Self-Discover
Free while signed in. Answers cite the passages they came from.
Google's Self-Discover lets LLMs compose their own task-specific reasoning strategies from a small library of atomic reasoning modules, at dramatically lower inference cost than self-consistency.
Module library: Defines a small set of atomic reasoning operations (critical thinking, step-by-step analysis, decomposition, etc.) that the LLM can select and compose.
Self-discovery stage: Given a task, the LLM picks and orders relevant modules into a reasoning structure once, which is then reused across all instances of that task.
+32% over CoT on BBH: Boosts GPT-4 and PaLM 2 by up to 32% on BigBench-Hard compared to plain CoT prompting.
10-40x cheaper: Outperforms inference-intensive methods like CoT-Self-Consistency by 20%+ while using 10-40x fewer inference calls; discovered structures also transfer between large and small models.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack