Research Papers

Balancing electricity demand and supply is increasingly difficult due to the inherent intermittency of renewable power generation and the stochastic power consumption. Grid operators require fine-grained, decision-relevant insights into household energy consumption to manage peak loads and design responsive tariffs, but increased transparency at this level raises significant privacy concerns. Traditional methods for explainable AI (XAI) can reveal sensitive information, while standard privacy techniques often reduce the usefulness of explanations. To address this issue, we introduce HXAI, a hierarchical framework that preserves privacy while enabling reasonable explainable analysis for grid-level demand management. HXAI consists of two main components: (1) a local model that generates fine-grained explanations within a secure, private environment, and (2) a zonal model that aggregates these explanations to support grid-level analysis while enforcing privacy through flexible privacy-budget management. We explicitly limit cumulative privacy exposure under repeated operator queries and show that the proposed framework preserves decision-relevant information without compromising household privacy. Experiments on both simulated and real-world energy datasets demonstrate that HXAI provides useful insights for zonal load management while ensuring that appliance-level consumption remains local and is never transmitted to grid operators. Our results show that preserving the semantic structure of explanations, rather than minimizing numerical error, is the key to XAI under differential privacy. This framework provides a way to achieve both privacy and explainability in energy management.

In finance, interpreting machine learning predictions is essential, yet the numerical outputs of explainable AI can be difficult for non-experts to understand. While large language models (LLMs) can translate these outputs into natural language, they may produce errors when inferring numerical changes and feature relations. We propose an LLM narrative framework for cross-sectional stock return prediction that combines temporal Shapley additive explanations (SHAP) evidence with historical regime analogs. Temporal evidence tracks changes in the normalized global SHAP importance of an XGBoost model over six months. Historical analogs are past periods with similar changes in SHAP importance, their model performance and subsequent market returns are provided as comparative context. Using this framework, we conduct a controlled study of progressive reasoning externalization, sequentially providing raw SHAP sequences, deterministic temporal descriptors, and feature relations. Each generated claim is verified against provenance-linked evidence. Across Qwen3, externalizing numerical and relational reasoning improved evidence faithfulness as well as temporal and relational accuracy. Evidence faithfulness increased from 0.696 to 0.996 for Qwen3-32B-Instruct. While historical analogs did not improve structured automatic faithfulness, they received higher human-rated usefulness scores. These results suggest that externalizing verifiable reasoning enhances narrative faithfulness and that historical context adds interpretive value.

When a graph neural network (GNN) explainer produces an unexpected attribution on a molecule, the attribution alone cannot reveal whether the explainer has failed or the model has learned a shortcut. We introduce WOMBAT, a benchmark of 14 whitebox GNNs, each with message-passing weights set by hand to detect a specific SMARTS motif. Each model's decision rule is known by construction, providing attribution ground truth against which explainer errors can be identified and studied. We validate the models on millions of PubChem molecules and evaluate post-hoc explainers including GNNExplainer, PGExplainer, and Integrated Gradients. Guided by our qualitative analysis, we construct a model that causes Integrated Gradients to spread attribution across the graph, even though the model reliably detects the intended motif. We release the dataset, models, and evaluation code to help researchers in the development of newer XAI tools for GNNs.

Purpose: Money laundering threatens financial systems, while rule-based monitoring suffers from high false-positive rates and limited ability to capture relational transaction patterns. This study proposes an explainable graph-based framework for anti-money laundering (AML) detection that jointly addresses predictive performance, explanation faithfulness, and uncertainty calibration. Methods: Using the IBM Transactions for Anti-Money Laundering (HI-Small) benchmark, comprising 5,078,345 transactions among 518,573 accounts with 0.10% illicit transactions, a directed attributed graph with 4,487,133 edges was constructed using temporal, leakage-safe partitioning. Three GATv2 architectures, BASE, BASE-Large, and IMPROVED, incorporating bidirectional message passing, edge updates, and port-aware features, were compared with XGBoost and Random Forest using identical features. The best model was evaluated using GNNExplainer against documented typologies and Mondrian conformal prediction for uncertainty calibration. Results: IMPROVED achieved the strongest performance (AUPRC = 64.85%, Best F1 = 68.42%), exceeding BASE-Large by 30.65 AUPRC points and XGBoost (AUPRC = 38.46%) by 26.4 points. The proposed mechanisms contributed more than capacity scaling alone. GNNExplainer recovered documented typologies with higher fidelity than attention-weight and random baselines (mean Jaccard overlap: 21.4% vs. 1.0%, p < 0.001). Mondrian conformal prediction achieved coverage close to the 90% nominal target with an average prediction-set size near one. Conclusion: Explicit transaction topology modeling substantially improves AML detection, while faithful explanations and calibrated uncertainty support interpretable, human-in-the-loop compliance decision-making.

