pith. sign in

In: Proceedings of the 11th international conference on World Wide Web (WWW)

Taher H · 2002 · arXiv 1446.511513

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it
read on arXiv browse 3 citing papers

citation-role summary

method 1

citation-polarity summary

use method 1

fields

cs.CL 1 cs.IR 1 cs.LG 1

years

2026 1 2025 1 2024 1

verdicts

UNVERDICTED 3

roles

method 1

polarities

use method 1

representative citing papers

From RAG to Memory: Non-Parametric Continual Learning for Large Language Models

cs.CL · 2025-02-20 · unverdicted · novelty 6.0

HippoRAG 2 improves on standard RAG and prior HippoRAG by adding deeper passage integration and more effective LLM use in Personalized PageRank, delivering superior performance on factual, sense-making, and associative memory tasks including a 7% gain in associative memory over state-of-the-art.

citing papers explorer

Showing 3 of 3 citing papers.

  • MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation cs.IR · 2026-04-04 · unverdicted · none · ref 27

    MG²-RAG proposes a multi-granularity graph RAG framework that constructs hierarchical multimodal nodes via entity-driven visual grounding and performs structured retrieval, delivering SOTA results on four multimodal tasks with 43.3× faster graph construction.

  • From RAG to Memory: Non-Parametric Continual Learning for Large Language Models cs.CL · 2025-02-20 · unverdicted · none · ref 2

    HippoRAG 2 improves on standard RAG and prior HippoRAG by adding deeper passage integration and more effective LLM use in Personalized PageRank, delivering superior performance on factual, sense-making, and associative memory tasks including a 7% gain in associative memory over state-of-the-art.

  • Explaining Graph Neural Networks for Node Similarity on Graphs cs.LG · 2024-07-10 · unverdicted · none · ref 25

    Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.