Podbean logo
  • Discover
  • Podcast Features

    Your all-in-one podcasting solution.

    Podcast Studio

    Easy-to-use audio recorder app.

  • Livestream

    High-performing audio live, without limits.

  • Podcast App

    The best podcast player & podcast app.

  • Ads Marketplace

    Join Ads Marketplace to earn money
    through sponsorship on your podcast.

    PodAds

    Manage your ads with dynamic ad insertion capability.

  • Patron & Paid Content

    The seamless way for fans to support you directly
    from your podcast.

  •  
  • All Arts Business Comedy Education
  • Fiction Government Health & Fitness History Kids & Family
  • Leisure Music News Religion & Spirituality Science
  • Society & Culture Sports Technology True Crime TV & Film
  • Live
  • Log in
  • Start your podcast for free
  • Podcasting
    • Podcast Features
    • Live Stream
    • PodAds
    • Podcast App
    • Podcast Studio
  • Monetization
    • Premium
    • Patron
    • Ads Marketplace
  • Enterprise
  • Pricing
  • Discover
  • Log in
    Sign up free
Papers Read on AI

Papers Read on AI

News:Tech News

Fine-Tuning Language Models from Human Preferences

Fine-Tuning Language Models from Human Preferences

2023-03-01
Download
Reward learning enables the application of reinforcement learning (RL) to tasks where reward is defined by human judgment, building a model of reward by asking humans questions. Most work on reward learning has used simulated environments, but complex information about values is often expressed in natural language, and we believe reward learning for language is a key to making RL practical and safe for real-world tasks. In this paper, we build on advances in generative pretraining of language models to apply reward learning to four natural language tasks: continuing text with positive sentiment or physically descriptive language, and summarization tasks on the TL;DR and CNN/Daily Mail datasets. For stylistic continuation we achieve good results with only 5,000 comparisons evaluated by humans. For summarization, models trained with 60,000 comparisons copy whole sentences from the input but skip irrelevant preamble; this leads to reasonable ROUGE scores and very good performance according to our human labelers, but may be exploiting the fact that labelers rely on simple heuristics. 2019: Daniel M. Ziegler, Nisan Stiennon, Jeff Wu, Tom B. Brown, Alec Radford, Dario Amodei, Paul Christiano, Geoffrey Irving https://arxiv.org/pdf/1909.08593v2.pdf
view more

More Episodes

Sparks of Artificial General Intelligence: Early experiments with GPT-4
2023-03-31 33
X-Risk Analysis for AI Research
2023-03-30 33
Zero-1-to-3: Zero-shot One Image to 3D Object
2023-03-29 36
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
2023-03-27 48
Zero-Shot Information Extraction via Chatting with ChatGPT
2023-03-24 64
Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
2023-03-23 54
Self-Instruct: Aligning Language Model with Self Generated Instructions
2023-03-22 67
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
2023-03-21 51
GPT-4 Technical Report
2023-03-20 85
Prismer: A Vision-Language Model with An Ensemble of Experts
2023-03-14 72
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
2023-03-13 46
LLaMA: Open and Efficient Foundation Language Models
2023-03-10 79
Dropout Reduces Underfitting
2023-03-09 48
Cross-domain Compositing with Pretrained Diffusion Models
2023-03-04 59
REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers
2023-03-03 57
Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey
2023-03-02 83
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
2023-02-28 52
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
2023-02-24 44
Mastering Diverse Domains through World Models
2023-02-23 59
  • ←
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • →
0123456789101112131415171819

Get this podcast on your
phone, FREE

Download Podbean app on App Store Download Podbean app on Google Play

Create your
podcast in
minutes

  • Full-featured podcast site
  • Unlimited storage and bandwidth
  • Comprehensive podcast stats
  • Integrate with iTunes and Google
    store
  • Make money with your podcast
Get started

It is Free

  • Podcast Services

    • Podcast Features
    • Pricing
    • Enterprise Solution
    • Private Podcast
    • The Podcast App
    • Live Stream
    • Audio Recorder
    • Remote Recording
  •  
    • Create a Podcast
    • Video Podcast
    • Start Podcasting
    • Start Radio Talk Show
    • Education Podcast
    • Church Podcast
    • Nonprofit Podcast
    • Get Sermons Online
    • Free Audiobooks
  • MONETIZATION & MORE

    • Podcast Advertising
    • Dynamic Ads Insertion
    • Patron Program
    • Affiliate Program
    • Switch to Podbean
    • Submit Your Podcast
    • Podbean Plugins
    • Developers
    • Badges
  • KNOWLEDGE BASE

    • How to Start a Podcast
    • How to Start a Live Podcast
    • How to Monetize a podcast
    • How to Promote Your Podcast
    • How to Use Group Recording
  • Support

    • Support Center
    • Podbean Blog
    • What’s New
    • Free Webinars
    • Podcast Events
    • Podbean Academy
    • Podcasting Smarter
    • Resources
  • Podbean

    • About Us
    • Careers
    • Press and Media
    • Terms of Use
    • Privacy Policy
    • Contact Us

Copyright © 2006-2023 Podbean.com