On a single task, deep networks can learn many solutions, depending on their optimizer, training data, architecture, and hyperparameters. Many of these solutions are mode-connected: rather than isolated points in weight space, they are connected by low-loss regions. Yet how their internal computation varies within these regions is unknown. A parallel line of work has identified the degeneracy of neural representations: many networks reach similar training loss with distinct internal structures. However, it is unclear how these solutions are related in weight space. We unify these subfields and show for the first time that many different internal mechanisms exist within a local mode-connected region in weight space. To do so, we introduce Hessian Null Space Continuation (HNC), a scalable method that uses local curvature to traverse regions of weight space that preserve network function, and can be steered toward solutions with specified properties. In RNNs trained on a memory task, HNC reaches drastically different representations and dynamics with maintained behavior. In ImageNet-trained Vision Transformers, HNC finds representations that differ more from the original network than any independently trained model with a different architecture or objective. In reinforcement-learning agents, HNC uncovers a distinct navigation strategy at comparable return and exposes reward hacking in an AI Safety Gridworld. Finally, HNC measures the local geometry of the solution set, showing how model size and task complexity shape its dimension and functional sensitivity. Our results show that a surprisingly large amount of representational diversity exists near a single trained solution, unseen by standard gradient-based optimization. HNC identifies and quantifies this diversity, opening new possibilities for mechanistic understanding of solution spaces and for model merging, editing, and fine-tuning.

Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces

Ratish Puduppully, Pranabendu Misra, Paarth Iyer +3

Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning. Testing this interpretation is difficult because natural-language thinking traces are rarely mechanically verifiable. We revisit it in iGSM, a synthetic grade-school mathematics benchmark designed to study thinking traces and used to support claims of learned reasoning and planning. Crucially, iGSM exposes the exact quantities and dependencies that a correct solution should use, allowing generated traces to be checked programmatically step by step and enabling us to test whether correct answers are reliably accompanied by valid traces. We first evaluate models trained exclusively on valid, minimal traces. Answer correctness and trace validity nearly coincide in distribution but decouple out of distribution: on the hardest instances, 31.6% of correct answers have invalid traces, over half of which pass all syntactic and arithmetic checks but fail semantic dependency checks. We then intervene on trace supervision. Non-minimal training traces induce non-minimal outputs, while re-asking the same problem with a different query reveals computations inherited from the original query, weakening minimality as evidence of selective planning. Shuffling tokens in 10% of training trace sentences preserves near-clean accuracy even out of distribution despite no trace passing verification. Swapped training traces likewise retain high in-distribution accuracy. We discuss the implications of these findings for chain-of-thought monitoring and interpretation in the context of AI safety.

The reliable prediction of passenger train delays is a critical component of railway management. While contemporary research frequently attempts to maximize absolute accuracy by deploying opaque deep learning architectures, the underlying data mechanics driving longitudinal predictive decay remain underexplored. Consequently, this study provides an explainable temporal robustness analysis of network-wide railway delay prediction. Focusing on the Dutch railway network, this research utilizes interpretable tree-based ensembles to integrate granular topological, environmental, and operational features. The overarching finding establishes that while feature-rich tree-based models improve simultaneous (within-month) prediction, predictive performance systematically degrades when evaluated across non-simultaneous (future) months. Furthermore, multi-horizon SHAP and dispersion analyses explicitly link this degradation to environmental feature volatility and instability within the statistical target definition. Ultimately, this study demonstrates that richer feature sets alone are insufficient to resolve long-term forecasting constraints, underscoring the necessity to transition toward dynamic, season-aware architectures anchored by absolute operational boundaries.

Concept-based explanations describe neural network predictions through human-understandable properties of inputs called concepts. The field encompasses approaches that differ in how they define and represent concepts and connect them to model predictions. We introduce a theoretical framework that describes these approaches in a common mathematical language and supports a shared analysis of their properties. For concept discovery, which identifies concepts automatically within a latent space of a trained model, we employ a concept autoencoder view. An encoder extracts concept representations from the model's latent space, and a decoder uses them to reconstruct the original latent representation. The autoencoder's reconstruction error measures how accurately its decoder recovers the original latent representation. We revisit model completeness: how well the concepts can reproduce the model's outputs. We show that model incompleteness of the concepts can be bounded by the autoencoder's reconstruction error. The autoencoder view also provides a common way to define individual concept attributions, which measure each concept's contribution to a prediction. We establish when these attributions sum to the model's prediction, and bound the discrepancy otherwise, thus providing attribution completeness guarantees.

