Rethinking Personalization in Large Language Models at the Token Level
arXiv:2603.06595v1 Announce Type: new Abstract: With large language models (LLMs) now performing strongly across diverse tasks, there is growing demand for them to personalize outputs for individual users. Personalization is typically framed as an additional layer on top of a...
Elenchus: Generating Knowledge Bases from Prover-Skeptic Dialogues
arXiv:2603.06974v1 Announce Type: new Abstract: We present Elenchus, a dialogue system for knowledge base construction grounded in inferentialist semantics, where knowledge engineering is re-conceived as explicitation rather than extraction from expert testimony or textual content. A human expert develops a...
A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity
arXiv:2603.06976v1 Announce Type: new Abstract: We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems. In our study, 36 segmentation methods spanning fixed-size, semantic, structure-aware, hierarchical, adaptive,...
Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models
arXiv:2603.07017v1 Announce Type: new Abstract: Safety alignment is critical for deploying large language models (LLMs) in real-world applications, yet most existing approaches rely on large human-annotated datasets and static red-teaming benchmarks that are costly, difficult to scale, and slow to...
AutoChecklist: Composable Pipelines for Checklist Generation and Scoring with LLM-as-a-Judge
arXiv:2603.07019v1 Announce Type: new Abstract: Checklists have emerged as a popular approach for interpretable and fine-grained evaluation, particularly with LLM-as-a-Judge. Beyond evaluation, these structured criteria can serve as signals for model alignment, reinforcement learning, and self-correction. To support these use...
Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin
arXiv:2603.07286v1 Announce Type: new Abstract: Global safety models exhibit strong performance across widely used benchmarks, yet their training data rarely captures the cultural and linguistic nuances of Taiwanese Mandarin. This limitation results in systematic blind spots when interpreting region-specific risks...
Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
arXiv:2603.07368v1 Announce Type: new Abstract: Biases in large language models (LLMs) often manifest as systematic distortions in associations between demographic attributes and professional or social roles, reinforcing harmful stereotypes across gender, ethnicity, and geography. This position paper advocates for addressing...
Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios
arXiv:2603.07372v1 Announce Type: new Abstract: Quality Estimation (QE) is essential for assessing machine translation quality in reference-less settings, particularly for domain-specific and low-resource language scenarios. In this paper, we investigate sentence-level QE for English to Indic machine translation across four...
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
arXiv:2603.07392v1 Announce Type: new Abstract: LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to newly arriving information on the fly. We introduce Online Adaptation to...
Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning
arXiv:2603.07445v1 Announce Type: new Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a...
The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
arXiv:2603.07461v1 Announce Type: new Abstract: Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct components: a token stream updated...
Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs
arXiv:2603.07475v1 Announce Type: new Abstract: Autoregressive (AR) language models form representations incrementally through left-to-right prediction, whereas diffusion language models (dLLMs) are trained via full-sequence denoising. Although recent dLLMs match AR performance, it remains unclear whether diffusion objectives fundamentally reshape internal...
QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis
arXiv:2603.07766v1 Announce Type: new Abstract: We present our system for SemEval-2026 Task 3 on dimensional aspect-based sentiment regression. Our approach combines a hybrid RoBERTa encoder, which jointly predicts sentiment using regression and discretized classification heads, with large language models (LLMs)...
CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
arXiv:2603.06610v1 Announce Type: new Abstract: Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known to induce forgetting, especially in the ubiquitous use-case of leveraging third-party pre-trained models, which...
OptiRoulette Optimizer: A New Stochastic Meta-Optimizer for up to 5.3x Faster Convergence
arXiv:2603.06613v1 Announce Type: new Abstract: This paper presents OptiRoulette, a stochastic meta-optimizer that selects update rules during training instead of fixing a single optimizer. The method combines warmup optimizer locking, random sampling from an active optimizer pool, compatibility-aware learning-rate scaling...
Grouter: Decoupling Routing from Representation for Accelerated MoE Training
arXiv:2603.06626v1 Announce Type: new Abstract: Traditional Mixture-of-Experts (MoE) training typically proceeds without any structural priors, effectively requiring the model to simultaneously train expert weights while searching for an optimal routing policy within a vast combinatorial space. This entanglement often leads...
Leakage Safe Graph Features for Interpretable Fraud Detection in Temporal Transaction Networks
arXiv:2603.06632v1 Announce Type: new Abstract: Illicit transaction detection is often driven by transaction level attributes however, fraudulent behavior may also manifest through network structure such as central hubs, high flow intermediaries, and coordinated neighborhoods. This paper presents a time respecting,...
From Statistical Fidelity to Clinical Consistency: Scalable Generation and Auditing of Synthetic Patient Trajectories
arXiv:2603.06720v1 Announce Type: new Abstract: Access to electronic health records (EHRs) for digital health research is often limited by privacy regulations and institutional barriers. Synthetic EHRs have been proposed as a way to enable safe and sovereign data sharing; however,...
Bi Directional Feedback Fusion for Activity Aware Forecasting of Indoor CO2 and PM2.5
arXiv:2603.06724v1 Announce Type: new Abstract: Indoor air quality (IAQ) forecasting plays a critical role in safeguarding occupant health, ensuring thermal comfort, and supporting intelligent building control. However, predicting future concentrations of key pollutants such as carbon dioxide (CO2) and fine...
Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
arXiv:2603.06727v1 Announce Type: new Abstract: Current safety alignment methods encode safe behavior implicitly within model parameters, creating a fundamental opacity: we cannot easily inspect why a model refuses a request, nor intervene when its safety judgments fail. We propose Safe...
Heterogeneous Decentralized Diffusion Models
arXiv:2603.06741v1 Announce Type: new Abstract: Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly coupled clusters, limiting participation to well-resourced institutions. While Decentralized Diffusion Models (DDM) enable training multiple experts in isolation, existing approaches require 1176 GPU-days...
Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
arXiv:2603.06745v1 Announce Type: new Abstract: Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of oversteering, where...
Artificial Intelligence for Climate Adaptation: Reinforcement Learning for Climate Change-Resilient Transport
arXiv:2603.06278v1 Announce Type: new Abstract: Climate change is expected to intensify rainfall and, consequently, pluvial flooding, leading to increased disruptions in urban transportation systems over the coming decades. Designing effective adaptation strategies is challenging due to the long-term, sequential nature...
Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection
arXiv:2603.05623v1 Announce Type: cross Abstract: Camera-LiDAR fusion is widely used in autonomous driving to enable accurate 3D object detection. However, bird's-eye view (BEV) fusion detectors can degrade significantly under domain shift and sensor failures, limiting reliability in real-world deployment. Existing...
Exploring Human-in-the-Loop Themes in AI Application Development: An Empirical Thematic Analysis
arXiv:2603.05510v1 Announce Type: cross Abstract: Developing and deploying AI applications in organizations is challenging when human decision authority and oversight are underspecified across the system lifecycle. Although Human-in-the-Loop (HITL) and Human-Centered AI (HCAI) principles are widely acknowledged, operational guidance for...
VDCook:DIY video data cook your MLLMs
arXiv:2603.05539v1 Announce Type: cross Abstract: We introduce VDCook: a self-evolving video data operating system, a configurable video data construction platform for researchers and vertical domain teams. Users initiate data requests via natural language queries and adjustable parameters (scale, retrieval-synthesis ratio,...
On the Value of Tokeniser Pretraining in Physics Foundation Models
arXiv:2603.05598v1 Announce Type: cross Abstract: We investigate the impact of tokeniser pretraining on the accuracy and efficiency of physics emulation. Modern high-resolution simulations produce vast volumes of data spanning diverse physical regimes and scales. Training foundation models to learn the...
An Interactive Multi-Agent System for Evaluation of New Product Concepts
arXiv:2603.05980v1 Announce Type: new Abstract: Product concept evaluation is a critical stage that determines strategic resource allocation and project success in enterprises. However, traditional expert-led approaches face limitations such as subjective bias and high time and cost requirements. To support...
Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent
arXiv:2603.05578v1 Announce Type: cross Abstract: Research on self-evolving language agents has accelerated, drawing increasing attention to their ability to create, adapt, and maintain tools from task requirements. However, existing benchmarks predominantly rely on predefined specifications, which limits scalability and hinders...