AICLMar 5, 2024

CURATRON: Complete and Robust Preference Data for Rigorous Alignment of Large Language Models

arXiv:2403.02745v327 citationsh-index: 15DASH
AI Analysis

This work contributes to more reliable and ethically aligned AI models by improving dataset curation for LLM alignment, though it is incremental as it builds on existing models like Bradley-Terry-Luce.

The paper tackles the problem of aligning large language models with human values via preference learning by addressing incomplete and corrupted data in preference datasets, proposing a novel method that recovers an ε-optimal ranking with high probability and handles adversarial noise and unobserved comparisons effectively.

This paper addresses the challenges of aligning large language models (LLMs) with human values via preference learning (PL), focusing on incomplete and corrupted data in preference datasets. We propose a novel method for robustly and completely recalibrating values within these datasets to enhance LLMs' resilience against the issues. In particular, we devise a guaranteed polynomial time ranking algorithm that robustifies several existing models, such as the classic Bradley-Terry-Luce (BTL) (Bradley and Terry, 1952) model and certain generalizations of it. To the best of our knowledge, our present work is the first to propose an algorithm that provably recovers an $ε$-optimal ranking with high probability while allowing as large as $O(n)$ perturbed pairwise comparison results per model response. Furthermore, we show robust recovery results in the partially observed setting. Our experiments confirm that our algorithms handle adversarial noise and unobserved comparisons well in both general and LLM preference dataset settings. This work contributes to the development and scaling of more reliable and ethically aligned AI models by equipping the dataset curation pipeline with the ability to handle missing and maliciously manipulated inputs.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes