List: Graph and LLM | Curated by Mirco Milletarì Ph.D.

Feb 2, 2025
166 stories
1 save
Graph and LLM
Shaw Talebi
Fine-Tuning Text Embeddings For Domain-Specific SearchAn overview with Python code
Jan 24
4
Jan 24
4
In
Generative AI
by
Kaushik Rajan
COCONUT: Redefining Reasoning in Large Language ModelsRevolutionizing reasoning in large language models through latent space.
Dec 17, 2024
8
Dec 17, 2024
8
In
Causality in Data Science
by
Kenneth Styppa
Introducing Causal Feature LearningCausal Feature Learning Pt. 1
Oct 22, 2024
1
Oct 22, 2024
1
SACHIN KUMAR
KV Cache compression with Inter-Layer Attention Similarity for efficient Long-Context LLM InferenceFor longer context LLM Inference, existing methods, including selective token retention and window-based attention, improve efficiency but…
Dec 4, 2024
Dec 4, 2024
SACHIN KUMAR
MCT Self-Refine algorithm : integrating LLMs with Monte Carlo Tree Search for complex mathematical…LLMs faces challenges in accuracy and reliability in strategic and mathematical reasoning. For addressing it, authors of this paper[1]…
Jun 17, 2024
Jun 17, 2024
Ozgur Guler
The Missing Piece in Graph RAG: Graph Attention NetworksHow Enhanced Contextual Relevance with GNN’s can improve GraphRAG
Nov 21, 2024
3
Nov 21, 2024
3
In
TDS Archive
by
Benjamin Wang
Monte Carlo Tree Search: An IntroductionMCTS is the cornerstone of AlphaGo and many AI applications. We aim to build some intuitions and along the way get our hands dirty.
Jan 10, 2021
2
Jan 10, 2021
2
In
TDS Archive
by
Giuseppe Futia
Ontology Reasoning in Knowledge GraphsA Python hands-on guide to understanding the principles of generating new knowledge by following logical processes
Nov 15, 2024
5
Nov 15, 2024
5
In
TDS Archive
by
Tomaz Bratanic
Building Knowledge Graphs with LLM Graph TransformerA deep dive into LangChain’s implementation of graph construction with LLMs
Nov 5, 2024
14
Nov 5, 2024
14
Pierre Lienhart
LLM Inference Series: 1. IntroductionIn this post, I introduce the outline of this deep dive series about the specifics and challenges of hosting LLMs for inference.
Dec 22, 2023
1
Dec 22, 2023
1
SACHIN KUMAR
vAttention: Dynamic KV-cache Memory Management for Serving LLMs without PagedAttentionEfficient GPU memory usage is essential for high throughput LLM inference. Prior systems reserved memory for the KV-cache ahead-of-time…
May 9, 2024
3
May 9, 2024
3
In
TDS Archive
by
Elahe Aghapour
Beyond Attention: How Advanced Positional Embedding Methods Improve upon the Original TransformersFrom Sinusoidal to RoPE and ALiBi: How advanced positional encodings overcome limitations in Transformers
Oct 29, 2024
1
Oct 29, 2024
1
In
TDS Archive
by
Benjamin Bodner
PyTorch Optimizers Aren’t Fast Enough. Try These InsteadThese 4 advanced optimizers will open your mind.
Oct 14, 2024
9
Oct 14, 2024
9
Emergent Methods
Outperforming Claude 3.5 Sonnet with Phi-3-mini-4k for graph entity relationship extraction tasksWhen you need fast and high-throughput graph extraction with better quality than Claude 3.5 Sonnet.
Aug 15, 2024
4
Aug 15, 2024
4
In
Neo4j Developer Blog
by
Tomaz Bratanic
Entity Linking and Relationship Extraction With Relik in LlamaIndexBuild a knowledge graph without an LLM for your RAG applications
Aug 12, 2024
7
Aug 12, 2024
7
In
Neo4j Developer Blog
by
Tomaz Bratanic
Build a Knowledge Graph-based Agent With Llama 3.1, NVIDIA NIM, and LangChainFunction-calling capabilities retrieve structured data from a knowledge graph to power your RAG apps
Aug 3, 2024
1
Aug 3, 2024
1
In
MantisNLP
by
Juan Martinez
Finetuning an LLM: RLHF and alternatives (Part I)Introduction
Aug 16, 2023
Aug 16, 2023
Amandeep Singh
How make async calls to OpenAI’s API.A guide to make asynchronous calls to OpenAI API with rate limiting.
Feb 25, 2024
1
Feb 25, 2024
1
Jeong Yitae
Today, I’d like to discuss the evaluation methods for GraphRAG.Additionally, there are evaluation methods where LLMs serve as the evaluators, including single point, reference-based, and pairwise-based…
Jul 3, 2024
1
Jul 3, 2024
1
In
Palantir Blog
by
Palantir
Industry AIHow Palantir AIP Enables the Unified Namespace
Jun 27, 2024
2
Jun 27, 2024
2