Learn Before
Consider a system that solves a complex problem (p_0) by breaking it down into a series of sub-problems and their answers ({p_≤n, a_≤n}). According to the final answer synthesis formula, a_0 = S_0(p_0, {p_≤n, a_≤n}), the synthesis function S_0 could still produce a correct and complete final answer (a_0) if it were only provided with the set of sub-problem answers (a_≤n).
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
A system is designed to solve a complex problem (
p_0) by first breaking it down into a series ofnsub-problems (p_1top_n) and finding their respective answers (a_1toa_n). The final answer to the original problem (a_0) is then generated in a concluding synthesis step, represented by the functiona_0 = S_0(p_0, {p_<=n, a_<=n}). Based on this formula, which of the following sets of information is required by the synthesis functionS_0to produce the final answera_0?Diagnosing a Faulty Summarization System
Consider a system that solves a complex problem (
p_0) by breaking it down into a series of sub-problems and their answers ({p_≤n, a_≤n}). According to the final answer synthesis formula,a_0 = S_0(p_0, {p_≤n, a_≤n}), the synthesis functionS_0could still produce a correct and complete final answer (a_0) if it were only provided with the set of sub-problem answers (a_≤n).