paper-with-me

Papers

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

2026-04-30 · Amirreza Esmaeili, Fatemeh Fard arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.01235

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Analyzing Latent Concepts in Code Language Models

2025-10-01 · Arushi Sharma, Vedant Pungliya, Christopher J. Quinn, Ali Jannesari arxiv

Interpreting the internal behavior of large language models trained on code remains a critical challenge, particularly for applications demanding trust, transparency, and semantic robustness. We propose Code Concept Anal…

Contrastive Token-level Explanations for Graph-based Rumour Detection

2025-02-05 · Daniel Wai Kit Chin, Roy Ka-Wei Lee

The widespread use of social media has accelerated the dissemination of information, but it has also facilitated the spread of harmful rumours, which can disrupt economies, influence political outcomes, and exacerbate pu…

Graph Neural NetworkRumour Detection

Challenges and Opportunities in Text Generation Explainability

2024-05-14 · Kenza Amara, Rita Sevastjanova, Mennatallah El-Assady

The necessity for interpretability in natural language processing (NLP) has risen alongside the growing prominence of large language models. Among the myriad tasks within NLP, text generation stands out as a primary obje…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Text Generation

Knowledge-Prompted Estimator: A Novel Approach to Explainable Machine Translation Assessment

2023-06-13 · Hao Yang, Min Zhang, Shimin Tao, Minghan Wang 외

Cross-lingual Machine Translation (MT) quality estimation plays a crucial role in evaluating translation performance. GEMBA, the first MT quality assessment metric based on Large Language Models (LLMs), employs one-step …

Machine TranslationSentenceTranslation

Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey

2024-12-03 · Yunkai Dang, Kaichen Huang, Jiahao Huo, Yibo Yan 외

The rapid development of Artificial Intelligence (AI) has revolutionized numerous fields, with large language models (LLMs) and computer vision (CV) systems driving advancements in natural language understanding and visu…

Cross-Modal RetrievalNatural Language UnderstandingQuestion AnsweringSurvey+2