Overcoming the Modality Gap in Context-Aided Forecasting
arXiv:2603.12451v1 Announce Type: new Abstract: Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal models often fail to outperform their...
Asymptotic and Finite-Time Guarantees for Langevin-Based Temperature Annealing in InfoNCE
arXiv:2603.12552v1 Announce Type: new Abstract: The InfoNCE loss in contrastive learning depends critically on a temperature parameter, yet its dynamics under fixed versus annealed schedules remain poorly understood. We provide a theoretical analysis by modeling embedding evolution under Langevin dynamics...
LLMs can construct powerful representations and streamline sample-efficient supervised learning
arXiv:2603.11679v1 Announce Type: new Abstract: As real-world datasets become increasingly complex and heterogeneous, supervised learning is often bottlenecked by input representation design. Modeling multimodal data for downstream tasks, such as time-series, free text, and structured records, often requires non-trivial domain-specific...
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
arXiv:2603.11388v1 Announce Type: new Abstract: Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem where aligned...
Understanding Wikidata Qualifiers: An Analysis and Taxonomy
arXiv:2603.11767v1 Announce Type: new Abstract: This paper presents an in-depth analysis of Wikidata qualifiers, focusing on their semantics and actual usage, with the aim of developing a taxonomy that addresses the challenges of selecting appropriate qualifiers, querying the graph, and...
Improving LLM Performance Through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI
arXiv:2603.11340v1 Announce Type: new Abstract: In this paper, we present a novel black-box online controller that uses only end-to-end measurements over short segments, without internal instrumentation, and hill climbing to maximize goodput, defined as the throughput of requests that satisfy...
BLooP: Zero-Shot Abstractive Summarization using Large Language Models with Bigram Lookahead Promotion
arXiv:2603.11415v1 Announce Type: new Abstract: Abstractive summarization requires models to generate summaries that convey information in the source document. While large language models can generate summaries without fine-tuning, they often miss key details and include extraneous information. We propose BLooP...
The Density of Cross-Persistence Diagrams and Its Applications
arXiv:2603.11623v1 Announce Type: new Abstract: Topological Data Analysis (TDA) provides powerful tools to explore the shape and structure of data through topological features such as clusters, loops, and voids. Persistence diagrams are a cornerstone of TDA, capturing the evolution of...
Artificial Intelligence for Sentiment Analysis of Persian Poetry
arXiv:2603.11254v1 Announce Type: new Abstract: Recent advancements of the Artificial Intelligence (AI) have led to the development of large language models (LLMs) that are capable of understanding, analysing, and creating textual data. These language models open a significant opportunity in...
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
arXiv:2603.11076v1 Announce Type: new Abstract: Recent work synthesizes agentic tasks for post-training tool-using LLMs, yet robust generalization under shifts in tasks and toolsets remains an open challenge. We trace this brittleness to insufficient diversity in synthesized tasks. Scaling diversity is...
MaterialFigBENCH: benchmark dataset with figures for evaluating college-level materials science problem-solving abilities of multimodal large language models
arXiv:2603.11414v1 Announce Type: new Abstract: We present MaterialFigBench, a benchmark dataset designed to evaluate the ability of multimodal large language models (LLMs) to solve university-level materials science problems that require accurate interpretation of figures. Unlike existing benchmarks that primarily rely...
Gender Bias in Generative AI-assisted Recruitment Processes
arXiv:2603.11736v1 Announce Type: new Abstract: In recent years, generative artificial intelligence (GenAI) systems have assumed increasingly crucial roles in selection processes, personnel recruitment and analysis of candidates' profiles. However, the employment of large language models (LLMs) risks reproducing, and in...
QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate
arXiv:2603.11650v1 Announce Type: new Abstract: The effectiveness upper bound of retrieval-augmented generation (RAG) is fundamentally constrained by the semantic integrity and information granularity of text chunks in its knowledge base. To address these challenges, this paper proposes QChunker, which restructures...
SemBench: A Universal Semantic Framework for LLM Evaluation
arXiv:2603.11687v1 Announce Type: new Abstract: Recent progress in Natural Language Processing (NLP) has been driven by the emergence of Large Language Models (LLMs), which exhibit remarkable generative and reasoning capabilities. However, despite their success, evaluating the true semantic understanding of...
