Hugging Face's logo
Yang Lee's picture
17 86 23

Yang Lee

innovation64
tinywell's profile picture chenglu's profile picture fuadam1982's profile picture
Ā·
https://innovation64.github.io/

AI & ML interests

AGI

Recent Activity

upvoted a paper 3 days ago
ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation
upvoted a paper 3 days ago
Diverse Inference and Verification for Advanced Reasoning
reacted to mmhamdy's post with šŸ‘€ 10 days ago
ā›“ Evaluating Long Context #2: SCROLLS and ZeroSCROLLS In this series of posts about tracing the history of long context evaluation, we started with Long Range Arena (LRA). Introduced in 2020, Long Range Arens (LRA) is one of the earliest benchmarks designed to tackle the challenge of long context evaluation. But it wasn't introduced to evaluate LLMs, but rather the transformer architecture in general. šŸ“œ The SCROLLS benchmark, introduced in 2022, addresses this gap in NLP/LLM research. SCROLLS challenges models with tasks that require reasoning over extended sequences (according to 2022 standards). So, what does it offer? 1ļøāƒ£ Long Text Focus: SCROLLS (unlike LRA) focus mainly on text and contain inputs with thousands of words, testing models' ability to synthesize information across lengthy documents. 2ļøāƒ£ Diverse Tasks: Includes summarization, question answering, and natural language inference across domains like literature, science, and business. 3ļøāƒ£ Unified Format: All datasets are available in a text-to-text format, facilitating easy evaluation and comparison of models. Building on SCROLLS, ZeroSCROLLS takes long text evaluation to the next level by focusing on zero-shot learning. Other features include: 1ļøāƒ£ New Tasks: Introduces tasks like sentiment aggregation and sorting book chapter summaries. 2ļøāƒ£ Leaderboard: A live leaderboard encourages continuous improvement and competition among researchers. šŸ’” What are some other landmark benchmarks in the history of long context evaluation? Feel free to share your thoughts and suggestions in the comments. - SCROLLS Paper: https://huggingface.co/papers/2201.03533 - ZeroSCROLLS Paper: https://huggingface.co/papers/2305.14196
View all activity

Organizations

Gradio-Blocks-Party's profile picture The Waifu Research Department's profile picture Blog-explorers's profile picture That Time I got Reincarnated as a Hugging Face Organization's profile picture ZeroGPU Explorers's profile picture Chinese LLMs on Hugging Face's profile picture Apocalypse-AGI-DAO's profile picture

Collections 2

papaer selecting
RAG
RAG research

Papers 1

datasets

None public yet