Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection

2025/06/26 by Fan Li, Fan, Li, Peng Wang +5
Computer Science · Engineering · #Advanced Memory and Neural Computing #Autoregressive model #Computational complexity theory #Computational model #FOS: Computer and information sciences #FOS: Electrical engineering #Information Theory (cs.IT) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Quantum-Dot Cellular Automata #Signal Processing (eess.SP) #Software deployment #Transformer #Wireless #Wireless Signal Modulation Classification #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.21093

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/06/26 · openalex created_date 2025/10/15 · openalex updated_date 2026/08/05

Abstract

Transformers have shown potential in solving wireless communication problems, particularly via in-context learning (ICL), where models adapt to new tasks through prompts without requiring model updates. However, prior ICL-based Transformer models rely on deep architectures with many layers to achieve satisfactory performance, resulting in substantial storage and computational costs. In this work, we propose CHain Of thOught Symbol dEtection (CHOOSE), a CoT-enhanced shallow Transformer framework for wireless symbol detection. By introducing autoregressive latent reasoning steps within the hidden space, CHOOSE significantly improves the reasoning capacity of shallow models (1-2 layers) without increasing model depth. This design enables lightweight Transformers to achieve detection performance comparable to much deeper models, making them well-suited for deployment on resource-constrained mobile devices. Experimental results demonstrate that our approach outperforms conventional shallow Transformers and achieves performance comparable to that of deep Transformers, while maintaining storage and computational efficiency. This represents a promising direction for implementing Transformer-based algorithms in wireless receivers with limited computational resources.

Citations

• Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought
• Reasoning Beyond Words ? Exploring framework for hidden state reasoning
• From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
• Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
• In-Context Learning for MIMO Equalization Using Transformer-Based Sequence Models
• Transformers are Provably Optimal In-context Estimators for Wireless Communications
• Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection
• What Can Transformers Learn In-Context? A Case Study of Simple Function Classes
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Language Models are Few-Shot Learners
• Attention Is All You Need
• Designing Security-Aware Incentives for Computation Offloading via Device-to-Device Communication
• Transformer-based Wireless Symbol Detection Over Fading Channels
• The Expressive Power of Transformers with Chain of Thought

Related

• Transformer-based Wireless Symbol Detection Over Fading Channels
• Decision Feedback In-Context Symbol Detection over Block-Fading Channels
• Transformers are Provably Optimal In-context Estimators for Wireless Communications
• Leveraging Large Language Models for Wireless Symbol Detection via In-Context Learning
• Unveiling the Power of Complex-Valued Transformers in Wireless Communications