CoMMET: To What Extent Can LLMs Perform Theory of Mind Tasks?
arXiv:2603.11915v1 Announce Type: new Abstract: Theory of Mind (ToM)-the ability to reason about the mental states of oneself and others-is a cornerstone of human social intelligence. As Large Language Models (LLMs) become ubiquitous in real-world applications, validating their capacity for...
To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Times
arXiv:2603.12105v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently been shown to produce estimates of psycholinguistic norms, such as valence, arousal, or concreteness, for words and multiword expressions, that correlate with human judgments. These estimates are obtained by...
Long-Context Encoder Models for Polish Language Understanding
arXiv:2603.12191v1 Announce Type: new Abstract: While decoder-only Large Language Models (LLMs) have recently dominated the NLP landscape, encoder-only architectures remain a cost-effective and parameter-efficient standard for discriminative tasks. However, classic encoders like BERT are limited by a short context window,...
Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration
arXiv:2603.12226v1 Announce Type: new Abstract: Despite interdisciplinary research leading to larger and longer-term impact, most work remains confined to single-domain academic silos. Recent AI-based approaches to scientific discovery show promise for interdisciplinary research, but many prioritize rapidly designing experiments and...
Group Resonance Network: Learnable Prototypes and Multi-Subject Resonance for EEG Emotion Recognition
arXiv:2603.11119v1 Announce Type: new Abstract: Electroencephalography(EEG)-basedemotionrecognitionre- mains challenging in cross-subject settings due to severe inter-subject variability. Existing methods mainly learn subject-invariant features, but often under-exploit stimulus-locked group regularities shared across sub- jects. To address this issue, we propose the Group...
Attention Gathers, MLPs Compose: A Causal Analysis of an Action-Outcome Circuit in VideoViT
arXiv:2603.11142v1 Announce Type: new Abstract: The paper explores how video models trained for classification tasks represent nuanced, hidden semantic information that may not affect the final outcome, a key challenge for Trustworthy AI models. Through Explainable and Interpretable AI methods,...
Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
arXiv:2603.11149v1 Announce Type: new Abstract: Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law framework...
Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks
arXiv:2603.11487v1 Announce Type: new Abstract: Transformers often display an attention sink: probability mass concentrates on a fixed, content-agnostic position. We prove that computing a simple trigger-conditional behavior necessarily induces a sink in softmax self-attention models. Our results formalize a familiar...
Live Nation director boasted of gouging ticket buyers, "robbing them blind"
Unsealed messages add wrinkle to trial after US agreed to settle with Live Nation.
Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives
arXiv:2603.09994v1 Announce Type: cross Abstract: Compositionality is considered central to language abilities. As performant language systems, how do large language models (LLMs) do on compositional tasks? We evaluate adjective-noun compositionality in LLMs using two complementary setups: prompt-based functional assessment and...
AraModernBERT: Transtokenized Initialization and Long-Context Encoder Modeling for Arabic
arXiv:2603.09982v1 Announce Type: cross Abstract: Encoder-only transformer models remain widely used for discriminative NLP tasks, yet recent architectural advances have largely focused on English. In this work, we present AraModernBERT, an adaptation of the ModernBERT encoder architecture to Arabic, and...
Empathy Is Not What Changed: Clinical Assessment of Psychological Safety Across GPT Model Generations
arXiv:2603.09997v1 Announce Type: cross Abstract: When OpenAI deprecated GPT-4o in early 2026, thousands of users protested under #keep4o, claiming newer models had "lost their empathy." No published study has tested this claim. We conducted the first clinical measurement, evaluating three...
Assessing Cognitive Biases in LLMs for Judicial Decision Support: Virtuous Victim and Halo Effects
arXiv:2603.10016v1 Announce Type: cross Abstract: We investigate whether large language models (LLMs) display human-like cognitive biases, focusing on potential implications for assistance in judicial sentencing, a decision-making system where fairness is paramount. Two of the most relevant biases were chosen:...
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
arXiv:2603.10384v1 Announce Type: new Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By decomposing reasoning traces into Progress...
The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration
arXiv:2603.09985v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet their ability to accurately assess their own confidence remains poorly understood. We present an empirical study investigating whether LLMs exhibit patterns reminiscent of...