BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs
arXiv:2603.11991v1 Announce Type: new Abstract: Zero-shot text classification (ZSC) offers the promise of eliminating costly task-specific annotation by matching texts directly to human-readable label descriptions. While early approaches have predominantly relied on cross-encoder models fine-tuned for natural language inference (NLI),...
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...
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...
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,...
Representation Finetuning for Continual Learning
arXiv:2603.11201v1 Announce Type: new Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams. While pre-trained models have shown powerful performance in continual learning, they still require finetuning to adapt effectively...
Beyond the Class Subspace: Teacher-Guided Training for Reliable Out-of-Distribution Detection in Single-Domain Models
arXiv:2603.11269v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection methods perform well on multi-domain benchmarks, yet many practical systems are trained on single-domain data. We show that this regime induces a geometric failure mode, Domain-Sensitivity Collapse (DSC): supervised training compresses features...
Duration Aware Scheduling for ASR Serving Under Workload Drift
arXiv:2603.11273v1 Announce Type: new Abstract: Scheduling policies in large-scale Automatic Speech Recognition (ASR) serving pipelines play a key role in determining end-to-end (E2E) latency. Yet, widely used serving engines rely on first-come-first-served (FCFS) scheduling, which ignores variability in request duration...
Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verification
arXiv:2603.11372v1 Announce Type: new Abstract: Mechanical ventilation (MV) is a life-saving intervention for patients with acute respiratory failure (ARF) in the ICU. However, inappropriate ventilator settings could cause ventilator-induced lung injury (VILI). Also, clinicians workload is shown to be directly...
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...
A writer is suing Grammarly for turning her and other authors into ‘AI editors’ without consent
Journalist Julia Angwin is leading a class action lawsuit against Grammarly for violating her privacy and publicity rights.
Explainable LLM Unlearning Through Reasoning
arXiv:2603.09980v1 Announce Type: cross Abstract: LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference alignment, it offers a more explicit way by removing undesirable knowledge characterized by specific unlearning...
Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations
arXiv:2603.09988v1 Announce Type: cross Abstract: Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level analysis and natural language explanations by (i) identifying...
Emulating Clinician Cognition via Self-Evolving Deep Clinical Research
arXiv:2603.10677v1 Announce Type: new Abstract: Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as single-pass retrospective prediction while...
The System Hallucination Scale (SHS): A Minimal yet Effective Human-Centered Instrument for Evaluating Hallucination-Related Behavior in Large Language Models
arXiv:2603.09989v1 Announce Type: cross Abstract: We introduce the System Hallucination Scale (SHS), a lightweight and human-centered measurement instrument for assessing hallucination-related behavior in large language models (LLMs). Inspired by established psychometric tools such as the System Usability Scale (SUS) and...
TAMUSA-Chat: A Domain-Adapted Large Language Model Conversational System for Research and Responsible Deployment
arXiv:2603.09992v1 Announce Type: cross Abstract: This paper presents TAMUSA-Chat, a research-oriented framework for building domain-adapted large language model conversational systems. The work addresses critical challenges in adapting general-purpose foundation models to institutional contexts through supervised fine-tuning, retrieval-augmented generation, and systematic...
RedFuser: An Automatic Operator Fusion Framework for Cascaded Reductions on AI Accelerators
arXiv:2603.10026v1 Announce Type: cross Abstract: Operator fusion, as a key performance optimization technique in the deployment of AI models, significantly improves execution efficiency and has been widely adopted in modern AI compilers. However, for cascaded reduction operations involving multiple loops...
The DMA Streaming Framework: Kernel-Level Buffer Orchestration for High-Performance AI Data Paths
arXiv:2603.10030v1 Announce Type: cross Abstract: AI transport libraries move bytes efficiently, but they commonly assume that buffers are already correctly allocated, placed, shared, registered, and safe under completion and teardown pressure. This paper presents dmaplane, a Linux kernel module that...
GhazalBench: Usage-Grounded Evaluation of LLMs on Persian Ghazals
arXiv:2603.09979v1 Announce Type: new Abstract: Persian poetry plays an active role in Iranian cultural practice, where verses by canonical poets such as Hafez are frequently quoted, paraphrased, or completed from partial cues. Supporting such interactions requires language models to engage...
Large Language Models and Book Summarization: Reading or Remembering, Which Is Better?
arXiv:2603.09981v1 Announce Type: new Abstract: Summarization is a core task in Natural Language Processing (NLP). Recent advances in Large Language Models (LLMs) and the introduction of large context windows reaching millions of tokens make it possible to process entire books...
GATech at AbjadGenEval Shared Task: Multilingual Embeddings for Arabic Machine-Generated Text Classification
arXiv:2603.10007v1 Announce Type: new Abstract: We present our approach to the AbjadGenEval shared task on detecting AI-generated Arabic text. We fine-tuned the multilingual E5-large encoder for binary classification, and we explored several pooling strategies to pool token representations, including weighted...
Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights
arXiv:2603.10033v1 Announce Type: new Abstract: Graph foundation models (GFM) aim to acquire transferable knowledge by pre-training on diverse graphs, which can be adapted to various downstream tasks. However, domain shift in graphs is inherently two-dimensional: graphs differ not only in...
The Generation-Recognition Asymmetry: Six Dimensions of a Fundamental Divide in Formal Language Theory
arXiv:2603.10139v1 Announce Type: new Abstract: Every formal grammar defines a language and can in principle be used in three ways: to generate strings (production), to recognize them (parsing), or -- given only examples -- to infer the grammar itself (grammar...
GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning
arXiv:2603.10243v1 Announce Type: new Abstract: Recent studies show that the safety alignment of large language models (LLMs) can be easily compromised even by seemingly non-adversarial fine-tuning. To preserve safety alignment during fine-tuning, a widely used strategy is to jointly optimize...
InFusionLayer: a CFA-based ensemble tool to generate new classifiers for learning and modeling
arXiv:2603.10049v1 Announce Type: new Abstract: Ensemble learning is a well established body of methods for machine learning to enhance predictive performance by combining multiple algorithms/models. Combinatorial Fusion Analysis (CFA) has provided method and practice for combining multiple scoring systems, using...
HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
arXiv:2603.10067v1 Announce Type: new Abstract: Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon's orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and over-emphasizes...
Improving Search Agent with One Line of Code
arXiv:2603.10069v1 Announce Type: new Abstract: Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools for a multi-turn information-seeking process autonomously. However, we identify a critical training instability that leads...
Lost in the Middle at Birth: An Exact Theory of Transformer Position Bias
arXiv:2603.10123v1 Announce Type: new Abstract: The ``Lost in the Middle'' phenomenon -- a U-shaped performance curve where LLMs retrieve well from the beginning and end of a context but fail in the middle -- is widely attributed to learned Softmax...
DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation Learning
arXiv:2603.10180v1 Announce Type: new Abstract: The growing adoption of electronic health record (EHR) systems has provided unprecedented opportunities for predictive modeling to guide clinical decision making. Structured EHRs contain longitudinal observations of patients across hospital visits, where each visit is...
Variance-Aware Adaptive Weighting for Diffusion Model Training
arXiv:2603.10391v1 Announce Type: new Abstract: Diffusion models have recently achieved remarkable success in generative modeling, yet their training dynamics across different noise levels remain highly imbalanced, which can lead to inefficient optimization and unstable learning behavior. In this work, we...
On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
arXiv:2603.10397v1 Announce Type: new Abstract: One crucial factor behind the success of deep learning lies in the implicit bias induced by noise inherent in gradient-based training algorithms. Motivated by empirical observations that training with noisy labels improves model generalization, we...