arXiv subjects

Dip Roy

Publications and source records attributed to Dip Roy.

7 recordsLinked to original sources

arXiv2026

MemGuard-Alpha: Detecting and Filtering Memorization-Contaminated Signals in LLM-Based Financial Forecasting via Membership Inference and Cross-Model Disagreement

Large language models (LLMs) are increasingly used to generate financial alpha signals, yet growing evidence shows that LLMs memorize historical financial data from their training corpora, producing spurious predictive accuracy that collapses out-of-sample. This memorization-induced look-ahead bias threatens the validity of LLM-based quantitative strategies. Prior remedies -- model retraining and input anonymization -- are either prohibitively expensive or introduce significant information loss. No existing method offers practical, zero-cost signal-level filtering for real-time trading. We introduce MemGuard-Alpha, a post-generation framework comprising two algorithms: (i) the MemGuard Composite Score (MCS), which combines five membership inference attack (MIA) methods with temporal proximity features via logistic regression, achieving Cohen's d = 18.57 for contamination separation (d = 0.39-1.37 using MIA features alone); and (ii) Cross-Model Memorization Disagreement (CMMD), which exploits variation in training cutoff dates across LLMs to separate memorized signals from genuine reasoning. Evaluated across seven LLMs (124M-7B parameters), 50 S&P 100 stocks, 42,800 prompts, and five MIA methods over 5.5 years (2019-2024), CMMD achieves a Sharpe ratio of 4.11 versus 2.76 for unfiltered signals (49% improvement). Clean signals produce 14.48 bps average daily return versus 2.13 bps for tainted signals (7x difference). A striking crossover pattern emerges: in-sample accuracy rises with contamination (40.8% to 52.5%) while out-of-sample accuracy falls (47% to 42%), providing direct evidence that memorization inflates apparent accuracy at the cost of generalization.

cs.LG↗

arXiv2026

Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data

Although mechanism-based interpretability has generated an abundance of insight for discriminative network analysis, generative models are less understood -- particularly outside of image-related applications. We investigate how much of the causal circuitry found within image-related variational autoencoders (VAEs) will generalize to tabular data, as VAEs are increasingly used for imputation, anomaly detection, and synthetic data generation. In addition to extending a four-level causal intervention framework to four tabular and one image benchmark across five different VAE architectures (with 75 individual training runs per architecture and three random seed values for each run), this paper introduces three new techniques: posterior-calibration of Causal Effect Strength (CES), path-specific activation patching, and Feature-Group Disentanglement (FGD). The results from our experiments demonstrate that: (i) Tabular VAEs have circuits with modularity that is approximately 50% lower than their image counterparts. (ii) $\beta$-VAE experiences nearly complete collapse in CES scores when applied to heterogeneous tabular features (0.043 CES score for tabular data compared to 0.133 CES score for images), which can be directly attributed to reconstruction quality degradation (r = -0.886 correlation coefficient between CES and MSE). (iii) CES successfully captures nine of eleven statistically significant architecture differences using Holm--\v{S}id\'{a}k corrections. (iv) Interventions with high specificity predict the highest downstream AUC values (r = 0.460, p < .001). This study challenges the common assumption that architectural guidance from image-related studies can be transferred to tabular datasets.

cs.LG↗

arXiv2026

Detection Without Correction: A Robust Asymmetry in Activation-Based Hallucination Probing

Activation-based linear probing is widely proposed as a method for both detecting and correcting hallucinations in autoregressive language models. We present an empirical study across seven models spanning 117M to 7B parameters and three architecture families (GPT-2, Pythia, Qwen-2.5) that documents a robust asymmetry: linear probes can detect hallucination signals with above-chance accuracy in larger models, but activation steering along the probe-derived direction fails to correct hallucinations in 7 of 7 models tested. We further find that output-confidence baselines outperform activation probes on raw detection AUC at every model above 410M parameters, with the gap reaching 0.157 AUC for Pythia-6.9B. The probe's distinguishing value is therefore not detection accuracy but temporal positioning: probe signals are accessible at position zero (before any output tokens are produced), enabling pre-generation flagging that output-based methods structurally cannot provide. The temporal signal is statistically significant in two of seven models (Pythia-1.4B, p = 0.012; Qwen2.5-7B, p = 0.038) and absent in models below 400M parameters and in the base-only Pythia-6.9B. We position these findings as a clean negative result for the dominant probing-as-detection-and-control research direction and as initial evidence that probe-based methods occupy a complementary deployment niche, namely pre-generation flagging, rather than competing with output-based detectors on raw accuracy.

cs.CL↗

arXiv2026

Fundamental Limits of Neural Network Sparsification: Evidence from Catastrophic Interpretability Collapse

