0

TODO: Enhancing LLM Alignment with Ternary Preferences

A new alignment algorithm, Tie-rank Oriented Direct Preference Optimization (TODO), improves preference modeling and LLM performance by incorporating ties into the Bradley-Terry ranking model.

Year
2024
Venue
arXiv 2024
Authors
4
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2411.02442v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Aligning large language models (LLMs) with human intent is critical for enhancing their performance across a variety of tasks. Standard alignment techniques, such as Direct Preference Optimization (DPO), often rely on the binary Bradley-Terry (BT) model, which can struggle to capture the complexities of human preferences -- particularly in the presence of noisy or inconsistent labels and frequent ties. To address these limitations, we introduce the Tie-rank Oriented Bradley-Terry model (TOBT), an extension of the BT model that explicitly incorporates ties, enabling more nuanced preference representation. Building on this, we propose Tie-rank Oriented Direct Preference Optimization (TODO), a novel alignment algorithm that leverages TOBT's ternary ranking system to improve preference alignment. In evaluations on Mistral-7B and Llama 3-8B models, TODO consistently outperforms DPO in modeling preferences across both in-distribution and out-of-distribution datasets. Additional assessments using MT Bench and benchmarks such as Piqa, ARC-c, and MMLU further demonstrate TODO's superior alignment performance. Notably, TODO also shows strong results in binary preference alignment, highlighting its versatility and potential for broader integration into LLM alignment. The implementation details can be found in https://github.com/XXares/TODO.

Authors

4