← Back ◬ AI & Machine Learning Aug 05, 2026

Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes

arXiv AI Archived Aug 05, 2026 ✓ Full text saved

arXiv:2608.02879v1 Announce Type: new Abstract: The widespread adoption of proprietary Large Language Models (LLMs) accessed strictly through closed APIs has created a critical challenge for responsible deployment: a fundamental lack of interpretability. To address this, we propose a model-agnostic, post-hoc attribution interpreter operating at the sentence level. Our approach trains an Energy-Based Model (EBM) as a surrogate to capture the LLM's internal conceptual consistency between prompts a

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Artificial Intelligence [Submitted on 3 Aug 2026] Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes Maryam Rezaee, Pooriya Safaei, Maryam Asgarinezhad, Fatemeh Seyyedsalehi The widespread adoption of proprietary Large Language Models (LLMs) accessed strictly through closed APIs has created a critical challenge for responsible deployment: a fundamental lack of interpretability. To address this, we propose a model-agnostic, post-hoc attribution interpreter operating at the sentence level. Our approach trains an Energy-Based Model (EBM) as a surrogate to capture the LLM's internal conceptual consistency between prompts and responses. This energy landscape guides the training of a lightweight interpreter network. Uniquely, our interpreter operates as a standalone tool; once trained, it quantifies the influence of prompt sentences on a user-specified target output without requiring further API queries to the LLM. By globally training a local interpreter across diverse inputs, our framework captures broader generation patterns and mitigates instance-specific biases. Experiments demonstrate that our EBM accurately simulates the target LLM, allowing the interpreter to effectively identify the prompt sentences most influential in generating specific target outputs. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2608.02879 [cs.AI] (or arXiv:2608.02879v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.02879 Focus to learn more Submission history From: Fatemeh Seyyedsalehi [view email] [v1] Mon, 3 Aug 2026 21:01:41 UTC (374 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes