読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニュースクイックテイク1 分で読めるDisconfirmAI 編集部

Interpretability tools get a new exam, with hallucination rates now scored

Researchers built and open-sourced WorkspaceBench to test activation-reading tools; it is a self-built benchmark, and independent adoption remains to be seen.

2026-09-23 14:58 GMT+8

Interpretability researchers have released and open-sourced WorkspaceBench, a benchmark testing whether activation-to-text tools can actually read a model's global workspace.

The benchmark has 3,356 questions across 27 eval families covering safety, logical reasoning and multihop computation, plus a dedicated hallucination eval, because J-lens is reliable but single-token while NLAs are expressive yet prone to confabulation.

It was built for Qwen-3.6-27B, and the authors admit it does not fully rule out shortcuts that infer intermediates from the prompt. This is a self-built, self-assessed benchmark; whether the field adopts it remains an open question.

ソース

  • lesswrong.com↗
リサーチを続ける →
ログイン / 新規登録
読書リサーチレーダー投資フレームワーク