Tailoring Self-Rationalizers with Multi-Reward Distillation

Sahana Ramnath, Brihi Joshi, Skyler Hallinan, Ximing Lu, Liunian Harold Li +4 more
2/12/2026

No official code found. Best implementation: INK-USC/RationaleMultiRewardDistillation (6 stars, last commit 2024-06-21).

Semantic Scholar

Code Implementations(1)

INK-USC/RationaleMultiRewardDistillationCommunity59%

Code and Dataset for preprint titled "Tailoring Self-Rationalizers with Multi-Reward Distillation"

62PythonNov 1, 20232 years ago

Cite this paper

@article{ramnath2026tailoring,
  title  = {Tailoring Self-Rationalizers with Multi-Reward Distillation},
  author = {Sahana Ramnath and Brihi Joshi and Skyler Hallinan and Ximing Lu and Liunian Harold Li and Aaron Chan and Jack Hessel and Yejin Choi and Xiang Ren},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:da3657410a97cde3ebaea4d0378d80e182367f22},
  journal = {ICLR 2024 2024}
}

Discussion