Stars
Improving Steering Vectors by Targeting Sparse Autoencoder Features
Representation Engineering: A Top-Down Approach to AI Transparency
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
[ICLR 2025] "GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation", Tao Feng, Yihang Sun, Jiaxuan You
User Profile-Based Long-Term Memory for AI Chatbot Applications.
Multilingual Document Layout Parsing in a Single Vision-Language Model
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
This is the code repository for the paper "RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systems", accepted to IEEE TVCG (PacificVis 2026)
Create a knowledge graph out of unstructed legal text - use said knowledge graph in a graph augmented retrieval augmented generation pipeline
Codebase for reproducing the experiments of the semantic uncertainty paper (paragraph-length experiments).
Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).
jim-plus / llm-abliteration
Forked from Orion-zhen/abliterationMake abliterated models with transformers, easy and fast
Cross-platform, customizable ML solutions for live and streaming media.
A high-performance topological machine learning toolbox in Python
CoDEx: A set of knowledge graph Completion Datasets Extracted from Wikidata and Wikipedia
A Python toolbox to compute topological metrics and statistics for Knowledge Graphs
Calculate structural properties of graphs and subgraphs based on node attributes.
PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals (EMNLP 2024)
Dynamic evolution agent system with multi-session memory for realistic seeker simulation in psychological counseling.
A Paper collection for LLM based Patient Simulators
A benchmark dataset designed to support the development and evaluation of large language models (LLMs) for conversational mental health assistance