FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection
Summary
FRAUDSkill is a structured frozen-weight adaptation framework for audio anti-fraud detection that optimizes external skill programs without modifying the underlying audio-language model, achieving higher accuracy and reduced invalid outputs.
View Cached Full Text
Cached at: 09/21/26, 07:19 AM
Paper page - FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection
Source: https://huggingface.co/papers/2609.18766 Authors:
,
,
,
,
,
,
,
,
,
Abstract
Largeaudio-languagemodelshaveshownpromiseforanti-frauddetectionbydirectlyprocessingspeechandreasoningoverfraud-relatedevidence.Theirdeployment,however,requirespredictionstofollowapredefinedlabelspaceandastructureddecisionprotocolconsistingofservice-scenarioidentification,frauddetection,andconditionalfraud-typeclassification.Existingfine-tuningandprompt-basedapproachestypicallyencodetaskknowledge,constraints,anddecisionrulesintomodelparametersormanuallymaintainedprompts,makingthemdifficulttoadaptasfraudpatternsandlabelingpoliciesevolve.Tothisend,weproposeFRAUDSkill,astructuredfrozen-weightadaptationframeworkthatleavestheunderlyingaudio-languagemodelunchangedwhileoptimizinganexternallayerofskillprograms,route-specificpolicies,anddecisionrules.Wefurthercombinestructuredoutputcontrolwithvalidation-guidedmulti-pathinferencetoensureprotocol-compliantpredictions.OntheTeleAntiFraudbenchmark,FRAUDSkillachieves73.50%Macro-F1,outperformingthesharedfrozen-modelbaselineby31.96%whilereducinginvalidoutputsto1.94%.Extensiveexperimentsdemonstratethatexternalskilloptimizationprovidesaneffectiveandadaptablesolutionforstructuredaudioanti-frauddetectionwithoutmodifyingtheunderlyingmodel.Thesourcecodeisavailableathttps://anonymous.4open.science/r/FRAUDSKILL-114514.
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2609\.18766
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.18766 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.18766 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.18766 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing
SkillAudit introduces a framework for evolving LLM agent skills without ground-truth feedback by using paired trajectory auditing and contrastive evaluation. It achieves 73.9% average task reward across 89 tasks, outperforming baseline methods.
@Yif_Yang: Introducing SkillOpt — an optimizer for agent skills. Instead of finetuning model weights, we treat a natural-language …
Introducing SkillOpt, an optimizer that treats natural-language skills as trainable external parameters instead of finetuning model weights. It uses bounded edits and validation gating to enable stable, controllable skill updates, achieving best or tied-best results across 52 settings on 6 benchmarks with 7 models.
MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills
This paper introduces MedSkillAudit, a domain-specific framework for auditing the safety and quality of medical research AI agent skills before deployment. The study demonstrates that the system achieves reliable assessment consistency comparable to or better than human expert review.
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
LatentSkill converts textual skills into LoRA adapters stored in weight space, reducing context overhead while maintaining modularity and composability for LLM agents, achieving significant improvements on ALFWorld and Search-QA benchmarks.
Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing
Skill-RAG is a failure-aware RAG framework that uses hidden-state probing and skill routing to diagnose and correct query-evidence misalignment in retrieval-augmented generation. The approach detects retrieval failures and selectively applies targeted skills (query rewriting, question decomposition, evidence focusing) to improve accuracy on hard cases and out-of-distribution datasets.