Semantic Containment as a Fundamental Property of Emergent Misalignment
arXiv:2603.04407v1 Announce Type: new Abstract: Fine-tuning language models on narrowly harmful data causes emergent misalignment (EM) -- behavioral failures extending far beyond training distributions. Recent work demonstrates compartmentalization of misalignment behind contextual triggers, but these experiments mixed 97% benign data...
Probing Memes in LLMs: A Paradigm for the Entangled Evaluation World
arXiv:2603.04408v1 Announce Type: new Abstract: Current evaluation paradigms for large language models (LLMs) characterize models and datasets separately, yielding coarse descriptions: items in datasets are treated as pre-labeled entries, and models are summarized by overall scores such as accuracy, together...
Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework
arXiv:2603.04409v1 Announce Type: new Abstract: The evaluation of large language models faces significant challenges. Technical benchmarks often lack real-world relevance, while existing human preference evaluations suffer from unrepresentative sampling, superficial assessment depth, and single-metric reductionism. To address these issues, we...
Additive Multi-Step Markov Chains and the Curse of Dimensionality in Large Language Models
arXiv:2603.04412v1 Announce Type: new Abstract: Large-scale language models (LLMs) operate in extremely high-dimensional state spaces, where both token embeddings and their hidden representations create complex dependencies that are not easily reduced to classical Markov structures. In this paper, we explore...
Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries
arXiv:2603.04413v1 Announce Type: new Abstract: Meaning in human language is relational, context dependent, and emergent, arising from dynamic systems of signs rather than fixed word-concept mappings. In computational settings, this semiotic and interpretive complexity complicates the generation and evaluation of...
Multiclass Hate Speech Detection with RoBERTa-OTA: Integrating Transformer Attention and Graph Convolutional Networks
arXiv:2603.04414v1 Announce Type: new Abstract: Multiclass hate speech detection across demographic categories remains computationally challenging due to implicit targeting strategies and linguistic variability in social media content. Existing approaches rely solely on learned representations from training data, without explicitly incorporating...
Context-Dependent Affordance Computation in Vision-Language Models
arXiv:2603.04419v1 Announce Type: new Abstract: We characterize the phenomenon of context-dependent affordance computation in vision-language models (VLMs). Through a large-scale computational study (n=3,213 scene-context pairs from COCO-2017) using Qwen-VL 30B and LLaVA-1.5-13B subject to systematic context priming across 7 agentic...
Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?
arXiv:2603.04421v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis, leveraging collaboration among agents to refine medical reasoning. However, most existing frameworks rely on single-vendor teams (e.g., multiple agents from...
What Is Missing: Interpretable Ratings for Large Language Model Outputs
arXiv:2603.04429v1 Announce Type: new Abstract: Current Large Language Model (LLM) preference learning methods such as Proximal Policy Optimization and Direct Preference Optimization learn from direct rankings or numerical ratings of model outputs, these rankings are subjective, and a single numerical...
A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science
arXiv:2603.04452v1 Announce Type: new Abstract: To advance foundation Large Language Models (LLMs) for combustion science, this study presents the first end-to-end framework for developing domain-specialized models for the combustion community. The framework comprises an AI-ready multimodal knowledge base at the...
Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models
arXiv:2603.04453v1 Announce Type: new Abstract: The use of multimodal large language models has become widespread, and as such the study of these models and their failure points has become of utmost importance. We study a novel mode of failure that...
From Static Inference to Dynamic Interaction: Navigating the Landscape of Streaming Large Language Models
arXiv:2603.04592v1 Announce Type: new Abstract: Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in dynamic, real-time scenarios. To address this gap, the streaming LLM paradigm has emerged. However, existing definitions...
Coordinated Semantic Alignment and Evidence Constraints for Retrieval-Augmented Generation with Large Language Models
arXiv:2603.04647v1 Announce Type: new Abstract: Retrieval augmented generation mitigates limitations of large language models in factual consistency and knowledge updating by introducing external knowledge. However, practical applications still suffer from semantic misalignment between retrieved results and generation objectives, as well...
iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics
arXiv:2603.04656v1 Announce Type: new Abstract: With the emergence of search-enabled generative QA systems, users are increasingly turning to tools that browse, aggregate, and reconcile evidence across multiple sources on their behalf. Yet many widely used QA benchmarks remain answerable by...
Optimizing Language Models for Crosslingual Knowledge Consistency
arXiv:2603.04678v1 Announce Type: new Abstract: Large language models are known to often exhibit inconsistent knowledge. This is particularly problematic in multilingual scenarios, where models are likely to be asked similar questions in different languages, and inconsistent responses can undermine their...
