Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Local Spatiotemporal Convolutional Network for Robust Gait Recognition
LSTCN is a dual-branch CNN that extracts temporal gait features by pooling spatial data into strips and applying local spatiotemporal convolutions with asymmetric kernels.
-
DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning
DAIN reframes multimodal fusion as dynamic agent collaboration with sparse activation, claiming SOTA results including 2.6% accuracy gain on ADNI across five benchmarks.
-
Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
SAME-Net adds a differentiable soft attention mask embedding module to achieve rectification-free end-to-end scene text spotting with 84.02% H-mean on Total-Text.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX accelerates Tree-of-Thought LLM reasoning 1.2-3x via speculative path selection, dynamic budget allocation across queries, and adaptive early termination, with up to 4.1x when combined with token speculative decoding.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX delivers 1.2-3x speedup on ToT algorithms via speculative path selection, dynamic budget allocation, and adaptive early termination, reaching up to 4.1x when combined with token-level speculative decoding.
-
ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators
ProWAFT proposes a workload-aware dynamic fault-tolerance method for FPGA CNN accelerators via selective TMR and partial reconfiguration, reporting lower composite cost than static TMR or reactive approaches on ResNet...
-
Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction
A multilevel perceptual CRF model using Swin Transformer, HPF fusion, HA adapters, and dynamic scaling attention achieves state-of-the-art monocular depth estimation on NYU Depth v2, KITTI, and MatterPort3D with reduc...
-
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
A survey that taxonomizes efficiency methods for LVLMs across the full inference pipeline, decouples the problem into information density, long-context attention, and memory limits, and outlines four future research f...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.