BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 8811-8826
Abstract
Sizhe Wang, Yongqi Tong, Hengyuan Zhang, Dawei Li, Xin Zhang, Tianlong Chen. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks2025
- "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models2024
- Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment2024
- Tree-Instruct: A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment2024
- SimPO: Simple Preference Optimization with a Reference-Free Reward2024
- DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature2024
- Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model2024
- Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning2024
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena2023