English

TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models

Computation and Language 2026-04-30 v1 Artificial Intelligence Software Engineering

Abstract

Understanding how Large Language Models (LLMs) make token-level decisions during code generation remains a major challenge for both researchers and practitioners. While recent tools provide insights into model internals or generation outcomes, they often lack decoding-time signals, fine-grained uncertainty measures, and interactive mechanisms for exploring alternative generation paths. We present TokenScope, an interactive interpretability and analysis tool for decoder-based LLMs that exposes token-level metrics, attention patterns, and structural information during generation. TokenScope supports interactive token replacement, counterfactual branching, and code-aware aggregation via abstract syntax trees. By unifying decoding-time signals with structural program analysis, TokenScope enables systematic investigation of LLM behaviour during code generation.

Cite

@article{arxiv.2607.01235,
  title  = {TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models},
  author = {Amirreza Esmaeili and Fatemeh Fard},
  journal= {arXiv preprint arXiv:2607.01235},
  year   = {2026}
}