Improving Large Vision and Language Models by Learning from a Panel of Peers
This addresses the scalability issue in model alignment for AI researchers and practitioners, though it is incremental as it builds on existing collaborative learning concepts.
The paper tackles the problem of costly and limited human-curated preference data for aligning Large Vision and Language Models by proposing a Panel-of-Peers learning framework, which improves average benchmark scores from 48% to 57% across fifteen benchmarks.
Traditional alignment methods for Large Vision and Language Models (LVLMs) primarily rely on human-curated preference data. Human-generated preference data is costly; machine-generated preference data is limited in quality; and self-supervised preference data often introduces hallucinations. To overcome these limitations, we propose a novel Panel-of-Peers learning framework inspired by collaborative learning among humans. This approach leverages a panel of LVLMs, each evaluating and learning from their collective outputs through an iterative self-improvement process. By simulating a peer review system, our models generate, assess, and refine outputs in response to a curated set of prompts, mimicking a classroom learning environment. We demonstrate that this methodology enhances model performance without requiring extensive human-labeled datasets. Our experiments show significant improvement across multiple benchmarks, demonstrating the potential of peer evaluations as a scalable alternative to self-supervised alignment. Notably, we show that Panel-of-Peers increases the average score on fifteen benchmarks from 48% to 57%