Extreme neural network sparsification (90% activation reduction) presents a critical challenge for mechanistic interpretability: understanding whether interpretable features survive aggressive compression. This work investigates feature survival under severe capacity constraints in hybrid Variational Autoencoder--Sparse Autoencoder (VAE-SAE) architectures. We introduce an adaptive sparsity scheduling framework that progressively reduces active neurons from 500 to 50 over 50 training epochs, and provide empirical evidence for fundamental limits of the sparsification-interpretability relationship. Testing across two benchmark datasets -- dSprites and Shapes3D -- with both Top-k and L1 sparsification methods, our key finding reveals a pervasive paradox: while global representation quality (measured by Mutual Information Gap) remains stable, local feature interpretability collapses systematically. Under Top-k sparsification, dead neuron rates reach $34.4\pm0.9\%$ on dSprites and $62.7\pm1.3\%$ on Shapes3D at k=50. L1 regularization -- a fundamentally different "soft constraint" paradigm -- produces equal or worse collapse: $41.7\pm4.4\%$ on dSprites and $90.6\pm0.5\%$ on Shapes3D. Extended training for 100 additional epochs fails to recover dead neurons, and the collapse pattern is robust across all tested threshold definitions. Critically, the collapse scales with dataset complexity: Shapes3D (RGB, 6 factors) shows $1.8\times$ more dead neurons than dSprites (grayscale, 5 factors) under Top-k and $2.2\times$ under L1. These findings establish that interpretability collapse under sparsification is intrinsic to the compression process rather than an artifact of any particular algorithm, training duration, or threshold choice.

cs.LG↗

arXiv2025

Mechanistic Interpretability of Diffusion Models: Circuit-Level Analysis and Causal Validation

We present a quantitative circuit-level analysis of diffusion models, establishing computational pathways and mechanistic principles underlying image generation processes. Through systematic intervention experiments across 2,000 synthetic and 2,000 CelebA facial images, we discover fundamental algorithmic differences in how diffusion architectures process synthetic versus naturalistic data distributions. Our investigation reveals that real-world face processing requires circuits with measurably higher computational complexity (complexity ratio = 1.084 plus/minus 0.008, p < 0.001), exhibiting distinct attention specialization patterns with entropy divergence ranging from 0.015 to 0.166 across denoising timesteps. We identify eight functionally distinct attention mechanisms showing specialized computational roles: edge detection (entropy = 3.18 plus/minus 0.12), texture analysis (entropy = 4.16 plus/minus 0.08), and semantic understanding (entropy = 2.67 plus/minus 0.15). Intervention analysis demonstrates critical computational bottlenecks where targeted ablations produce 25.6% to 128.3% performance degradation, providing causal evidence for identified circuit functions. These findings establish quantitative foundations for algorithmic understanding and control of generative model behavior through mechanistic intervention strategies.

cs.CV↗

arXiv2025

A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders

Understanding how generative models represent and transform data is a foundational problem in deep learning interpretability. While mechanistic interpretability of discriminative architectures has yielded substantial insights, relatively little work has addressed variational autoencoders (VAEs). This paper presents the first general-purpose multilevel causal intervention framework for mechanistic interpretability of VAEs. The framework comprises four manipulation types: input manipulation, latent-space perturbation, activation patching, and causal mediation analysis. We also define three new quantitative metrics capturing properties not measured by existing disentanglement metrics alone: Causal Effect Strength (CES), intervention specificity, and circuit modularity. We conduct the largest empirical study to date of VAE causal mechanisms across six architectures (standard VAE, beta-VAE, FactorVAE, beta-TC-VAE, DIP-VAE-II, and VQ-VAE) and five benchmarks (dSprites, 3DShapes, MPI3D, CelebA, and SmallNORB), with three seeds per configuration, totaling 90 independent training runs. Our results reveal several findings: (i) a consistent within-dataset negative correlation between CES and DCI disentanglement (the CES-DCI trade-off); (ii) that the KL reweighting mechanism of beta-VAE induces a capacity bottleneck when generative factors approach latent dimensionality, degrading disentanglement on complex datasets; (iii) that no single VAE architecture dominates across all five datasets, with optimal choice depending on dataset structure; and (iv) that CES-based metrics applied to discrete latent spaces (VQ-VAE) yield near-zero values, revealing a critical limitation of continuous-intervention methods for discrete representations. These results provide both a theoretical foundation and comprehensive empirical evaluation for mechanistic interpretability of generative models.

cs.LG↗

arXiv2025

Bayesian Autoencoder for Medical Anomaly Detection: Uncertainty-Aware Approach for Brain 2 MRI Analysis

In medical imaging, anomaly detection is a vital element of healthcare diagnostics, especially for neurological conditions which can be life-threatening. Conventional deterministic methods often fall short when it comes to capturing the inherent uncertainty of anomaly detection tasks. This paper introduces a Bayesian Variational Autoencoder (VAE) equipped with multi-head attention mechanisms for detecting anomalies in brain magnetic resonance imaging (MRI). For the purpose of improving anomaly detection performance, we incorporate both epistemic and aleatoric uncertainty estimation through Bayesian inference. The model was tested on the BraTS2020 dataset, and the findings were a 0.83 ROC AUC and a 0.83 PR AUC. The data in our paper suggests that modeling uncertainty is an essential component of anomaly detection, enhancing both performance and interpretability and providing confidence estimates, as well as anomaly predictions, for clinicians to leverage in making medical decisions.

cs.LG↗