IAFM'26

Time	#	Title	Authors
14:00–14:30	Opening
14:30–14:55	1224	The Recourse Test: Do LLM Adverse-Action Explanations Survive Repair-and-Replay?	Jonathan Chang
14:55–15:20	1261	Inside Chat Bankman-Fried: Geometric Insights into LLM Alignment in Finance	Chiara Coltellacci, Anastasia Di Blasio, Giulia Iadisernia, Carolina Camassa, Diego Doimo, Andrea Coletta, Aldo Glielmo, Anna Russo Russo
15:20–15:40	1283	Two Sides of the Same €-coin: Explaining Euro-Area Economic Activity with Interventional and Observational SHAP	Aldo Glielmo, Andrea Coletta, Cristina Conflitti, Giordano Zevi
15:40–16:00	1326	AssetDART: Interpreting Neural Portfolio Models Through Decision Regimes	Silu Li, John Mulvey, Siyu Li
16:00–16:30	Coffee break
16:30–16:50	1319	Text as Structure, Not Signal: Text-Aligned Groups for Distributionally Robust Stock Ranking	Jiwon Park, Namhyoung Kim, Sungweon Shin, Jae Wook Song
16:50–17:10	1159	What Post-hoc Attributions of FRTB-IMA Capital Answer	Yuhe Sui, Yingzhi Tang
17:10–17:30	1260	PolicyAttention: A Certifiable and Testable Update Rule for Attention-Based Allocation Controllers	Shufang Chen, Yuhe Sui, Yingzhi Tang, Xinyue Wu
17:30–17:50	1270	Explainability-Informed Evaluation of AI Challengers for Heston Option Pricing: Comparator Choice, Regime Dependence, and Model Risk	Bhupendra Kumar Singh, Kashmala Mangrio, Umer Ijaz
17:50–18:00	Closing remarks

Scope

Topics of interest

IAFM'26 spans an arc from discriminative XAI to the mechanistic interpretability and safety of generative-AI pipelines in finance. Only submissions concerning AI in financial services are in scope.

Discriminative XAI

Post-hoc attribution (SHAP, counterfactuals) in credit, fraud/AML, trading, risk — methods and failure modes
Concept-based and prototype-based explanations grounded in financial semantics
Fairness–interpretability interplay in financial decisions

Mechanistic interpretability

Sparse autoencoders, circuit-level analysis, and feature-steering for financial LLMs and agents
Interpretability of the foundation models now entering finance
Moving the interpretability frontier inward: what circuit- and feature-level analysis adds to classical attribution

GenAI pipelines & safety

Hallucination, toxicity, robustness, and misuse of financial LLMs and agentic systems
Where classical XAI methods still transfer to generative pipelines, and where new challenges emerge
From XAI to genAI safety: how explainability relates to the broader safety agenda in finance

Evaluation & benchmarking

Faithful, robust, true-to-the-model evaluation of explanations; benchmarks and metrics
Interpretability for regulatory compliance (EU AI Act) and model-risk management; lessons from production deployments
Human factors: explanations for risk officers, auditors, and customers; user studies

Organizing committee

Convened by the Intesa Sanpaolo AI Research Group

Anchored in a setting where explainable and interpretable models are deployed under real regulatory and model-risk scrutiny, combined with academic expertise in XAI and mechanistic interpretability.

Lead organizer

Alan Perotti

Team Leader of the Model Explainability and Alignment team at Intesa Sanpaolo AI Research. PhD in AI (Turin & City University London). Chairs the XAI Session of the International Neural Networks Society; designed the Intesa Sanpaolo XAI library. alan.perotti@intesasanpaolo.com

Co-organizer

André Panisson

Team Leader of the Trust, Safety & Resilience team, Intesa Sanpaolo AI Research. Co-organizes the AI for Financial Crime Fight workshop series; co-authored the KDD 2025 concept-based XAI / mechanistic-interpretability tutorial.

Senior advisor

Francesco Bonchi

Head of Intesa Sanpaolo AI Research. General Chair of KDD 2024; PC Chair of The Web Conference 2026. 25+ years across academic research and industrial leadership in ML, data mining, and algorithmic fairness.

Interpretability & Alignment of Financial Models