{"data":{"id":"9c27181f-9943-433a-b1d9-80161c065955","title":"Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods","summary":"Researchers study gender bias in audio-enabled large language models (AuLLMs), which infer attributes such as gender from speech cues. They apply adversarial training to unlearn gender perception without losing performance on other benchmarked tasks, and then distil the gender-agnostic model into a student that perceives gender but responds similarly to the teacher unless explicitly asked. The methods are tested on three AuLLMs, with satisfactory unlearning results and partially satisfactory distillation results.","solution":"Adversarial unlearning of gender perception in the AuLLM, followed by distillation from the gender-agnostic model into a student model that perceives gender but responds similarly to the teacher unless explicitly asked.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.21763v1","publishedAt":"2026-10-15T12:19:47.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["audio-enabled LLMs (AuLLMs)"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-15T12:19:47.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}