Artificial-intelligence studies using computed tomography (CT) for lung cancer are often broadly labelled "prediction" despite addressing clinically distinct tasks. We systematically mapped CT/low-dose CT (LDCT)-centered lung-cancer AI using five-database retrieval, full-text eligibility assessment, role-aware modality/omics extraction, clinical-task classification, and a Multi-Tier Evidence Graph (MTEG). The final corpus comprised 293 studies (2016-2026): 230 Detection, 8 future Risk-prediction, and 55 Other studies. Clinical variables (96.2%), 3D CT/LDCT (73.0%), and radiomics (63.5%) predominated, whereas external validation (29.0%), calibration (20.5%), decision-curve analysis (13.0%), longitudinal CT (17.7%), and saliency/attribution XAI (21.5%) were less frequent. The MTEG comprised 377 nodes and 3,444 edges; only 31 studies (10.6%) completed the six-tier substantive evidence chain, with greatest attrition at reasoning/explanation. Overall, the literature is detection-dominated, genuine future risk prediction remains uncommon, and complete translational evidence chains are rare.

Reliable refusal of harmful requests is essential to the safe deployment of language models. Because excessive eagerness to please users may undermine existing refusal capabilities, reducing sycophancy offers a potential route to stronger refusal beyond the harmful scenarios covered by safety training. We investigate this possibility using compensatory feature injection (CFI), a training technique designed to limit the acquisition of a target concept by supplying its associated activation during learning. Across three Qwen3.5 base models, we use sparse autoencoders (SAEs) to identify the top-ranked sycophancy feature from paired sycophantic and independent responses, then validate its behavioral influence through inference steering. We subsequently inject the selected feature during supervised fine-tuning on sycophantic targets. Positive injection reduces learned sycophancy after removal (by 62.0% relative to ordinary fine-tuning in 35B-A3B), whereas modest negative injection increases it. Unexpectedly, these reductions in sycophancy do not consistently improve direct refusal of harmful requests, motivating a narrower evaluation of the same harmful intents under user pressure. In this setting, ordinary fine-tuning on sycophantic responses substantially weakens refusal, while selected checkpoints trained with positive injection recover part of the loss, including approximately 95% in 35B-A3B. These findings show that persistent sycophancy reduction does not guarantee stronger direct refusal, while identifying recovery under user pressure as a distinct, conditional benefit of training intervention.

Deep learning classifiers for dermoscopic skin lesions often reach high in-distribution accuracy while quietly relying on spurious background cues such as skin tone, device vignetting, and embedded rulers, rather than on lesion morphology. This undermines robustness and fairness across skin tones. This work asks whether Explainable AI (XAI), typically used only to audit a finished model, can instead be repurposed as an active training signal that corrects this shortcut without sacrificing diagnostic accuracy. We introduce CAMEO (Class Activation Mapped Equitable Overlay), a framework that improves skin-lesion classification by selecting stable model explanations and using them to separate lesions from their backgrounds. It then replaces the background with realistic synthetic skin while keeping the lesion unchanged. On HAM10000 and dark-skin ISIC images, CAMEO maintained accuracy while reducing background-driven errors by nearly four times. It also made the model's attention more consistent when backgrounds changed. Results across multiple tests show that reducing reliance on background information improves robustness, with Fitzpatrick-based backgrounds providing a realistic and interpretable approach. Results show that XAI-guided augmentation can make dermoscopic classifiers measurably more robust and fair at no cost to accuracy. They also clarify that it is the mechanism and not the specific tone palette that matters, and that the lasting contribution of XAI here lies in stability-screened, annotation-free lesion localisation rather than in the robustness number itself.

Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition

Nico García-Peguinho, David Kelly, Fabrizio Smeraldi +1

Perturbation-based XAI methods for audio classifiers often estimate feature importance by masking spectrogram regions and crediting output changes to the retained signal. Yet they typically assume the fill (the mask replacement) is negligible. We propose logit-space trajectory decomposition to examine this assumption. An on-axis component captures output along a line connecting the fully filled (occluded) spectrogram to the fully retained original; an off-axis component captures perpendicular displacement. We evaluate across three fills, three audio classifiers, and 1,100 AudioSet clips. We demonstrate that no fill is acoustically neutral under full occlusion: Zero fill activates silence and Gaussian Noise fill activates broadband noise. Under partial masking, 41-77% of output displacement is off-axis, with the direction of the residual stable across mask retention fraction and specific to each model-fill combination. Attribution methods are unevenly exposed to off-axis displacement through their sampling and weighting strategies, revealing apparatus-dependence. Where the off-axis residual is stable and low-dimensional, its structure affords mitigation.