
cs.CL2026
Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language Models
Mehrdad Ghassabi, Pedram Rostami, Hamidreza Baradaran Kashani +2
Hallucination detection is particularly important for medical language models, but repeated-sampling approaches are computationally expensive. A faster alternative is a single-pass…
cs.CL2026
Gaokerena: A Small Persian Medical Language Model Family
Mehrdad Ghassabi, Hamidreza Baradaran Kashani, Pedram Rostami +5
Persian medical natural language processing remains limited by the scarcity of domain-specific resources and insufficient public characterization of their coverage and quality. We…