CIDER Dataset: Personalized Privacy Preference Alignment
tianshi_li · x · 2026-08-26
Introduces CIDER, a dataset designed to align Large Language Models (LLMs) with personalized human privacy preferences. It contains 14,850 annotations from 169 users across 60 interpersonal communication scenarios.
Key Findings:
- With just 6 historical examples, in-context personalization improves prediction accuracy by up to 11.41 percentage points.
- Larger models like GPT-5.4 and Claude Sonnet 4.6 are better at leveraging semantic context to understand user-specific preferences.
- Smaller models tend to rely on structured heuristics based on disclosure granularity and identifiability.
More from Safety
- ASML CFO says US Match Act restricting DUV sales to China would backfire — pstAsiatech · 2026-10-15
- Rumor: New Anthropic model imminent, apparently behind a batch of high-severity Chrome CVEs — matthew_d_green · 2026-10-15
- Fully-automated combat drones are already on the battlefield, warns Toby Walsh — TobyWalsh · 2026-10-15
- Pope's AI adviser warns Australia's copyright changes risk a new form of colonialism — TobyWalsh · 2026-10-15
- Jamie Dimon Warns of AI Agent Risks to Bank Accounts; JPMorgan Blocks Outside Agents — AccBalanced · 2026-10-15
- 'A lot of you are into alignment faking': meme nod to Anthropic's alignment faking paper — dejavucoder · 2026-10-15