Evaluating Austrian A-Level German Essays with Large Language Models for Automated Essay Scoring
arXiv:2603.06066v1 Announce Type: new Abstract: Automated Essay Scoring (AES) has been explored for decades with the goal to support teachers by reducing grading workload and mitigating subjective biases. While early systems relied on handcrafted features and statistical models, recent advances...
A Causal Graph Approach to Oppositional Narrative Analysis
arXiv:2603.06135v1 Announce Type: new Abstract: Current methods for textual analysis rely on data annotated within predefined ontologies, often embedding human bias within black-box models. Despite achieving near-perfect performance, these approaches exploit unstructured, linear pattern recognition rather than modeling the structured...
MAPO: Mixed Advantage Policy Optimization for Long-Horizon Multi-Turn Dialogue
arXiv:2603.06194v1 Announce Type: new Abstract: Subjective multi-turn dialogue tasks, such as emotional support, require conversational policies that adapt to evolving user states and optimize long-horizon interaction quality. However, reinforcement learning (RL) for such settings remains challenging due to the absence...
Wisdom of the AI Crowd (AI-CROWD) for Ground Truth Approximation in Content Analysis: A Research Protocol & Validation Using Eleven Large Language Models
arXiv:2603.06197v1 Announce Type: new Abstract: Large-scale content analysis is increasingly limited by the absence of observable ground truth or gold-standard labels, as creating such benchmarks through extensive human coding becomes impractical for massive datasets due to high time, cost, and...
FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
arXiv:2603.06199v1 Announce Type: new Abstract: Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. While various sparse attention mechanisms have been explored, they...
Transparent AI for Mathematics: Transformer-Based Large Language Models for Mathematical Entity Relationship Extraction with XAI
arXiv:2603.06348v1 Announce Type: new Abstract: Mathematical text understanding is a challenging task due to the presence of specialized entities and complex relationships between them. This study formulates mathematical problem interpretation as a Mathematical Entity Relation Extraction (MERE) task, where operands...
Abductive Reasoning with Syllogistic Forms in Large Language Models
arXiv:2603.06428v1 Announce Type: new Abstract: Research in AI using Large-Language Models (LLMs) is rapidly evolving, and the comparison of their performance with human reasoning has become a key concern. Prior studies have indicated that LLMs and humans share similar biases,...
PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations
arXiv:2603.06485v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm that neglects user differences in expertise, goals, and cognitive needs. Although Large Language...
Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning
arXiv:2603.06505v1 Announce Type: new Abstract: Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR show promise, two...
FuseDiff: Symmetry-Preserving Joint Diffusion for Dual-Target Structure-Based Drug Design
arXiv:2603.05567v1 Announce Type: new Abstract: Dual-target structure-based drug design aims to generate a single ligand together with two pocket-specific binding poses, each compatible with a corresponding target pocket, enabling polypharmacological therapies with improved efficacy and reduced resistance. Existing approaches typically...
The Value of Graph-based Encoding in NBA Salary Prediction
arXiv:2603.05671v1 Announce Type: new Abstract: Market valuations for professional athletes is a difficult problem, given the amount of variability in performance and location from year to year. In the National Basketball Association (NBA), a straightforward way to address this problem...
Reinforcement Learning for Power-Flow Network Analysis
arXiv:2603.05673v1 Announce Type: new Abstract: The power flow equations are non-linear multivariate equations that describe the relationship between power injections and bus voltages of electric power networks. Given a network topology, we are interested in finding network parameters with many...
Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression
arXiv:2603.05691v1 Announce Type: new Abstract: It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenomenon of weak-to-strong generalization exemplifies the advantage of this two-stage...
Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment
arXiv:2603.05739v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a reference model and the one with the highest predicted reward according to a learned...
MIRACL: A Diverse Meta-Reinforcement Learning for Multi-Objective Multi-Echelon Combinatorial Supply Chain Optimisation
arXiv:2603.05760v1 Announce Type: new Abstract: Multi-objective reinforcement learning (MORL) is effective for multi-echelon combinatorial supply chain optimisation, where tasks involve high dimensionality, uncertainty, and competing objectives. However, its deployment in dynamic environments is hindered by the need for task-specific retraining...