AI-Assisted Moot Courts: Simulating Justice-Specific Questioning in Oral Arguments
arXiv:2603.04718v1 Announce Type: new Abstract: In oral arguments, judges probe attorneys with questions about the factual record, legal claims, and the strength of their arguments. To prepare for this questioning, both law schools and practicing attorneys rely on moot courts:...
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
arXiv:2603.04759v1 Announce Type: new Abstract: The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data...
TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings
arXiv:2603.04772v1 Announce Type: new Abstract: Despite the exceptional reasoning capabilities of Multimodal Large Language Models (MLLMs), their adaptation into universal embedding models is significantly impeded by task conflict. To address this, we propose TSEmbed, a universal multimodal embedding framework that...
Attention's Gravitational Field:A Power-Law Interpretation of Positional Correlation
arXiv:2603.04805v1 Announce Type: new Abstract: This paper explores the underlying principles of positional relationships and encodings within Large Language Models (LLMs) and introduces the concept of the Attention Gravitational Field (AGF). By decoupling positional encodings from semantic embeddings, we optimize...
Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses
arXiv:2603.04820v1 Announce Type: new Abstract: Automated short-answer scoring lags other LLM applications. We meta-analyze 890 culminating results across a systematic review of LLM short-answer scoring studies, modeling the traditional effect size of Quadratic Weighted Kappa (QWK) with mixed effects metaregression....
HACHIMI: Scalable and Controllable Student Persona Generation via Orchestrated Agents
arXiv:2603.04855v1 Announce Type: new Abstract: Student Personas (SPs) are emerging as infrastructure for educational LLMs, yet prior work often relies on ad-hoc prompting or hand-crafted profiles with limited control over educational theory and population distributions. We formalize this as Theory-Aligned...
Free Lunch for Pass@$k$? Low Cost Diverse Sampling for Diffusion Language Models
arXiv:2603.04893v1 Announce Type: new Abstract: Diverse outputs in text generation are necessary for effective exploration in complex reasoning tasks, such as code generation and mathematical problem solving. Such Pass@$k$ problems benefit from distinct candidates covering the solution space. However, traditional...
AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection
arXiv:2603.04921v1 Announce Type: new Abstract: This paper presents a novel agentic LLM pipeline for SemEval-2026 Task 10 that jointly extracts psycholinguistic conspiracy markers and detects conspiracy endorsement. Unlike traditional classifiers that conflate semantic reasoning with structural localization, our decoupled design...
AILS-NTUA at SemEval-2026 Task 3: Efficient Dimensional Aspect-Based Sentiment Analysis
arXiv:2603.04933v1 Announce Type: new Abstract: In this paper, we present AILS-NTUA system for Track-A of SemEval-2026 Task 3 on Dimensional Aspect-Based Sentiment Analysis (DimABSA), which encompasses three complementary problems: Dimensional Aspect Sentiment Regression (DimASR), Dimensional Aspect Sentiment Triplet Extraction (DimASTE),...
Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognition
arXiv:2603.04945v1 Announce Type: new Abstract: Training automatic speech recognition (ASR) models increasingly relies on decentralized federated learning to ensure data privacy and accessibility, producing multiple local models that require effective merging. In hybrid ASR systems, while acoustic models can be...
When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
arXiv:2603.04968v1 Announce Type: new Abstract: Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether a weak LLM can...
VRM: Teaching Reward Models to Understand Authentic Human Preferences
arXiv:2603.04974v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on directly mapping...
ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts
arXiv:2603.04992v1 Announce Type: new Abstract: The safety evaluation of large language models (LLMs) remains largely centered on English, leaving non-English languages and culturally grounded risks underexplored. In this work, we investigate LLM safety in the context of the Thai language...
Decorrelating the Future: Joint Frequency Domain Learning for Spatio-temporal Forecasting
arXiv:2603.04418v1 Announce Type: new Abstract: Standard direct forecasting models typically rely on point-wise objectives such as Mean Squared Error, which fail to capture the complex spatio-temporal dependencies inherent in graph-structured signals. While recent frequency-domain approaches such as FreDF mitigate temporal...
Machine Learning for Complex Systems Dynamics: Detecting Bifurcations in Dynamical Systems with Deep Neural Networks
arXiv:2603.04420v1 Announce Type: new Abstract: Critical transitions are the abrupt shifts between qualitatively different states of a system, and they are crucial to understanding tipping points in complex dynamical systems across ecology, climate science, and biology. Detecting these shifts typically...