ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning
arXiv:2603.05878v1 Announce Type: new Abstract: Pruning is widely recognized as an effective method for reducing the parameters of large language models (LLMs), potentially leading to more efficient deployment and inference. One classic and prominent path of LLM one-shot pruning is...
Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation
arXiv:2603.05881v1 Announce Type: new Abstract: Reliable deployment of large language models (LLMs) requires accurate uncertainty estimation. Existing methods are predominantly answer-first, producing confidence only after generating an answer, which measure the correctness of a specific response and limits practical usability....
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
arXiv:2603.05890v1 Announce Type: new Abstract: What happens when a storyteller forgets its own story? Large Language Models (LLMs) can now generate narratives spanning tens of thousands of words, but they often fail to maintain consistency throughout. When generating long-form narratives,...
Learning Next Action Predictors from Human-Computer Interaction
arXiv:2603.05923v1 Announce Type: new Abstract: Truly proactive AI systems must anticipate what we will do next. This foresight demands far richer information than the sparse signals we type into our prompts -- it demands reasoning over the entire context of...
Addressing the Ecological Fallacy in Larger LMs with Human Context
arXiv:2603.05928v1 Announce Type: new Abstract: Language model training and inference ignore a fundamental linguistic fact -- there is a dependence between multiple sequences of text written by the same person. Prior work has shown that addressing this form of \textit{ecological...
ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning
arXiv:2603.06024v1 Announce Type: new Abstract: Multi-view spatial reasoning remains difficult for current vision-language models. Even when multiple viewpoints are available, models often underutilize cross-view relations and instead rely on single-image shortcuts, leading to fragile performance on viewpoint transformation and occlusion-sensitive...
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...
CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation
arXiv:2603.06183v1 Announce Type: new Abstract: We introduce CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that assesses reports based on diagnostic correctness, contextual relevance, and patient safety. Unlike prior metrics, CRIMSON incorporates full clinical context, including patient...
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...
From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring
arXiv:2603.06424v1 Announce Type: new Abstract: Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2) writing. To...
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...
IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings
arXiv:2603.05556v1 Announce Type: new Abstract: Integer sequences in the OEIS span values from single-digit constants to astronomical factorials and exponentials, making prediction challenging for standard tokenised models that cannot handle out-of-vocabulary values or exploit periodic arithmetic structure. We present IntSeqBERT,...
Autocorrelation effects in a stochastic-process model for decision making via time series
arXiv:2603.05559v1 Announce Type: new Abstract: Decision makers exploiting photonic chaotic dynamics obtained by semiconductor lasers provide an ultrafast approach to solving multi-armed bandit problems by using a temporal optical signal as the driving source for sequential decisions. In such systems,...
Aligning the True Semantics: Constrained Decoupling and Distribution Sampling for Cross-Modal Alignment
arXiv:2603.05566v1 Announce Type: new Abstract: Cross-modal alignment is a crucial task in multimodal learning aimed at achieving semantic consistency between vision and language. This requires that image-text pairs exhibit similar semantics. Traditional algorithms pursue embedding consistency to achieve semantic consistency,...
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...
A Novel Hybrid Heuristic-Reinforcement Learning Optimization Approach for a Class of Railcar Shunting Problems
arXiv:2603.05579v1 Announce Type: new Abstract: Railcar shunting is a core planning task in freight railyards, where yard planners need to disassemble and reassemble groups of railcars to form outbound trains. Classification tracks with access from one side only can be...
Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models
arXiv:2603.05582v1 Announce Type: new Abstract: The issue of algorithmic biases in deep learning has led to the development of various debiasing techniques, many of which perform complex training procedures or dataset manipulation. However, an intriguing question arises: is it possible...
Identifying Adversary Characteristics from an Observed Attack
arXiv:2603.05625v1 Announce Type: new Abstract: When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization) directly affect the ML models while others (e.g., anomaly detection) act within the broader...
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...
Warm Starting State-Space Models with Automata Learning
arXiv:2603.05694v1 Announce Type: new Abstract: We prove that Moore machines can be exactly realized as state-space models (SSMs), establishing a formal correspondence between symbolic automata and these continuous machine learning architectures. These Moore-SSMs preserve both the complete symbolic structure and...
Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy
arXiv:2603.05719v1 Announce Type: new Abstract: Training machine learning models for radioisotope identification using gamma spectroscopy remains an elusive challenge for many practical applications, largely stemming from the difficulty of acquiring and labeling large, diverse experimental datasets. Simulations can mitigate this...
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...