作者位次 #8/11ACL 2026Poster· Natural Language Processing
SAFE - QAQ : End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning
Peidong Wang · Zhiming Ma · Xin Dai · Yongkang Liu · Shi Feng · Xiaocui Yang · Wenxing Hu · Zhihao Wang · Mingjun Pan · Li Yuan · Daling Wang
摘要
Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive strategies. To address these challenges, we first propose SAFE-...