Can I read Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios on EtoBox?

Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios by Lin, Lei; Fu, Jiayi; Liu, Pengli; Li, Qingyang; Gong, Yan; Wan, Junchen; Zhang, Fuzheng; Wang, Zhongyuan; Zhang, Di; Gai, Kun is a scholarly article available to read on EtoBox.

What is Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios about?

Although chain-of-thought (CoT) prompting combined with language models has achieved encouraging results on complex reasoning tasks, the naive greedy decoding used in CoT prompting usually causes the repetitiveness and local optimality. To address this shortcoming, ensemble-optimization tries to obtain multiple reasoning paths to get the final answer assembly. However, current ensemble-optimization methods either simply employ rule-based post-processing such as \textit{self-consistency}, or train an additional model based on several task-related human annotations to select the best one among multiple reasoning paths, yet fail to generalize to realistic settings where the type of input questions is unknown or the answer format of reasoning paths is unknown. To avoid their limitations, we propose \textbf{Self-Agreement}, a generalizable ensemble-optimization method applying in almost all scenarios where the type of input questions and the answer format of reasoning paths may be known or unknown. Self-agreement firstly samples from language model's decoder to generate a \textit{diverse} set of reasoning paths, and subsequently prompts the language model \textit{one more time} to deter

Author

Lin, Lei; Fu, Jiayi; Liu, Pengli; Li, Qingyang; Gong, Yan; Wan, Junchen; Zhang, Fuzheng; Wang, Zhongyuan; Zhang, Di; Gai, Kun

Published

2023

Language

EN