DoLa
by voidism · GitHub
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
# factuality# hallucinations# large-language-models
⭐ Stars
557
🍴 Forks
68
🔥 Trending
+1 today
📜 License
—
License not specified📅 Created
2023
🔄 Last commit
10 days ago
🏷️ Category
factuality
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-22
📄 About
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
❓ Frequently asked questions
What is DoLa?
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
Is DoLa open source?
DoLa is an open-source project.
Is DoLa free?
Yes. DoLa is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/voidism-dola.html)
🧬 Related projects
WikiChat
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving…
★ 1.6k · chatbot
long-form-factuality
Benchmarking long-form factuality in large language models. Original code for our paper "Long-f…
★ 692 · benchmark
hallucination-leaderboard
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Docume…
★ 3.3k · generative-ai