Retrieval Enhanced Feedback via In-context Neural Error-book
By: Jongyeop Hyun, Bumsoo Kim
Potential Business Impact:
Teaches AI to learn from mistakes better.
Recent advancements in Large Language Models (LLMs) have significantly improved reasoning capabilities, with in-context learning (ICL) emerging as a key technique for adaptation without retraining. While previous works have focused on leveraging correct examples, recent research highlights the importance of learning from errors to enhance performance. However, existing methods lack a structured framework for analyzing and mitigating errors, particularly in Multimodal Large Language Models (MLLMs), where integrating visual and textual inputs adds complexity. To address this issue, we propose REFINE: Retrieval-Enhanced Feedback via In-context Neural Error-book, a teacher-student framework that systematically structures errors and provides targeted feedback. REFINE introduces three systematic queries to construct structured feedback -- Feed-Target, Feed-Check, and Feed-Path -- to enhance multimodal reasoning by prioritizing relevant visual information, diagnosing critical failure points, and formulating corrective actions. Unlike prior approaches that rely on redundant retrievals, REFINE optimizes structured feedback retrieval, improving inference efficiency, token usage, and scalability. Our results demonstrate substantial speedup, reduced computational costs, and successful generalization, highlighting REFINE's potential for enhancing multimodal reasoning.
Similar Papers
Retrieval Enhanced Feedback via In-context Neural Error-book
Machine Learning (CS)
Teaches AI to learn from mistakes better.
Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
Machine Learning (CS)
Lets AI learn from many computers without sharing data.
A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback
CV and Pattern Recognition
Improves image search by learning from results.