Relational In-Context Learning via Synthetic Pre-training with Structural Prior
arXiv:2603.03805v1 Announce Type: new Abstract: Relational Databases (RDBs) are the backbone of modern business, yet they lack foundation models comparable to those in text or vision. A key obstacle is that high-quality RDBs are private, scarce and structurally heterogeneous, making...
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
arXiv:2603.03818v1 Announce Type: new Abstract: Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual learning in relatively...
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration
arXiv:2603.02760v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) have recently attracted significant attention for their ability to enhance diversity, controllability, and parallelism. However, their non-sequential, bidirectionally masked generation makes quality assessment difficult, underscoring the need for effective self-evaluation....
Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments Extraction
arXiv:2603.02909v1 Announce Type: new Abstract: Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents.In the zero-shot setting, existing methods employ LLMs to generate synthetic data to address the challenge posed by...
PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems
arXiv:2603.03054v1 Announce Type: new Abstract: Large language models are increasingly used for patient-facing medical assistance and clinical decision support, but adapting them to clinical dialogue often requires supervision derived from doctor-patient conversations that may contain sensitive information. Conventional supervised fine-tuning...
Routing Absorption in Sparse Attention: Why Random Gates Are Hard to Beat
arXiv:2603.02227v1 Announce Type: cross Abstract: Can a transformer learn which attention entries matter during training? In principle, yes: attention distributions are highly concentrated, and a small gate network can identify the important entries post-hoc with near-perfect accuracy. In practice, barely....
A Directed Graph Model and Experimental Framework for Design and Study of Time-Dependent Text Visualisation
arXiv:2603.02422v1 Announce Type: cross Abstract: Exponential growth in the quantity of digital news, social media, and other textual sources makes it difficult for humans to keep up with rapidly evolving narratives about world events. Various visualisation techniques have been touted...
Is Retraining-Free Enough? The Necessity of Router Calibration for Efficient MoE Compression
arXiv:2603.02217v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models scale capacity efficiently, but their massive parameter footprint creates a deployment-time memory bottleneck. We organize retraining-free MoE compression into three paradigms - Expert Pruning, Expert Editing, and Expert Merging - and show...
Subspace Geometry Governs Catastrophic Forgetting in Low-Rank Adaptation
arXiv:2603.02224v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for adapting large pre-trained models, yet its behavior under continual learning remains poorly understood. We present a geometric theory characterizing catastrophic forgetting in LoRA through the...
Generalized Discrete Diffusion with Self-Correction
arXiv:2603.02230v1 Announce Type: new Abstract: Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such approaches often suffer from limited...
CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles
arXiv:2603.00523v1 Announce Type: new Abstract: Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty. We reframe circuit discovery as an uncertainty-quantification problem...
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging
arXiv:2603.00573v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT methods, particularly MoE-LoRA architectures, suffer from limited parameter efficiency and coarse-grained adaptation due to the...
QQ: A Toolkit for Language Identifiers and Metadata
arXiv:2603.00620v1 Announce Type: new Abstract: The growing number of languages considered in multilingual NLP, including new datasets and tasks, poses challenges regarding properly and accurately reporting which languages are used and how. For example, datasets often use different language identifiers;...
BLUFF: Benchmarking the Detection of False and Synthetic Content across 58 Low-Resource Languages
arXiv:2603.00634v1 Announce Type: new Abstract: Multilingual falsehoods threaten information integrity worldwide, yet detection benchmarks remain confined to English or a few high-resource languages, leaving low-resource linguistic communities without robust defense tools. We introduce BLUFF, a comprehensive benchmark for detecting false...
SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge Graphs
arXiv:2603.00669v1 Announce Type: new Abstract: Sustainability disclosure standards (e.g., GRI, SASB, TCFD, IFRS S2) are comprehensive yet lengthy, terminology-dense, and highly cross-referential, hindering structured analysis and downstream use. We present SSKG Hub (Sustainability Standards Knowledge Graph Hub), a research prototype...
MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine
arXiv:2603.00842v1 Announce Type: new Abstract: Biomedical multimodal assistants have the potential to unify radiology, pathology, and clinical-text reasoning, yet a critical deployment gap remains: top-performing systems are either closed-source or computationally prohibitive, precluding the on-premises deployment required for patient privacy...
GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
arXiv:2603.01059v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled increasingly capable chatbots. However, most existing systems focus on single-user settings and do not generalize well to multi-user group chats, where agents require more proactive and...
How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
arXiv:2603.01070v1 Announce Type: new Abstract: Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logical deductions. Although recent Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities in visual generation and plotting, we...
StaTS: Spectral Trajectory Schedule Learning for Adaptive Time Series Forecasting with Frequency Guided Denoiser
arXiv:2603.00037v1 Announce Type: new Abstract: Diffusion models have been used for probabilistic time series forecasting and show strong potential. However, fixed noise schedules often produce intermediate states that are hard to invert and a terminal state that deviates from the...
Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
arXiv:2603.00042v1 Announce Type: new Abstract: We identify the Spectral Energy Gain in extreme model compression, where low-rank binary approximations outperform tiny-rank floating-point baselines for heavy-tailed spectra. However, prior attempts fail to realize this potential, trailing state-of-the-art 1-bit methods. We attribute...
MAML-KT: Addressing Cold Start Problem in Knowledge Tracing for New Students via Few-Shot Model-Agnostic Meta Learning
arXiv:2603.00137v1 Announce Type: new Abstract: Knowledge tracing (KT) models are commonly evaluated by training on early interactions from all students and testing on later responses. While effective for measuring average predictive performance, this evaluation design obscures a cold start scenario...
Bridging Policy and Real-World Dynamics: LLM-Augmented Rebalancing for Shared Micromobility Systems
arXiv:2603.00176v1 Announce Type: new Abstract: Shared micromobility services such as e-scooters and bikes have become an integral part of urban transportation, yet their efficiency critically depends on effective vehicle rebalancing. Existing methods either optimize for average demand patterns or employ...
Vectorized Adaptive Histograms for Sparse Oblique Forests
arXiv:2603.00326v1 Announce Type: new Abstract: Classification using sparse oblique random forests provides guarantees on uncertainty and confidence while controlling for specific error types. However, they use more data and more compute than other tree ensembles because they create deep trees...
Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols
arXiv:2603.00478v1 Announce Type: new Abstract: Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.However, there lacks a unified, rigorous evaluation protocol that is both challenging and realistic for real-world usage. In this work, we establish FEWTRANS,...
Multi-Agent Causal Reasoning for Suicide Ideation Detection Through Online Conversations
arXiv:2602.23577v1 Announce Type: new Abstract: Suicide remains a pressing global public health concern. While social media platforms offer opportunities for early risk detection through online conversation trees, existing approaches face two major limitations: (1) They rely on predefined rules (e.g.,...
LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning
arXiv:2602.23610v1 Announce Type: new Abstract: The reasoning capability of large language models (LLMs), defined as their ability to analyze, infer, and make decisions based on input information, is essential for building intelligent task-oriented dialogue systems. However, existing benchmarks do not...
Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space
arXiv:2602.23753v1 Announce Type: new Abstract: This study addresses the issues of semantic entanglement, unclear label structure, and insufficient feature representation in few-shot text classification, and proposes an optimization framework based on structured prompts to enhance semantic understanding and task adaptation...
Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysis
arXiv:2602.24060v1 Announce Type: new Abstract: Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across language tasks. We test this claim through a comprehensive evaluation of 504 configurations across seven model families--including...
CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning
arXiv:2602.24142v1 Announce Type: new Abstract: Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning, including screen summary, subtask planning, action decision and action function. However, existing agents struggle to achieve both decoupled enhancement and balanced integration of these...
Task-Centric Acceleration of Small-Language Models
arXiv:2602.24174v1 Announce Type: new Abstract: Small language models (SLMs) have emerged as efficient alternatives to large language models for task-specific applications. However, they are often employed in high-volume, low-latency settings, where efficiency is crucial. We propose TASC, Task-Adaptive Sequence Compression,...