Bridging Domains through Subspace-Aware Model Merging
arXiv:2603.05768v1 Announce Type: new Abstract: Model merging integrates multiple task-specific models into a single consolidated one. Recent research has made progress in improving merging performance for in-distribution or multi-task scenarios, but domain generalization in model merging remains underexplored. We investigate...
First-Order Softmax Weighted Switching Gradient Method for Distributed Stochastic Minimax Optimization with Stochastic Constraints
arXiv:2603.05774v1 Announce Type: new Abstract: This paper addresses the distributed stochastic minimax optimization problem subject to stochastic constraints. We propose a novel first-order Softmax-Weighted Switching Gradient method tailored for federated learning. Under full client participation, our algorithm achieves the standard...
Sparse Crosscoders for diffing MoEs and Dense models
arXiv:2603.05805v1 Announce Type: new Abstract: Mixture of Experts (MoE) achieve parameter-efficient scaling through sparse expert routing, yet their internal representations remain poorly understood compared to dense models. We present a systematic comparison of MoE and dense model internals using crosscoders,...
MoE Lens -- An Expert Is All You Need
arXiv:2603.05806v1 Announce Type: new Abstract: Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We present a systematic analysis of...
Self-Auditing Parameter-Efficient Fine-Tuning for Few-Shot 3D Medical Image Segmentation
arXiv:2603.05822v1 Announce Type: new Abstract: Adapting foundation models to new clinical sites remains challenging in practice. Domain shift and scarce annotations must be handled by experts, yet many clinical groups do not have ready access to skilled AI engineers to...
Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls
arXiv:2603.05829v1 Announce Type: new Abstract: Test-time adaptation enables large language models (LLMs) to modify their behavior at inference without updating model parameters. A common approach is many-shot prompting, where large numbers of in-context learning (ICL) examples are injected as an...
Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
arXiv:2603.05900v1 Announce Type: new Abstract: Large language models (LLMs) benefit substantially from supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) in reasoning tasks. However, these recipes perform poorly in instruction-based molecular optimization, where each data point typically provides...
Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence
arXiv:2603.05960v1 Announce Type: new Abstract: Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existing approaches either lack clear convergence guarantees, or only achieve the standard ${\mathcal{O}}(\epsilon^{-4})$ iteration complexity...
EvoESAP: Non-Uniform Expert Pruning for Sparse MoE
arXiv:2603.06003v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (SMoE) language models achieve strong capability at low per-token compute, yet deployment remains memory- and throughput-bound because the full expert pool must be stored and served. Post-training expert pruning reduces this cost, but...
Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments
arXiv:2603.06009v1 Announce Type: new Abstract: Plateaus, where an agent's performance stagnates at a suboptimal level, are a common problem in deep on-policy RL. Focusing on PPO due to its widespread adoption, we show that plateaus in certain regimes arise not...
Agnostic learning in (almost) optimal time via Gaussian surface area
arXiv:2603.06027v1 Announce Type: new Abstract: The complexity of learning a concept class under Gaussian marginals in the difficult agnostic model is closely related to its $L_1$-approximability by low-degree polynomials. For any concept class with Gaussian surface area at most $\Gamma$,...
Dynamic Momentum Recalibration in Online Gradient Learning
arXiv:2603.06120v1 Announce Type: new Abstract: Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the...
DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection
arXiv:2603.06131v1 Announce Type: new Abstract: Time series anomaly detection has achieved remarkable progress in recent years. However, evaluation practices have received comparatively less attention, despite their critical importance. Existing metrics exhibit several limitations: (1) bias toward point-level coverage, (2) insensitivity...
Partial Policy Gradients for RL in LLMs
arXiv:2603.06138v1 Announce Type: new Abstract: Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset...
Topological descriptors of foot clearance gait dynamics improve differential diagnosis of Parkinsonism
arXiv:2603.06212v1 Announce Type: new Abstract: Differential diagnosis among parkinsonian syndromes remains a clinical challenge due to overlapping motor symptoms and subtle gait abnormalities. Accurate differentiation is crucial for treatment planning and prognosis. While gait analysis is a well established approach...