ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback
This work addresses the challenge of enhancing reasoning accuracy in AI models for multi-modal tasks, though it is incremental as it builds on existing RLHF and RLAIF methods.
The paper tackles the problem of improving multi-modal chain-of-thought reasoning in large multimodal models by proposing ARES, a two-stage algorithm that alternates reinforcement learning and supervised fine-tuning using diverse AI feedback, resulting in a 70% win rate against baselines and a 2.5% average increase in inference answer accuracy.
Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by aligning them with specific preferences. These methods primarily use ranking-based feedback for entire generations. With advanced AI models (Teacher), such as GPT-4 and Claude 3 Opus, we can request various types of detailed feedback that are expensive for humans to provide. We propose a two-stage algorithm ARES that Alternates REinforcement Learning (RL) and Supervised Fine-Tuning (SFT). First, we request the Teacher to score how much each sentence contributes to solving the problem in a Chain-of-Thought (CoT). This sentence-level feedback allows us to consider individual valuable segments, providing more granular rewards for the RL procedure. Second, we ask the Teacher to correct the wrong reasoning after the RL stage. The RL procedure requires massive efforts for hyperparameter tuning and often generates errors like repetitive words and incomplete sentences. With the correction feedback, we stabilize the RL fine-tuned model through SFT. We conduct experiments on multi-model dataset ScienceQA and A-OKVQA to demonstrate the effectiveness of our proposal. ARES rationale reasoning achieves around 70% win rate against baseline models judged by GPT-4o. Additionally, we observe that the improved rationale reasoning leads to a 2.5% increase in inference answer accuracy on average for the multi-modal datasets.