Back to Arena
HippoRAG 2
by OSU NLP Group
System Card
OrganizationOSU NLP Group
Released2025-02
Architecturegraph-rag / Extended PPR with deeper passage integration
DetailsBuilds on HippoRAG's Personalized PageRank algorithm with deeper passage integration and more effective online LLM use. Positions RAG as a non-parametric continual learning mechanism outperforming standard RAG on factual, sense-making, and associative memory tasks.
Parameters—
Domainrag-retrievalknowledge-graphlifelong-learning
Open SourceYes
PaperView Paper
CodeRepository
icml-2025continual-learningkgassociative-memory
Capability Profile
Benchmark Scores
6 of 14 benchmarksLong-Context Retrieval0/5
RULER
no dataNIAH
no dataLooGLE
no dataLongBench
no data∞Bench
no dataMulti-Turn Recall1/2
MemoryBank
no dataCross-Session Memory1/1
Multi-Hop QA3/3
Agent Task Memory0/1
AgentBench-Mem
no dataPersonalization0/1
PerLTQA
no dataFactuality / Grounding1/1
Sources:arXiv:2502.14802 Table 2 — F1 with Llama-3.3-70B-Instruct backboneHippoRAG 2 paper (arXiv:2502.14802); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)HippoRAG 2 paper (arXiv:2502.14802); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)HippoRAG 2 paper (arXiv:2502.14802); evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)HippoRAG 2 paper (arXiv:2502.14802); evaluated on BABILong: Testing the Limits of LLMs with Long-Context Reasoning-in-a-Haystack (AIRI, 2406)HippoRAG 2 paper (arXiv:2502.14802); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)