Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
arXiv:2602.16823v1 Announce Type: new Abstract: *Automated circuit discovery* is a central tool in mechanistic interpretability for identifying the internal components of neural networks responsible for specific behaviors. While prior methods have made significant progress, they typically depend on heuristics or...
Position: Why a Dynamical Systems Perspective is Needed to Advance Time Series Modeling
arXiv:2602.16864v1 Announce Type: new Abstract: Time series (TS) modeling has come a long way from early statistical, mainly linear, approaches to the current trend in TS foundation models. With a lot of hype and industrial demand in this field, it...
Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning
arXiv:2602.16947v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GNNs attempt to bridge this gap, they often rely...
Malliavin Calculus as Stochastic Backpropogation
arXiv:2602.17013v1 Announce Type: new Abstract: We establish a rigorous connection between pathwise (reparameterization) and score-function (Malliavin) gradient estimators by showing that both arise from the Malliavin integration-by-parts identity. Building on this equivalence, we introduce a unified and variance-aware hybrid estimator...
Forecasting Anomaly Precursors via Uncertainty-Aware Time-Series Ensembles
arXiv:2602.17028v1 Announce Type: new Abstract: Detecting anomalies in time-series data is critical in domains such as industrial operations, finance, and cybersecurity, where early identification of abnormal patterns is essential for ensuring system reliability and enabling preventive maintenance. However, most existing...
AI-Driven Legal Automation to Enhance Legal Processes with Natural Language Processing
The legal sector often faces delays and inefficiencies due to the overwhelming volume of information, the labor-intensive nature of research, and high service costs. This paper introduces a novel framework for AI-driven legal automation, which employs Natural Language Processing (NLP)...
Input out, output in: towards positive-sum solutions to AI-copyright tensions
Abstract This article addresses the legal tensions between artificial intelligence (AI) development and copyright law, exploring policymaking on the use of copyrighted data for AI training at the input level and the generation of AI content at the output level....
Justices to consider constitutionality of tax foreclosure sales
The argument next week in Pung v Isabella County asks the court to consider the constitutionality of the longstanding practice of tax foreclosures sales. This is one of those cases […]The postJustices to consider constitutionality of tax foreclosure salesappeared first...
Understanding LLM Failures: A Multi-Tape Turing Machine Analysis of Systematic Errors in Language Model Reasoning
arXiv:2602.15868v1 Announce Type: new Abstract: Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic multi-tape Turing machine, where each tape represents a distinct component: input characters, tokens, vocabulary,...
P-RAG: Prompt-Enhanced Parametric RAG with LoRA and Selective CoT for Biomedical and Multi-Hop QA
arXiv:2602.15874v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable capabilities but remain limited by their reliance on static training data. Retrieval-Augmented Generation (RAG) addresses this constraint by retrieving external knowledge during inference, though it still depends heavily on...
DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting
arXiv:2602.15958v1 Announce Type: new Abstract: Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together. Despite recent advances in visual document understanding, the fundamental task of document packet splitting, which involves separating a...
Beyond Learning: A Training-Free Alternative to Model Adaptation
arXiv:2602.16189v1 Announce Type: new Abstract: Despite the continuous research and evolution of language models, they sometimes underperform previous versions. Existing approaches to overcome these challenges are resource-intensive, highlighting the need for alternatives that enable immediate action. We assume that each...
The Validity of Coreference-based Evaluations of Natural Language Understanding
arXiv:2602.16200v1 Announce Type: new Abstract: In this thesis, I refine our understanding as to what conclusions we can reach from coreference-based evaluations by expanding existing evaluation practices and considering the extent to which evaluation results are either converging or conflicting....
Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications
arXiv:2602.16201v1 Announce Type: new Abstract: Large language models (LLMs) are trained on web-scale corpora that exhibit steep power-law distributions, in which the distribution of knowledge is highly long-tailed, with most appearing infrequently. While scaling has improved average-case performance, persistent failures...
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
arXiv:2602.16346v1 Announce Type: new Abstract: LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test single-prompt instructions, leaving a...
Distributed physics-informed neural networks via domain decomposition for fast flow reconstruction
arXiv:2602.15883v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) offer a powerful paradigm for flow reconstruction, seamlessly integrating sparse velocity measurements with the governing Navier-Stokes equations to recover complete velocity and latent pressure fields. However, scaling such models to large...
Verifier-Constrained Flow Expansion for Discovery Beyond the Data
arXiv:2602.15984v1 Announce Type: new Abstract: Flow and diffusion models are typically pre-trained on limited available data (e.g., molecular samples), covering only a fraction of the valid design space (e.g., the full molecular space). As a consequence, they tend to generate...
MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching
arXiv:2602.16020v1 Announce Type: new Abstract: Molecular crystal structure prediction represents a grand challenge in computational chemistry due to large sizes of constituent molecules and complex intra- and intermolecular interactions. While generative modeling has revolutionized structure discovery for molecules, inorganic solids,...
Extracting and Analyzing Rail Crossing Behavior Signatures from Videos using Tensor Methods
arXiv:2602.16057v1 Announce Type: new Abstract: Railway crossings present complex safety challenges where driver behavior varies by location, time, and conditions. Traditional approaches analyze crossings individually, limiting the ability to identify shared behavioral patterns across locations. We propose a multi-view tensor...
Discrete Stochastic Localization for Non-autoregressive Generation
arXiv:2602.16169v1 Announce Type: new Abstract: Non-autoregressive (NAR) generation reduces decoding latency by predicting many tokens in parallel, but iterative refinement often suffers from error accumulation and distribution shift under self-generated drafts. Masked diffusion language models (MDLMs) and their remasking samplers...
Lawsuit: ChatGPT told student he was "meant for greatness"—then came psychosis
"AI Injury Attorneys" target the chatbot design itself.
ViTaB-A: Evaluating Multimodal Large Language Models on Visual Table Attribution
arXiv:2602.15769v1 Announce Type: new Abstract: Multimodal Large Language Models (mLLMs) are often used to answer questions in structured data such as tables in Markdown, JSON, and images. While these models can often give correct answers, users also need to know...
Avey-B
arXiv:2602.15814v1 Announce Type: new Abstract: Compact pretrained bidirectional encoders remain the backbone of industrial NLP under tight compute and memory budgets. Their effectiveness stems from self-attention's ability to deliver high-quality bidirectional contextualization with sequence-level parallelism, as popularized by BERT-style architectures....
FrameRef: A Framing Dataset and Simulation Testbed for Modeling Bounded Rational Information Health
arXiv:2602.15273v1 Announce Type: cross Abstract: Information ecosystems increasingly shape how people internalize exposure to adverse digital experiences, raising concerns about the long-term consequences for information health. In modern search and recommendation systems, ranking and personalization policies play a central role...
MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference
arXiv:2602.15206v1 Announce Type: new Abstract: Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as...
Automatically Finding Reward Model Biases
arXiv:2602.15222v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce...
Size Transferability of Graph Transformers with Convolutional Positional Encodings
arXiv:2602.15239v1 Announce Type: new Abstract: Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. A key design choice in GTs is the use of Graph Neural Network (GNN)-based positional...
Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models
arXiv:2602.15332v1 Announce Type: new Abstract: Understanding how language models carry out long-horizon reasoning remains an open challenge. Existing interpretability methods often highlight tokens or spans correlated with an answer, but they rarely reveal where the model makes consequential reasoning turns,...
Benchmarking IoT Time-Series AD with Event-Level Augmentations
arXiv:2602.15457v1 Announce Type: new Abstract: Anomaly detection (AD) for safety-critical IoT time series should be judged at the event level: reliability and earliness under realistic perturbations. Yet many studies still emphasize point-level results on curated base datasets, limiting value for...
CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals
arXiv:2602.15546v1 Announce Type: new Abstract: The ability to accurately perform counterfactual inference on time series is crucial for decision-making in fields like finance, healthcare, and marketing, as it allows us to understand the impact of events or treatments on outcomes...