SYNAPSE: Neuro-Symbolic Visual Thought-to-Text Decoding via Topological Semantic Denoising

2026-05-26

AI Summary

This work addresses the semantic instability and hallucination issues of existing EEG-to-text decoding systems under biological noise by introducing, for the first time, a neuro-symbolic approach through a lightweight inference-time framework. The proposed method integrates an EEG encoder, a frozen large language model, a commonsense knowledge graph, and latent intent exemplars to regularize text generation via graph-structured topological denoising and symbolic constraints—eliminating the need for fine-tuning while substantially enhancing semantic robustness. Designed for localized EEG processing to preserve biometric privacy, the framework consistently outperforms unconstrained prompting baselines across multiple benchmarks, demonstrates resilience to missing labels, and achieves performance comparable to resource-intensive fine-tuned systems.

Abstract

Recent advances in large language models have accelerated open-vocabulary EEG-to-imagined-text decoding, where non-invasive neural activity recorded during visual perception is translated into coherent natural language descriptions of viewed stimuli. However, existing systems remain highly vulnerable to biological noise, where corrupted neural projections induce hallucinated or semantically unstable generation in frozen language models. We introduce SYNAPSE (Symbolic Neural Alignment for Precise Semantic Extraction), a lightweight neuro-symbolic framework that stabilizes neural text generation through inference-time symbolic regularization. By purifying EEG-derived semantic candidates using commonsense graph structure and latent exemplars, SYNAPSE improves semantic stability without end-to-end LLM fine-tuning. Experiments across popular EEG decoding benchmarks and multiple frozen LLM backends demonstrate consistent gains over unconstrained prompting baselines, robustness under object-label ablation, and performance commensurate with substantially more resource-intensive fine-tuned systems, while preserving biometric privacy by localizing raw EEG processing entirely within the encoder stack.

Problem

• EEG-to-text decoding
• biological noise
• semantic instability
• neural decoding
• visual perception

Innovation

• neuro-symbolic
• semantic denoising
• EEG-to-text decoding
• symbolic regularization
• commonsense graph