{"ID":2890149,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.19898","arxiv_id":"2507.19898","title":"TS-Insight: Visualizing Thompson Sampling for Verification and XAI","abstract":"Thompson Sampling (TS) and its variants are powerful Multi-Armed Bandit algorithms used to balance exploration and exploitation strategies in active learning. Yet, their probabilistic nature often turns them into a \"black box\", hindering debugging and trust. We introduce TS-Insight, a visual analytics tool explicitly designed to shed light on the internal decision mechanisms of Thompson Sampling-based algorithms, for model developers. It comprises multiple plots, tracing for each arm the evolving posteriors, evidence counts, and sampling outcomes, enabling the verification, diagnosis, and explainability of exploration/exploitation dynamics. This tool aims at fostering trust and facilitating effective debugging and deployment in complex binary decision-making scenarios especially in sensitive domains requiring interpretable decision-making.","short_abstract":"Thompson Sampling (TS) and its variants are powerful Multi-Armed Bandit algorithms used to balance exploration and exploitation strategies in active learning. Yet, their probabilistic nature often turns them into a \"black box\", hindering debugging and trust. We introduce TS-Insight, a visual analytics tool explicitly d...","url_abs":"https://arxiv.org/abs/2507.19898","url_pdf":"https://arxiv.org/pdf/2507.19898v2","authors":"[\"Parsa Vares\",\"Éloi Durant\",\"Jun Pang\",\"Nicolas Médoc\",\"Mohammad Ghoniem\"]","published":"2025-07-26T09:58:26Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"cs.AI\",\"cs.LG\",\"stat.ML\"]","methods":"[\"LoRA\"]","has_code":false}