Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model

ArXi:2604.06176v1 Announce Type: cross We present an empirical study of embedding-based retrieval under realistic conversational settings, where queries are short, dialogue-like, and weakly specified, and retrieval corpora contain structured conversational artifacts. Focusing on Qwen3-embedding models, we identify a deployment-relevant robustness vulnerability: under conversational retrieval without query prompting, structured dialogue-style noise can become disproportionately retrievable and intrude into top-ranked results, despite being semantically uninformative.