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

Amirreza Esmaeili; Fatemeh Fard

cs.CLApr 30, 2026

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

Authors: Amirreza Esmaeili, Fatemeh Fard

Organizations: University of British Columbia Kelowna, British Columbia, Canada

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.

Explore similar work

Probabilistic Attribution For Large Language Models
May 20, 2026Shilpika Shilpika, Carlo Graziani, Bethany Lusch +2Token-Level Uncertainty Instability
Code Is More Than Text: Uncertainty Estimation for Code Generation
Jun 8, 2026Yuling Shi, Caiqi Zhang, Yuexian Li +4Code Generation Large Language Model Uncertainty
AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation
Jul 24, 2026Jie "JW" WuCode Generation Large Language

May 20, 2026 · cs.CLJ/K move · Enter open · S save

Probabilistic Attribution For Large Language Models

Shilpika Shilpika, Carlo Graziani, Bethany Lusch, Venkatram Vishwanath+1

Argonne Leadership Computing Facility Argonne National Laboratory Lemont, IL, USA · Mathematics and Computer Science Division Argonne National Laboratory Lemont, IL, USA · Department of Computer Science University of Illinois Chicago Chicago, IL, USA

The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the previous tokens. These probabilities encode the distributional structure that the model learns in training and exploits in inference. In this work, we use these probabilities to situate LLMs within the mathematical theory of stochastic processes. We use this framework to design a model-agnostic probabilistic token attribution measure, using Bayes rule to invert the next-token log-probabilities so as to capture the models internal representation of the distribution over token sequences. The representation is independent of the models computational structure. This representation yields the conditional probability of the response given the prompt, and of the response given the prompt with a token marginalized away. Our attribution score is the log of the ratio of these probabilities. We further compute the entropies of a single prompts token distributions, conditioned on the remaining context. The interplay between entropy and attribution score sheds light on LLM behavior. We evaluate 8 models across 7 prompts and investigate anomalies, token sensitivity, response stability, model stability, and training convergence, thereby improving interpretability and guiding users to focus on uncertain or unstable parts of the generation.

Token-Level Uncertainty Instability

Open paper Ask about it PDF

Abstract

Explore similar work

Probabilistic Attribution For Large Language Models

Code Is More Than Text: Uncertainty Estimation for Code Generation

AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation