← Back to all news
arXiv AI By Samah Kareem, Bar{\i}\c{s} \c{C}elikta\c{s}

Causal Evidentiary Governance for High-Risk Machine Learning Systems

Read the original on arXiv AI →

The paper proposes Causal Evidentiary Governance (CEG), a framework that requires regulated institutions to maintain a versioned directed acyclic graph (DAG) separating allowable from disallowed causal pathways in high‑risk machine learning systems. CEG introduces the Causal Harm Rate to quantify prediction variation due to disallowed pathways and pairs each decision with a signed Decision‑Evidence Packet (DEP) that cryptographically links the prediction to the DAG and path‑specific attributions, enabling efficient inclusion proofs via a Merkle tree. Empirical validation on synthetic credit data and the German Credit dataset demonstrates that CEG more clearly isolates causal effects than traditional fairness metrics and that a proof‑of‑concept implementation shows operational feasibility with manageable performance tradeoffs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
5d ago

Decomposing Discrimination: Causal Mediation Analysis for AI-Driven Credit Decisions

The paper introduces a causal mediation framework to separate direct discrimination from structural inequality in AI-driven credit decisions. Using Pearl’s natural direct and indirect effects, it presents an identification strategy under treatment‑induced confounding and proposes a doubly‑robust estimator with efficiency guarantees. Empirical analysis of 89,465 mortgage applications shows that about 77% of racial denial disparities stem from financial mediators, while the remaining 23% represents a conservative lower bound on direct discrimination.

By Duraimurugan Rajamanickam
safety
More like this →
arXiv AI
Aug 19

Communicating Credit Risk with Large Language Models: Evaluation of Explanations from Standard and Alternative Data-Based Models

The study investigates whether Large Language Models (LLMs) can translate technical explanations from credit risk models into stakeholder-friendly narratives. Using Freddie Mac loan data, the authors compare standard tabular models (XGBoost + SHAP) with alternative data pipelines (GNN + GNNExplainer and a bimodal mix) and generate explanations with three LLM configurations: a small fine‑tuned Gemma 3 4B, a large fine‑tuned DeepSeek R1 70B, and a zero‑shot Gemini 2.5. Findings show that the quality of explanations is more dependent on the evidence representation than on the LLM, that narratives reliably identify influential factors but are less consistent about the direction of influence, and that credit professionals demand higher evidentiary standards than non‑professionals.

By Sahab Zandi, Noah Kostesku, Christophe Mues, Mar\'ia \'Oskarsd\'ottir, Cristi\'an Bravo
llmsfine-tuningsafety
More like this →
arXiv AI
Aug 28

Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs

The paper introduces REMI, a framework that treats counterfactual fairness as a relational invariant discovery problem. By learning over paired examples, REMI identifies input regions where fairness is violated and generates interpretable rule-based models—fairness invariants—that can block or relabel unfair predictions without retraining the underlying model. Experiments on symbolic and neural network programs show REMI localizes fairness bugs in over 83% of cases and reduces discriminatory decisions in black-box models by up to 70%.

By Ranit Debnath Akash, Ashish Kumar, Gang Tan, Saeid Tizpaz-Niari
benchmarkssafety
More like this →