😀🤓😎 New Research Alert - NAACL 2024 (Big Five Personality Traits Collection)! 😎😉😤
📄 Title: PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits 💬

📝 Description: This research examines the ability of LLMs to express personality traits and finds that LLMs can generate content consistent with assigned personality profiles and that humans can recognize certain traits with up to 80% accuracy. However, accuracy drops significantly when annotators are aware that the content was generated by an AI.

👥 Authors: Hang Jiang et al.

📅 Conference: NAACL, June 16–21, 2024 | Mexico City, Mexico 🇲🇽

🔗 Paper: PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits (2305.02547)

📁 Repository: https://github.com/hjian42/PersonaLLM

🚀 Added to the Big Five Personality Traits Collection: DmitryRyumin/big-five-personality-traits-661fb545292ab3d12a5a4890

🔥🔝 See also OCEAN-AI - ElenaRyumina/OCEANAI (App, co-authored by @DmitryRyumin ) 😉

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🔍 Keywords: #PersonaLLM #OCEANAI #BigFive #PersonalityTraits #PersonalityAnalysis #Chatbots #LLMs #NAACL2024 #DeepLearning #Innovation

upvoted an article over 1 year ago

Article

quanto: a pytorch quantization toolkit

and 2 others •

Mar 18, 2024

• 42

reacted to akhaliq's post with 🔥 over 1 year ago

Post

3528

Phi-3 Technical Report

A Highly Capable Language Model Locally on Your Phone

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone (2404.14219)

We introduce phi-3-mini, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3.5 (e.g., phi-3-mini achieves 69% on MMLU and 8.38 on MT-bench), despite being small enough to be deployed on a phone. The innovation lies entirely in our dataset for training, a scaled-up version of the one used for phi-2, composed of heavily filtered web data and synthetic data. The model is also further aligned for robustness, safety, and chat format. We also provide some initial parameter-scaling results with a 7B and 14B models trained for 4.8T tokens, called phi-3-small and phi-3-medium, both significantly more capable than phi-3-mini (e.g., respectively 75% and 78% on MMLU, and 8.7 and 8.9 on MT-bench).

reacted to isidentical's post with 🔥 over 1 year ago

Post

2138

Happy to announce https://imgsys.org -- a sister project to Chatbot Arena by lmsys -- for comparing different text guided image generation models models. Try it natively on HuggingFace: https://huggingface.co/spaces/fal-ai/imgsys

1 reply

Nguyen Ngoc Hai

AI & ML interests

Recent Activity

Organizations

Dang's activity

Open-source DeepResearch – Freeing our search agents

FineWeb: decanting the web for the finest text data at scale

Let's talk about LLM evaluation

quanto: a pytorch quantization toolkit