Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations
arXiv:2603.13264v1 Announce Type: new Abstract: Personalized recommendation increasingly relies on private user data, motivating approaches that can adapt to individuals without centralizing their information. We present Federated Targeted Recommendations with Evolving Knowledge graphs and Language Models (FedTREK-LM), a framework that...
FastODT: A tree-based framework for efficient continual learning
arXiv:2603.13276v1 Announce Type: new Abstract: Machine learning models deployed in real-world settings must operate under evolving data distributions and constrained computational resources. This challenge is particularly acute in non-stationary domains such as energy time series, weather monitoring, and environmental sensing....
From Stochastic Answers to Verifiable Reasoning: Interpretable Decision-Making with LLM-Generated Code
arXiv:2603.13287v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for high-stakes decision-making, yet existing approaches struggle to reconcile scalability, interpretability, and reproducibility. Black-box models obscure their reasoning, while recent LLM-based rule systems rely on per-sample evaluation, causing...
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...
Linear Predictability of Attention Heads in Large Language Models
arXiv:2603.13314v1 Announce Type: new Abstract: Large language model (LLM) inference is increasingly bottlenecked by the Key-Value (KV) cache, yet the fine-grained structure of attention-head activations remains poorly understood. We show that pretrained Transformers exhibit a pervasive inter-head linear structure: for...
Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
arXiv:2603.12298v1 Announce Type: cross Abstract: Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from static activation differences are susceptible to high-dimensional noise and layer-wise semantic drift, often...
On Using Machine Learning to Early Detect Catastrophic Failures in Marine Diesel Engines
arXiv:2603.12733v1 Announce Type: new Abstract: Catastrophic failures of marine engines imply severe loss of functionality and destroy or damage the systems irreversibly. Being sudden and often unpredictable events, they pose a severe threat to navigation, crew, and passengers. The abrupt...
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,...
AI Planning Framework for LLM-Based Web Agents
arXiv:2603.12710v1 Announce Type: new Abstract: Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why...
Optimizing Task Completion Time Updates Using POMDPs
arXiv:2603.12340v1 Announce Type: cross Abstract: Managing announced task completion times is a fundamental control problem in project management. While extensive research exists on estimating task durations and task scheduling, the problem of when and how to update completion times communicated...
Revisiting Model Stitching In the Foundation Model Era
arXiv:2603.12433v1 Announce Type: cross Abstract: Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility. Prior work finds that models trained on...
TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction
arXiv:2603.12500v1 Announce Type: cross Abstract: We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs...
When LLM Judge Scores Look Good but Best-of-N Decisions Fail
arXiv:2603.12520v1 Announce Type: cross Abstract: Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels. This can be misleading when the real deployment task is...
Interpreting Negation in GPT-2: Layer- and Head-Level Causal Analysis
arXiv:2603.12423v1 Announce Type: new Abstract: Negation remains a persistent challenge for modern language models, often causing reversed meanings or factual errors. In this work, we conduct a causal analysis of how GPT-2 Small internally processes such linguistic transformations. We examine...
AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents
arXiv:2603.12564v1 Announce Type: new Abstract: Tool-augmented LLM agents increasingly serve as multi-turn advisors in high-stakes domains, yet their evaluation relies on ranking-quality metrics that measure what is recommended but not whether it is safe for the user. We introduce a...
Continual Learning in Large Language Models: Methods, Challenges, and Opportunities
arXiv:2603.12658v1 Announce Type: new Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static pre-training paradigm...
SteerRM: Debiasing Reward Models via Sparse Autoencoders
arXiv:2603.12795v1 Announce Type: new Abstract: Reward models (RMs) are critical components of alignment pipelines, yet they exhibit biases toward superficial stylistic cues, preferring better-presented responses over semantically superior ones. Existing debiasing methods typically require retraining or architectural modifications, while direct...
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design
arXiv:2603.12826v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scalable source of verifiable data but risk inducing reward hacking, where...
DS$^2$-Instruct: Domain-Specific Data Synthesis for Large Language Models Instruction Tuning
arXiv:2603.12932v1 Announce Type: new Abstract: Adapting Large Language Models (LLMs) to specialized domains requires high-quality instruction tuning datasets, which are expensive to create through human annotation. Existing data synthesis methods focus on general-purpose tasks and fail to capture domain-specific terminology...
Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation
arXiv:2603.13045v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capability in machine translation on high-resource language pairs, yet their performance on low-resource translation still lags behind. Existing post-training methods rely heavily on high-quality parallel data, which are...
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...
A Reduction Algorithm for Markovian Contextual Linear Bandits
arXiv:2603.12530v1 Announce Type: new Abstract: Recent work shows that when contexts are drawn i.i.d., linear contextual bandits can be reduced to single-context linear bandits. This ``contexts are cheap" perspective is highly advantageous, as it allows for sharper finite-time analyses and...
CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstruction
arXiv:2603.12591v1 Announce Type: new Abstract: Federated learning on heterogeneous edge devices requires personalized compression while preserving aggregation compatibility and stable convergence. We present Curvature-Aware Heterogeneous Federated Pruning (CA-HFP), a practical framework that enables each client perform structured, device-specific pruning guided...
Maximizing Incremental Information Entropy for Contrastive Learning
arXiv:2603.12594v1 Announce Type: new Abstract: Contrastive learning has achieved remarkable success in self-supervised representation learning, often guided by information-theoretic objectives such as mutual information maximization. Motivated by the limitations of static augmentations and rigid invariance constraints, we propose IE-CL (Incremental-Entropy...
Google Fiber will be sold to private equity firm and merge with cable company
GFiber and Astound to merge with Alphabet selling majority stake to Stonepeak.
FinRule-Bench: A Benchmark for Joint Reasoning over Financial Tables and Principles
arXiv:2603.11339v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to financial analysis, yet their ability to audit structured financial statements under explicit accounting principles remains poorly explored. Existing benchmarks primarily evaluate question answering, numerical reasoning, or anomaly...
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...
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...
RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents
arXiv:2603.11337v1 Announce Type: new Abstract: LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation pipeline...