Question Answering On Webquestions

评估指标

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
CoA	70.7	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
CoA w/o actions	64.7	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
DSP	59.4	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
DSP	59.4	DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
FiE+PAQ	56.3	FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering	-
FiE	52.4	FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering	-
FiDO	51.1	FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference	-
RAG	45.2	Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Few-shot	44.7	Language Models are Few-Shot Learners
Few-shot	44.7	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
PaLM-540B (Few-Shot)	43.5	PaLM: Scaling Language Modeling with Pathways
Zero-shot	43	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
Zero-shot	43	Language Models are Unsupervised Multitask Learners	-
T5.1.1-XXL+SSM	42.8	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
CoT	42.5	Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
CoT	42.5	Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
DPR	42.4	Dense Passage Retrieval for Open-Domain Question Answering
GPT-3-175B (Few-Shot)	41.5	Language Models are Few-Shot Learners
REALM	40.7	REALM: Retrieval-Augmented Language Model Pre-Training
React	38.3	ReAct: Synergizing Reasoning and Acting in Language Models

0 of 37 row(s) selected.