2 7 9

Choi Jaehun

Ash-Hun

https://github.com/ash-hun

AI & ML interests

LLM, RAG, Agent, GenAI, Modeling for RAG

Recent Activity

reacted to singhsidhukuldeep's post with 🔥 about 2 months ago

Exciting breakthrough in LLM reasoning: Introducing "Thread of Thought" (ThoT) - a novel prompting strategy that revolutionizes how language models handle chaotic contexts! Unlike traditional approaches that struggle with complex, interleaved information, ThoT enables LLMs to methodically segment and analyze extended contexts with remarkable precision. Here's how it works: Technical Deep Dive: - ThoT employs a two-step prompting mechanism: 1. Initial Analysis: Uses a template combining chaotic context (X) and query (Q) with a trigger sentence that initiates systematic reasoning. 2. Conclusion Refinement: Leverages the organized thought sequence to extract definitive answers. Implementation Details: - Seamlessly integrates as a "plug-and-play" module with existing LLMs. - Requires no model retraining or fine-tuning. - Works with various prompting techniques and model architectures. Performance Highlights: - Outperformed traditional methods on PopQA and EntityQ datasets. - Achieved 57.4% accuracy with GPT-3.5-turbo (vs. 48.2% for Chain-of-Thought). - Demonstrated superior performance across model scales, from 7B to 70B parameters. Key Applications: - Retrieval-augmented generation. - Multi-turn conversation responses. - Complex reasoning tasks requiring information synthesis. What makes it special: ThoT mirrors human cognitive processes by breaking down complex information into manageable segments while maintaining logical continuity – a game-changer for handling information-dense contexts.

updated a dataset about 2 months ago

Ash-Hun/Translation_Prompt_Template

updated a collection about 2 months ago

Prompt for RAG

View all activity

Organizations

Ash-Hun's activity

upvoted a paper 3 months ago

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Paper • 2410.10814 • Published Oct 14, 2024 • 49

upvoted 2 collections 3 months ago

Model for RAG

Collection

This is the modeling dataset collection for each stage of Advanced RAG / Modular RAG. • 0 items • Updated Oct 11, 2024 • 1

Prompt for RAG

Collection

Prompt Template for RAG • 2 items • Updated Nov 20, 2024 • 1

upvoted an article 6 months ago

Article

MTEB: Massive Text Embedding Benchmark

Oct 19, 2022

• 57

upvoted an article 8 months ago

Article

Decoding GPT-4'o': In-Depth Exploration of Its Mechanisms and Creating Similar AI.

•

May 21, 2024

• 35

upvoted a collection 9 months ago

Agent

Collection

112 items • Updated Sep 9, 2024 • 21

upvoted a paper 11 months ago

DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows

Paper • 2402.10379 • Published Feb 16, 2024 • 30