arXiv:2604.01366v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal representations and can be mitigated through targeted intervention remains an open question. We define LLM cognitive bias as systematic, reproducible deviations […]
Predicting LLM Output Length via Entropy-Guided Representations
arXiv:2602.11812v2 Announce Type: replace Abstract: The long-tailed distribution of sequence lengths in LLM serving and reinforcement learning (RL) sampling causes significant computational waste due to excessive padding in batched inference. Existing methods rely on auxiliary models for static length prediction, but they incur high overhead, generalize poorly, and fail in stochastic “one-to-many” sampling scenarios. We […]
RIFT: A RubrIc Failure Mode Taxonomy and Automated Diagnostics
arXiv:2604.01375v1 Announce Type: new Abstract: Rubric-based evaluation is widely used in LLM benchmarks and training pipelines for open-ended, less verifiable tasks. While prior work has demonstrated the effectiveness of rubrics using downstream signals such as reinforcement learning outcomes, there remains no principled way to diagnose rubric quality issues from such aggregated or downstream signals alone. […]
LLM-as-a-Judge for Time Series Explanations
arXiv:2604.02118v1 Announce Type: new Abstract: Evaluating factual correctness of LLM generated natural language explanations grounded in time series data remains an open challenge. Although modern models generate textual interpretations of numerical signals, existing evaluation methods are limited: reference based similarity metrics and consistency checking models require ground truth explanations, while traditional time series methods operate […]
Transformer self-attention encoder-decoder with multimodal deep learning for response time series forecasting and digital twin support in wind structural health monitoring
arXiv:2604.01712v1 Announce Type: cross Abstract: The wind-induced structural response forecasting capabilities of a novel transformer methodology are examined here. The model also provides a digital twin component for bridge structural health monitoring. Firstly, the approach uses the temporal characteristics of the system to train a forecasting model. Secondly, the vibration predictions are compared to the […]
The Geometric Anatomy of Capability Acquisition in Transformers
arXiv:2602.15997v4 Announce Type: replace-cross Abstract: Neural networks gain capabilities during training, but the internal changes that precede capability acquisition are not well understood. In particular, the relationship between geometric change and behavioral change, and the effect of task difficulty and model scale on that relationship, is unclear. We track geometric measures and linear probes across […]
MiCA Learns More Knowledge Than LoRA and Full Fine-Tuning
arXiv:2604.01694v1 Announce Type: cross Abstract: Minor Component Adaptation (MiCA) is a novel parameter-efficient fine-tuning method for large language models that focuses on adapting underutilized subspaces of model representations. Unlike conventional methods such as Low-Rank Adaptation (LoRA), which target dominant subspaces, MiCA leverages Singular Value Decomposition to identify subspaces related to minor singular vectors associated with […]
MIRAGE: The Illusion of Visual Understanding
arXiv:2603.21687v3 Announce Type: replace Abstract: Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language reasoning remain surprisingly poorly understood. We report three findings that challenge prevailing assumptions about how these systems process and integrate visual information. First, Frontier models readily generate detailed image descriptions and […]
Retrieval-Augmented Question Answering over Scientific Literature for the Electron-Ion Collider
arXiv:2604.02259v1 Announce Type: cross Abstract: To harness the power of Language Models in answering domain specific specialized technical questions, Retrieval Augmented Generation (RAG) is been used widely. In this work, we have developed a Q&A application inspired by the Retrieval Augmented Generation (RAG), which is comprised of an in-house database indexed on the arXiv articles […]
Understanding visual attention beehind bee-inspired UAV navigation
arXiv:2507.11992v4 Announce Type: replace Abstract: Bio-inspired design is often used in autonomous UAV navigation due to the capacity of biological systems for flight and obstacle avoidance despite limited sensory and computational capabilities. In particular, honeybees mainly use the sensory input of optic flow, the apparent motion of objects in their visual field, to navigate cluttered […]
Rare-Aware Autoencoding: Reconstructing Spatially Imbalanced Data
arXiv:2604.02031v1 Announce Type: cross Abstract: Autoencoders can be challenged by spatially non-uniform sampling of image content. This is common in medical imaging, biology, and physics, where informative patterns occur rarely at specific image coordinates, as background dominates these locations in most samples, biasing reconstructions toward the majority appearance. In practice, autoencoders are biased toward dominant […]
A Self-Improving Architecture for Dynamic Safety in Large Language Models
arXiv:2511.07645v2 Announce Type: replace-cross Abstract: Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to autonomously detect safety failures and synthesize defense policies at runtime, without retraining or manual intervention. Method: We propose the Self-Improving […]