Automatic Pair Construction for Contrastive Post-training

Canwen Xu, Corby Rosset, Ethan Chau, Luciano Corro, Shweti Mahajan, Julian McAuley, Jennifer Neville, Ahmed Awadallah, Nikhil Rao


Abstract
Alignment serves as an important step to steer large language models (LLMs) towards human preferences. In this paper, we propose an automatic way to construct contrastive data for LLM, using preference pairs from multiple models of varying strengths (e.g., InstructGPT, ChatGPT and GPT-4). We compare the contrastive techniques of SLiC and DPO to SFT baselines and find that DPO provides a step-function improvement even after continuing SFT saturates. We also explore a data curriculum learning scheme for contrastive post-training, which starts by learning from “easier” pairs and transitioning to “harder” ones, which further improves alignment. Finally, we scale up our experiments to train with more data and larger models like Orca. Remarkably, our automatic contrastive post-training further improves the performance of Orca, already a state-of-the-art instruction learning model tuned with GPT-4 outputs, to outperform ChatGPT.
Anthology ID:
2024.findings-naacl.11
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
149–162
Language:
URL:
https://aclanthology.org/2024.findings-naacl.11
DOI:
Bibkey:
Cite (ACL):
Canwen Xu, Corby Rosset, Ethan Chau, Luciano Corro, Shweti Mahajan, Julian McAuley, Jennifer Neville, Ahmed Awadallah, and Nikhil Rao. 2024. Automatic Pair Construction for Contrastive Post-training. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 149–162, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Automatic Pair Construction for Contrastive Post-training (Xu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.11.pdf
Copyright:
 2024.findings-naacl.11.copyright.pdf