notesum.ai

Published at December 9

SiReRAG: Indexing Similar and Related Information for Multihop Reasoning

cs.CL

Released Date: December 9, 2024

Authors: Nan Zhang¹, Prafulla Kumar Choubey², Alexander Fabbri², Gabriel Bernadett-Shapiro², Rui Zhang¹, Prasenjit Mitra¹, Caiming Xiong², Chien-Sheng Wu²

Aff.: ¹The Pennsylvania State University; ²Salesforce AI Research

Arxiv: http://arxiv.org/pdf/2412.06206v1

	MuSiQue		2Wiki		HotpotQA		Average
Model	EM	F1	EM	F1	EM	F1	EM	F1
HippoRAG (GPT-3.5-Turbo)	32.60	43.78	66.40	74.01	59.90	74.29	52.97	64.03
RAPTOR (GPT-3.5-Turbo)	35.30	47.47	54.90	61.20	58.10	72.48	49.43	60.38
GraphRAG (GPT-4o)	12.10	20.22	22.50	27.49	31.70	42.74	22.10	30.15
RAPTOR (GPT-4o)	36.40	49.09	53.80	61.45	58.00	73.08	49.40	61.21
SiReRAG (GPT-3.5-Turbo)	38.90	52.08	60.40	68.20	62.50	77.36	53.93	65.88
SiReRAG (GPT-4o)	40.50	53.08	59.60	67.94	61.70	76.48	53.93	65.83