Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Mind the Implicit Gap: Quantifying Attribute Inference Leakage in Privacy-Conscious Delegation

AbstractEven when explicit Personally Identifiable Information (PII) is removed from LLM queries, implicit contextual cues can still reveal sensitive user attributes. Yet current Privacy-Conscious Delegation frameworks overlook this threat entirely, and existing PII span-based evaluation metrics cannot address it. We address this gap on both fronts. First, we introduce Attribute Inference Leakage (AIL), a label-free metric that quantifies implicit privacy leakage through set-based semantic comparison of attributes inferred before and after sanitisation. Using AIL, we provide the first empirical evidence in Privacy-Conscious Delegation that even perfect PII removal eliminates only 18% of implicit leakage relative to direct delegation, leaking the vast majority of inferable attributes. Second, we propose GIST, a training-free approach for context-aware generalisation to protect both explicit and implicit privacy while preserving response quality. Experiments across six local models (1B to 8B parameters) show GIST consistently achieves a Pareto improvement over state-of-the-art PAPILLON on all three evaluation dimensions of quality, explicit and implicit leakage. GIST also consistently reduces implicit leakage below the explicit leakage lower bound (perfect PII removal), hence GIST addresses a privacy dimension that PII-centric methods cannot.

More from EMNLP 2026

All EMNLP 2026 papers →