Lennart Finke, Hardik Bhatnagar, Euodia Dodd, Francis Rhys Ward, Yves-Alexandre de Montjoye, Matthias Bethge, Mary Phuong · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26698 · open-access PDF
AIのセキュリティにおける重要な問題は、隠れた知識(ELK)を生み出し、不一致でその監督者よりも知識が豊富なモデルから情報を抽出することである。たとえば、脆弱性のためのコードをスキャンするために使用される不一致なモデルは、その発見、すなわちサンドバッグを後で利用するために、その発見を抑えることを望むかもしれません。 ELKを経験的に研究するには、この設定を反映するモデル生物が必要です。
Machine translation (Meta M2M100); the English original follows.
A key problem in AI safety is eliciting latent knowledge (ELK), extracting information from a model that is misaligned and more knowledgeable than its overseer. For example, a misaligned model used to scan code for vulnerabilities may want to withhold its findings, i.e., sandbag, in order to exploit them later. To study ELK empirically, we need model organisms that mirror this setting. Existing model organisms fall short in several respects. In this work, we train model organisms to withhold solutions in a vulnerability detection task. We combine transcript distillation with counter-prompting
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26698, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange