How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing
arXiv:2603.13259v1 Announce Type: new Abstract: When a language model is fed a wrong answer, what happens inside the network? Current understanding treats truthfulness as a static property of individual-layer representations-a direction to be probed, a feature to be extracted. Less...
Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities
arXiv:2603.13651v1 Announce Type: new Abstract: Bibliographic reference extraction and parsing are foundational for citation indexing, linking, and downstream scholarly knowledge-graph construction. However, most established evaluations focus on clean, English, end-of-document bibliographies, and therefore underrepresent the Social Sciences and Humanities (SSH),...
Intelligent Materials Modelling: Large Language Models Versus Partial Least Squares Regression for Predicting Polysulfone Membrane Mechanical Performance
arXiv:2603.13834v1 Announce Type: new Abstract: Predicting the mechanical properties of polysulfone (PSF) membranes from structural descriptors remains challenging due to extreme data scarcity typical of experimental studies. To investigate this issue, this study benchmarked knowledge-driven inference using four large language...
Executable Archaeology: Reanimating the Logic Theorist from its IPL-V Source
arXiv:2603.13514v1 Announce Type: new Abstract: The Logic Theorist (LT), created by Allen Newell, J. C. Shaw, and Herbert Simon in 1955-1956, is widely regarded as the first artificial intelligence program. While the original conceptual model was described in 1956, it...
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent
arXiv:2603.13875v1 Announce Type: new Abstract: Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative is ompressive memory: read...
FLUX: Data Worth Training On
arXiv:2603.13972v1 Announce Type: new Abstract: Modern large language model training is no longer limited by data availability, but by the inability of existing preprocessing pipelines to simultaneously achieve massive scale and high data quality. Current approaches are forced to sacrifice...
Translational Gaps in Graph Transformers for Longitudinal EHR Prediction: A Critical Appraisal of GT-BEHRT
arXiv:2603.13231v1 Announce Type: new Abstract: Transformer-based models have improved predictive modeling on longitudinal electronic health records through large-scale self-supervised pretraining. However, most EHR transformer architectures treat each clinical encounter as an unordered collection of codes, which limits their ability to...
Beyond Attention: True Adaptive World Models via Spherical Kernel Operator
arXiv:2603.13263v1 Announce Type: new Abstract: The pursuit of world model based artificial intelligence has predominantly relied on projecting high-dimensional observations into parameterized latent spaces, wherein transition dynamics are subsequently learned. However, this conventional paradigm is mathematically flawed: it merely displaces...
Learning Retrieval Models with Sparse Autoencoders
arXiv:2603.13277v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned Sparse Retrieval (LSR),...
FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
arXiv:2603.13282v1 Announce Type: new Abstract: Federated Learning (FL) with Low-Rank Adaptation (LoRA) has become a standard for privacy-preserving LLM fine-tuning. However, existing personalized methods predominantly operated under a restrictive Flat-Model Assumption: they addressed client-side \textit{statistical heterogeneity} but treated the model...
Brittlebench: Quantifying LLM robustness via prompt sensitivity
arXiv:2603.13285v1 Announce Type: new Abstract: Existing evaluation methods largely rely on clean, static benchmarks, which can overestimate true model performance by failing to capture the noise and variability inherent in real-world user inputs. This is especially true for language models,...
FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis
arXiv:2603.13291v1 Announce Type: new Abstract: Multimodal sentiment analysis in federated learning environments faces significant challenges due to missing modalities, heterogeneous data distributions, and unreliable client updates. Existing federated approaches often struggle to maintain robust performance under these practical conditions. In...
A Robust Framework for Secure Cardiovascular Risk Prediction: An Architectural Case Study of Differentially Private Federated Learning
arXiv:2603.13293v1 Announce Type: new Abstract: Accurate cardiovascular risk prediction is crucial for preventive healthcare; however, the development of robust Artificial Intelligence (AI) models is hindered by the fragmentation of clinical data across institutions due to stringent privacy regulations. This paper...
Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training
arXiv:2603.13297v1 Announce Type: new Abstract: Atrial fibrillation (AF) is a major complication following embolic stroke of undetermined source (ESUS), elevating the risk of recurrent stroke and mortality. Early identification is clinically important, yet existing tools face limitations in accuracy, scalability,...
DreamReader: An Interpretability Toolkit for Text-to-Image Models
arXiv:2603.13299v1 Announce Type: new Abstract: Despite the rapid adoption of text-to-image (T2I) diffusion models, causal and representation-level analysis remains fragmented and largely limited to isolated probing techniques. To address this gap, we introduce DreamReader: a unified framework that formalizes diffusion...
Residual Stream Analysis of Overfitting And Structural Disruptions
arXiv:2603.13318v1 Announce Type: new Abstract: Ensuring that large language models (LLMs) remain both helpful and harmless poses a significant challenge: fine-tuning on repetitive safety datasets, where unsafe prompts are paired with standard refusal templates, often leads to false refusals, in...
Feature-level Interaction Explanations in Multimodal Transformers
arXiv:2603.13326v1 Announce Type: new Abstract: Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision. Most existing multimodal explainable AI (MXAI) methods extend unimodal saliency to multimodal backbones, highlighting important tokens or patches within each modality,...
AdaBox: Adaptive Density-Based Box Clustering with Parameter Generalization
arXiv:2603.13339v1 Announce Type: new Abstract: Density-based clustering algorithms like DBSCAN and HDBSCAN are foundational tools for discovering arbitrarily shaped clusters, yet their practical utility is undermined by acute hyperparameter sensitivity -- parameters tuned on one dataset frequently fail to transfer...
PolyGLU: State-Conditional Activation Routing in Transformer Feed-Forward Networks
arXiv:2603.13347v1 Announce Type: new Abstract: Biological neural systems employ diverse neurotransmitters -- glutamate, GABA, dopamine, acetylcholine -- to implement distinct signal-processing modalities within shared neural circuits. In contrast, modern transformers apply a single fixed activation function across all feed-forward neurons....
SCOTUStoday: Trump v. the Fed
Six years ago today, the court announced that it was postponing its March argument session in response to the COVID-19 pandemic. The press release noted that its “postponement of argument […]The postSCOTUStoday: Trump v. the Fedappeared first onSCOTUSblog.
When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO
arXiv:2603.13134v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has emerged as an effective method for training reasoning models. While it computes advantages based on group mean, GRPO treats each output as an independent sample during the optimization and...
Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation
arXiv:2603.13099v1 Announce Type: new Abstract: We introduce **CRYSTAL** (*__C__lear __R__easoning via __Y__ielded __S__teps, __T__raceability and __L__ogic*), a diagnostic benchmark with 6,372 instances that evaluates multimodal reasoning through verifiable intermediate steps. We propose two complementary metrics: *Match F1*, which scores step-level...
Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation
arXiv:2603.13017v1 Announce Type: new Abstract: Long conversations with an AI agent create a simple problem for one user: the history is useful, but carrying it verbatim is expensive. We study personalized agent memory: one user's conversation history with an agent,...
Efficient Reasoning with Balanced Thinking
arXiv:2603.12372v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths despite inherent capabilities. These issues...
GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
arXiv:2603.12275v1 Announce Type: new Abstract: Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and digest training data at scale, raising more significant issues regarding safety, privacy, and intellectual...
From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
arXiv:2603.12664v1 Announce Type: new Abstract: Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fusion: textual descriptions express temporal impacts implicitly and qualitatively, whereas forecasting models rely on explicit and...
Experimental evidence of progressive ChatGPT models self-convergence
arXiv:2603.12683v1 Announce Type: new Abstract: Large Language Models (LLMs) that undergo recursive training on synthetically generated data are susceptible to model collapse, a phenomenon marked by the generation of meaningless output. Existing research has examined this issue from either theoretical...
A Method for Learning Large-Scale Computational Construction Grammars from Semantically Annotated Corpora
arXiv:2603.12754v1 Announce Type: new Abstract: We present a method for learning large-scale, broad-coverage construction grammars from corpora of language use. Starting from utterances annotated with constituency structure and semantic frames, the method facilitates the learning of human-interpretable computational construction grammars...
Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
arXiv:2603.12565v1 Announce Type: cross Abstract: SpeechLLMs typically combine ASR-trained encoders with text-based LLM backbones, leading them to inherit written-style output patterns unsuitable for text-to-speech synthesis. This mismatch is particularly pronounced in Japanese, where spoken and written registers differ substantially in...
Generalist Large Language Models for Molecular Property Prediction: Distilling Knowledge from Specialist Models
arXiv:2603.12344v1 Announce Type: new Abstract: Molecular Property Prediction (MPP) is a central task in drug discovery. While Large Language Models (LLMs) show promise as generalist models for MPP, their current performance remains below the threshold for practical adoption. We propose...