FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection
- 类型：arxiv
- 标识：2609.18766
- 链接：https://arxiv.org/abs/2609.18766
- 主分类：multimodal
- 形态：application
- TLDR：Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence. Their deployment, however, requires predictions to follow a predefined label space and a structured decision protocol consisting of service-scenario identification, fraud detection, and conditional fraud-type classification. Existing fine-tuning and prompt-based approaches typically encode task knowledge, constraints, and decision rules into model parameters or manually maintained prompts, making them difficult to adapt as fraud patterns and labeling
- 副分类：engineering
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-21-agent-rag-longcontext-candidates.json