HyperAI超神经

首页资讯最新论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Question Answering On Strategyqa

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称	Accuracy	Paper Title	Repository
Rethinking with retrieval (GPT-3)	77.73	Rethinking with Retrieval: Faithful Large Language Model Inference	-
SearchChain	-	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models	-
PaLM 540B	76.4	Transcending Scaling Laws with 0.1% Extra Compute	-
Least-to-Most	-	Least-to-Most Prompting Enables Complex Reasoning in Large Language Models	-
Self-Evaluation Guided Decoding (Codex, CoT, single reasoning chain, 6-shot gen, 4-shot eval)	77.2	-	-
SearchChain	-	Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks	-
CoA w/o actions	-	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models	-
CoA	-	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models	-
Least-to-Most	-	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models	-
U-PaLM 540B	76.6	Transcending Scaling Laws with 0.1% Extra Compute	-
Minerva 540B	61.9	Transcending Scaling Laws with 0.1% Extra Compute	-
PaLM 2 (few-shot, CoT, SC)	90.4	PaLM 2 Technical Report	-

0 of 12 row(s) selected.