AbnormalLemmings
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 3 months ago

Chain of Draft: Thinking Faster by Writing Less

arxiv.org

external-link
message-square
0
link
fedilink
1
external-link

Chain of Draft: Thinking Faster by Writing Less

arxiv.org

morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 3 months ago
message-square
0
link
fedilink
Large Language Models (LLMs) have demonstrated remarkable performance in solving complex reasoning tasks through mechanisms like Chain-of-Thought (CoT) prompting, which emphasizes verbose, step-by-step reasoning. However, humans typically employ a more efficient strategy: drafting concise intermediate thoughts that capture only essential information. In this work, we propose Chain of Draft (CoD), a novel paradigm inspired by human cognitive processes, where LLMs generate minimalistic yet informative intermediate reasoning outputs while solving tasks. By reducing verbosity and focusing on critical insights, CoD matches or surpasses CoT in accuracy while using as little as only 7.6% of the tokens, significantly reducing cost and latency across various reasoning tasks. Our code and data are available at https://github.com/sileix/chain-of-draft.
alert-triangle
You must log in or register to comment.

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !localllama@sh.itjust.works

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they’re still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 22 users / day
  • 122 users / week
  • 635 users / month
  • 781 users / 6 months
  • 1 local subscriber
  • 3.14K subscribers
  • 93 Posts
  • 330 Comments
  • Modlog
  • mods:
  • MonsterBug@sh.itjust.works
  • SmokeyDope@lemmy.world
  • SkySyrup@sh.itjust.works
  • pax@sh.itjust.works
  • noneabove1182@sh.itjust.works
  • UI: unknown version
  • BE: 0.19.11
  • Modlog
  • Legal
  • Instances
  • Docs
  • Code
  • join-lemmy.org