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

• URL: http://arxiv.org/abs/2608.17715v1
• Date: Tue, 18 Aug 2026 12:39:46 GMT
• Title: Communicating Credit Risk with Large Language Models: Evaluation of Explanations from Standard and Alternative Data-Based Models
• Abstract summary: Credit decisioning is a high-stakes task in which model outputs must be accurate and explainable to support compliant decisions.<n>Modern credit risk models such as eXtreme Gradient Boosting (XGBoost) and Graph Neural Networks (GNNs) improve predictive performance.<n>We examine whether Large Language Models (LLMs) can serve as explanation layers that translate post-hoc explanation artefacts into stakeholder-appropriate risk narratives.
• Score: 1.5136899433821893
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Credit decisioning is a high-stakes task in which model outputs must be accurate and explainable to support compliant decisions. Although modern credit risk models such as eXtreme Gradient Boosting (XGBoost) and Graph Neural Networks (GNNs) improve predictive performance, their explanations are often too technical for stakeholders creating communication gaps that can shape approvals, denials, and fairness judgments. We examine whether Large Language Models (LLMs) can serve as explanation layers that translate post-hoc explanation artefacts into stakeholder-appropriate risk narratives. Using Freddie Mac single-family loan-level data, we develop three pipelines: standard tabular (XGBoost + SHAP), and two with alternative data, a pure network-based (GNN + GNNExplainer), and a bimodal one (combining tabular and network data). We generate narratives with three LLM configurations: a small fine-tuned LLM (Gemma 3 4B), a large fine-tuned LLM (DeepSeek R1 70B), and a zero-shot commercial LLM (Gemini 2.5). Explanation quality is evaluated through automated checks across all pipelines and a human study of bimodal explanations comparing credit risk professionals and non-professionals on eight decision-relevant dimensions. We have three main findings. First, the pipeline accounts for higher variance in evidence-grounding scores than the language model, meaning that the binding constraint on explanation quality is the evidence representation, not the model used. Second, the explanation narratives reliably name the influential factors but are less reliable when stating the direction of influence, which may be consequential for adverse-action communication. Finally, professionals apply stricter evidentiary standards than non-professionals. We discuss implications for the governance of risk models, including deployment considerations and the value of domain-aligned LLMs in regulated credit settings.

Related papers

• A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation [59.98516959731531]
  Abstract reasoning ability reflects intelligence and capacity of LLMs to extract and apply abstract rules.<n>Existing benchmarks either rely on expensive manual annotation, limiting their scale, or risk measuring memorization rather than genuine reasoning.<n>We introduce an automated pipeline named A2RBench, encompassing generation, expansion, evaluation, and analysis.
  arXiv  Detail & Related papers  (2026-05-17T06:14:20Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models [61.33372454250959]
  Contextual causal reasoning is a critical yet challenging capability for Large Language Models.<n>Existing benchmarks fail to ensure context consistency or cover the full causal hierarchy.<n>We pioneer METER to systematically benchmark LLMs across all three levels of the causal ladder.
  arXiv  Detail & Related papers  (2026-04-13T14:07:11Z)
• FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios [58.34124792457706]
  The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to transition from simple perception to autonomous execution.<n>Progress is hindered by data scarcity and a lack of fine-grained domain semantics in existing datasets.<n>We first construct a high-quality dataset that combines realworld 2D images and 3D point clouds, annotated with fine-grained domain semantics.<n>We then evaluate 18 state-of-the-art MLLMs across three manufacturing tasks, namely verification, structural surface inspection, and assembly verification, revealing significant performance gaps.
  arXiv  Detail & Related papers  (2026-04-08T12:23:27Z)
• Could Large Language Models work as Post-hoc Explainability Tools in Credit Risk Models? [1.3253687170778101]
  Post-hoc explainability is central to credit risk model governance.<n>This paper investigates whether large language models (LLMs) can serve as post-hoc explainability tools for credit risk predictions through in-context learning.
  arXiv  Detail & Related papers  (2026-02-21T16:35:06Z)
• Utilizing Large Language Models for Machine Learning Explainability [37.31918138232927]
  This study explores the explainability capabilities of large language models (LLMs), when employed to autonomously generate machine learning (ML) solutions.<n>Three state-of-the-art LLMs are prompted to design training pipelines for four common classifiers: Random Forest, XGBoost, Multilayer Perceptron, and Long Short-Term Memory networks.<n>The generated models are evaluated in terms of predictive performance (recall, precision, and F1-score) and explainability using SHAP (SHapley Additive exPlanations)
  arXiv  Detail & Related papers  (2025-10-08T11:46:23Z)
• SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models [23.6287295499467]
  We introduce SMARTER, a framework for explainable content moderation using Large Language Models (LLMs)<n>In Stage 1, we leverage LLMs' own outputs to generate synthetic explanations for both correct and incorrect labels.<n>In Stage 2, we refine explanation quality through cross-model training, allowing weaker models to align stylistically and semantically with stronger ones.
  arXiv  Detail & Related papers  (2025-09-18T17:30:36Z)
• LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations [8.734404327315291]
  To collaborate effectively with humans, language models must be able to explain their decisions in natural language.<n>We study a specific type of self-generated counterfactual explanations (SCEs)<n>We evaluate whether models can produce SCEs that are valid, achieving the intended outcome, and minimal, modifying the input no more than necessary.
  arXiv  Detail & Related papers  (2025-09-11T12:25:41Z)
• Towards Large Language Models with Self-Consistent Natural Language Explanations [11.085839471231552]
  Large language models (LLMs) seem to offer an easy path to interpretability.<n>Yet, studies show that these post-hoc explanations often misrepresent the true decision process.
  arXiv  Detail & Related papers  (2025-06-09T08:06:33Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.