Dual Length Codes for Lossless Compression of BFloat16
arXiv:2602.17849v1 Announce Type: new Abstract: Training and serving Large Language Models (LLMs) relies heavily on parallelization and collective operations, which are frequently bottlenecked by network bandwidth. Lossless compression using e.g., Huffman codes can alleviate the issue, however, Huffman codes suffer...
Distribution-Free Sequential Prediction with Abstentions
arXiv:2602.17918v1 Announce Type: new Abstract: We study a sequential prediction problem in which an adversary is allowed to inject arbitrarily many adversarial instances in a stream of i.i.d.\ instances, but at each round, the learner may also \emph{abstain} from making...
LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets
arXiv:2602.13209v1 Announce Type: cross Abstract: We introduce LemonadeBench v0.5, a minimal benchmark for evaluating economic intuition, long-term planning, and decision-making under uncertainty in large language models (LLMs) through a simulated lemonade stand business. Models must manage inventory with expiring goods,...
CircuChain: Disentangling Competence and Compliance in LLM Circuit Analysis
arXiv:2602.15037v1 Announce Type: cross Abstract: As large language models (LLMs) advance toward expert-level performance in engineering domains, reliable reasoning under user-specified constraints becomes critical. In circuit analysis, for example, a numerically correct solution is insufficient if it violates established methodological...
Safe-SDL:Establishing Safety Boundaries and Control Mechanisms for AI-Driven Self-Driving Laboratories
arXiv:2602.15061v1 Announce Type: cross Abstract: The emergence of Self-Driving Laboratories (SDLs) transforms scientific discovery methodology by integrating AI with robotic automation to create closed-loop experimental systems capable of autonomous hypothesis generation, experimentation, and analysis. While promising to compress research timelines...
Structural Divergence Between AI-Agent and Human Social Networks in Moltbook
arXiv:2602.15064v1 Announce Type: cross Abstract: Large populations of AI agents are increasingly embedded in online environments, yet little is known about how their collective interaction patterns compare to human social systems. Here, we analyze the full interaction network of Moltbook,...
StrokeNeXt: A Siamese-encoder Approach for Brain Stroke Classification in Computed Tomography Imagery
arXiv:2602.15087v1 Announce Type: cross Abstract: We present StrokeNeXt, a model for stroke classification in 2D Computed Tomography (CT) images. StrokeNeXt employs a dual-branch design with two ConvNeXt encoders, whose features are fused through a lightweight convolutional decoder based on stacked...
Far Out: Evaluating Language Models on Slang in Australian and Indian English
arXiv:2602.15373v1 Announce Type: new Abstract: Language models exhibit systematic performance gaps when processing text in non-standard language varieties, yet their ability to comprehend variety-specific slang remains underexplored for several languages. We present a comprehensive evaluation of slang awareness in Indian...
In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations
arXiv:2602.15456v1 Announce Type: new Abstract: Agents based on Large Language Models (LLMs) are increasingly being deployed as interfaces to information on online platforms. These agents filter, prioritize, and synthesize information retrieved from the platforms' back-end databases or via web search....
ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling
arXiv:2602.15537v1 Announce Type: new Abstract: Pure speech language models aim to learn language directly from raw audio without textual resources. A key challenge is that discrete tokens from self-supervised speech encoders result in excessively long sequences, motivating recent work on...
How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment
arXiv:2602.16039v1 Announce Type: new Abstract: The rapid rise of large language models (LLMs) is reshaping the landscape of automatic assessment in education. While these systems demonstrate substantial advantages in adaptability to diverse question types and flexibility in output formats, they...
EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices
arXiv:2602.15836v1 Announce Type: cross Abstract: Large Action Models (LAMs) have shown immense potential in autonomous navigation by bridging high-level reasoning with low-level control. However, deploying these multi-billion parameter models on edge devices remains a significant challenge due to memory constraints...
Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
arXiv:2602.15847v1 Announce Type: cross Abstract: Personality steering in large language models (LLMs) commonly relies on injecting trait-specific steering vectors, implicitly assuming that personality traits can be controlled independently. In this work, we examine whether this assumption holds by analysing the...
Building Safe and Deployable Clinical Natural Language Processing under Temporal Leakage Constraints
arXiv:2602.15852v1 Announce Type: cross Abstract: Clinical natural language processing (NLP) models have shown promise for supporting hospital discharge planning by leveraging narrative clinical documentation. However, note-based models are particularly vulnerable to temporal and lexical leakage, where documentation artifacts encode future...
IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentation
arXiv:2602.15878v1 Announce Type: cross Abstract: In industrial scenarios, data augmentation is an effective approach to improve model performance. However, its benefits are not unidirectionally beneficial. There is no theoretical research or established estimation for the optimal sample size (OSS) in...
FUTURE-VLA: Forecasting Unified Trajectories Under Real-time Execution
arXiv:2602.15882v1 Announce Type: cross Abstract: General vision-language models increasingly support unified spatiotemporal reasoning over long video streams, yet deploying such capabilities on robots remains constrained by the prohibitive latency of processing long-horizon histories and generating high-dimensional future predictions. To bridge...
Doc-to-LoRA: Learning to Instantly Internalize Contexts
arXiv:2602.15902v1 Announce Type: cross Abstract: Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow. While context distillation (CD) can...
RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
arXiv:2602.17053v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability and trust. We introduce a formal framework for reasoning faithfulness, defined...
How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses
arXiv:2602.17084v1 Announce Type: new Abstract: The rapid adoption of large language models has led to the emergence of AI coding agents that autonomously create pull requests on GitHub. However, how these agents differ in their pull request description characteristics, and...
Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)
arXiv:2602.17107v1 Announce Type: new Abstract: Shapley value-based methods have become foundational in explainable artificial intelligence (XAI), offering theoretically grounded feature attributions through cooperative game theory. However, in practice, particularly in vision tasks, the assumption of feature independence breaks down, as...
Towards Cross-lingual Values Assessment: A Consensus-Pluralism Perspective
arXiv:2602.17283v1 Announce Type: new Abstract: While large language models (LLMs) have become pivotal to content safety, current evaluation paradigms primarily focus on detecting explicit harms (e.g., violence or hate speech), neglecting the subtler value dimensions conveyed in digital content. To...
ABCD: All Biases Come Disguised
arXiv:2602.17445v1 Announce Type: new Abstract: Multiple-choice question (MCQ) benchmarks have been a standard evaluation practice for measuring LLMs' ability to reason and answer knowledge-based questions. Through a synthetic NonsenseQA benchmark, we observe that different LLMs exhibit varying degrees of label-position-few-shot-prompt...
Auditing Reciprocal Sentiment Alignment: Inversion Risk, Dialect Representation and Intent Misalignment in Transformers
arXiv:2602.17469v1 Announce Type: new Abstract: The core theme of bidirectional alignment is ensuring that AI systems accurately understand human intent and that humans can trust AI behavior. However, this loop fractures significantly across language barriers. Our research addresses Cross-Lingual Sentiment...
Unmasking the Factual-Conceptual Gap in Persian Language Models
arXiv:2602.17623v1 Announce Type: new Abstract: While emerging Persian NLP benchmarks have expanded into pragmatics and politeness, they rarely distinguish between memorized cultural facts and the ability to reason about implicit social norms. We introduce DivanBench, a diagnostic benchmark focused on...
Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking
arXiv:2602.17653v1 Announce Type: new Abstract: Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities in human languages, particularly for syntactic phenomena such as word order. In this paper, we...
Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
arXiv:2602.16740v1 Announce Type: new Abstract: In mechanistic interpretability, recent work scrutinizes transformer "circuits" - sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid-tested for their stability across different instances...
Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
arXiv:2602.16793v1 Announce Type: new Abstract: In the past year, custom and unreleased math reasoning models reached gold medal performance on the International Mathematical Olympiad (IMO). Similar performance was then reported using large-scale inference on publicly available models but at prohibitive...
Discovering Universal Activation Directions for PII Leakage in Language Models
arXiv:2602.16980v1 Announce Type: new Abstract: Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information (PII) leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability...
Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
arXiv:2602.17063v1 Announce Type: new Abstract: Sub-bit model compression seeks storage below one bit per weight; as magnitudes are aggressively compressed, the sign bit becomes a fixed-cost bottleneck. Across Transformers, CNNs, and MLPs, learned sign matrices resist low-rank approximation and are...
Multi-source Heterogeneous Public Opinion Analysis via Collaborative Reasoning and Adaptive Fusion: A Systematically Integrated Approach
arXiv:2602.15857v1 Announce Type: new Abstract: The analysis of public opinion from multiple heterogeneous sources presents significant challenges due to structural differences, semantic variations, and platform-specific biases. This paper introduces a novel Collaborative Reasoning and Adaptive Fusion (CRAF) framework that systematically...