https://github.com/frankaging/dancing-in-chains

Code and data for "Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models"
https://github.com/frankaging/dancing-in-chains

Last synced: 4 months ago
JSON representation

Code and data for "Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models"

• Host: GitHub
• URL: https://github.com/frankaging/dancing-in-chains
• Owner: frankaging
• License: apache-2.0
• Created: 2024-07-30T07:31:35.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-31T20:05:11.000Z (almost 2 years ago)
• Last Synced: 2025-11-21T22:02:55.000Z (7 months ago)
• Size: 8.79 KB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models

Code and data for "Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models"[^1][^2] are **coming soon**!

[^1]: Work done at AWS AI Labs during the summer of 2023.

[^2]: Results are largely based on some of the best open-source models back in 2023. We might, and we welcome the community to, validate our findings with much newer models. Offline, similar results are obtained for Llama-2 as well as Falcon models.