Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning
This addresses efficiency issues in LLM/MLLM reasoning for AI practitioners, though it is incremental as it builds on existing reasoning methods.
The paper tackles the problem of excessive chain-of-thought reasoning impairing LLM/MLLM performance and efficiency, proposing CAR to dynamically switch between short answers and long-form reasoning based on perplexity, which outperforms both approaches across benchmarks.
Recent advancements in reasoning have significantly enhanced the capabilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) across diverse tasks. However, excessive reliance on chain-of-thought (CoT) reasoning can impair model performance and brings unnecessarily lengthened outputs, reducing efficiency. Our work reveals that prolonged reasoning does not universally improve accuracy and even degrade performance on simpler tasks. To address this, we propose Certainty-based Adaptive Reasoning (CAR), a novel framework that dynamically switches between short answers and long-form reasoning based on the model perplexity. CAR first generates a short answer and evaluates its perplexity, triggering reasoning only when the model exhibits low confidence (i.e., high perplexity). Experiments across diverse multimodal VQA/KIE benchmarks and text reasoning datasets show that CAR outperforms both short-answer and long-form reasoning approaches, striking an optimal balance between accuracy and efficiency.