30 秒でわかる
A speaker describes research that uses formats found in language-model training data to improve prompt accuracy. He offers a tentative explanation and an example of an unfamiliar separator.
- 1Use familiar formatsThe speaker cites prompt-mining work that found accuracy improvements from formats common in training data.
- 2A possible explanationHe speculates that familiar formats may make the task easier for the model.
- 3Avoid unusual separatorsAn unusual question-and-answer layout may be unfamiliar to the model.
ポイント
- The speaker cites prompt-mining work that found accuracy improvements from formats common in training data.
- He speculates that familiar formats may make the task easier for the model.
- An unusual question-and-answer layout may be unfamiliar to the model.
チャプターごとに整えた全文を読む
Mining common formats
The speaker cites prompt-mining work that found accuracy improvements from formats common in training data.
When choosing an exemplar format for a prompt, I suggest using a common format. I describe a prompt-mining paper in which researchers looked through a language model’s training corpus for common ways of asking and answering questions, then used those formats in prompts and improved accuracy.
A possible explanation
He speculates that familiar formats may make the task easier for the model. An unusual question-and-answer layout may be unfamiliar to the model.
I suspect the explanation may resemble the benefit of a smoother loss function during optimization: the space of questions may be smoother when the model has encountered the format before. That is my interpretation, not a proven mechanism in this clip.
For example, if I separate a question and answer with an unusual run of equal signs, the model probably has not seen that exact format often and may be more confused about what to do.
同じチャンネルの記事
1:49:40EN
Cognitive Revolution "How AI Changes Everything"· 2026年10月28日ポッドキャスト · 4 人A Strategy for Preserving Options on the Path to Advanced AIゲスト Joel Predd, Ben Boudreaux, Matt Chessen · ホスト Nathan LabenzRAND researchers discuss uncertainty, security architecture and human agency with Nathan Labenz.
1:28:36ENCognitive Revolution "How AI Changes Everything"· 2026年10月24日ポッドキャスト · 5 人AI’s Pace: Interpretability, GPU Credit and the Physical Supply Chainゲスト Zvi Mowshowitz, Evan Conrad, Lonis Hamaili · ホスト Nathan Labenz, Prakash NarayananA weekly highlights episode weighs uncertain AI research trajectories against finance, infrastructure, security and regulation.
3:13:44ENCognitive Revolution "How AI Changes Everything"· 2026年10月22日ポッドキャスト · 4 人AI’s Physical Bottlenecks: Compute Markets, Chip Investments and Agent Trustゲスト Evan Conrad, Lonis Hamaili · ホスト Nathan Labenz, Prakash NarayananA full AI:AM discussion of security incidents, GPU financing, semiconductor supply and an agent-to-agent network.
2:40:58ENCognitive Revolution "How AI Changes Everything"· 2026年10月21日ポッドキャスト · 3 人Frontier AI, Interpretability and the Fight Over Its Paceゲスト Zvi Mowshowitz · ホスト Nathan Labenz, Prakash NarayananZvi Mowshowitz joins AI:AM to discuss neural networks, policy and the institutions facing rapid change.
1:25:56ENCognitive Revolution "How AI Changes Everything"· 2026年10月17日ポッドキャストClaude Changed the Password. The Steering Wheel Was Already Optionalホスト Nathan LabenzNathan Labenz and Prakash Narayanan spend a week on agents that can lock you out, models that dodge a feeling they deny having, and formal proofs that found Linux bugs.
2:51:22ENCognitive Revolution "How AI Changes Everything"· 2026年10月14日ポッドキャスト · 4 人AI Minds and 8 mm Memories: Research, Archives and Simulationゲスト Cameron Berg, Phil Maher · ホスト Nathan Labenz, Prakash NarayananCameron Berg discusses hidden model states; Phil Maher explains preserving home movies and a fly-brain demo.