Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
arXiv:2604.05179v1 Announce Type: new Abstract: Large language models (LLMs) remain susceptible to jailbreak and direct prompt-injection attacks, yet the strongest defensive filters frequently over-refuse benign queries and degrade user experience. Previous work on jailbreak and prompt injection detection such as...
MedLayBench-V: A Large-Scale Benchmark for Expert-Lay Semantic Alignment in Medical Vision Language Models
arXiv:2604.05738v1 Announce Type: new Abstract: Medical Vision-Language Models (Med-VLMs) have achieved expert-level proficiency in interpreting diagnostic imaging. However, current models are predominantly trained on professional literature, limiting their ability to communicate findings in the lay register required for patient-centered care....
Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction
arXiv:2604.05477v1 Announce Type: new Abstract: Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency, rendering delays, and system interruptions, this assumption leads...
Do Domain-specific Experts exist in MoE-based LLMs?
arXiv:2604.05267v1 Announce Type: new Abstract: In the era of Large Language Models (LLMs), the Mixture of Experts (MoE) architecture has emerged as an effective approach for training extremely large models with improved computational efficiency. This success builds upon extensive prior...
A Theoretical Framework for Statistical Evaluability of Generative Models
arXiv:2604.05324v1 Announce Type: new Abstract: Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d.\ test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance metrics such as error rate are...
Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling
arXiv:2604.05445v1 Announce Type: new Abstract: Vision-language reward modeling faces a dilemma: generative approaches are interpretable but slow, while discriminative ones are efficient but act as opaque "black boxes." To bridge this gap, we propose VL-MDR (Vision-Language Multi-Dimensional Reward), a framework...
Multilingual Language Models Encode Script Over Linguistic Structure
arXiv:2604.05090v1 Announce Type: new Abstract: Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space, yet the nature of this internal organization remains elusive. In this work, we investigate which linguistic properties -...
Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext
arXiv:2604.05273v1 Announce Type: new Abstract: Human communication is fundamentally creative, and often makes use of subtext -- implied meaning that goes beyond the literal content of the text. Here, we systematically study whether language models can use subtext in communicative...
OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward
arXiv:2604.05514v1 Announce Type: new Abstract: The paradigm of programmable diagram generation is evolving rapidly, playing a crucial role in structured visualization. However, most existing studies are confined to a narrow range of task formulations and language support, constraining their applicability...
Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya
arXiv:2604.04937v1 Announce Type: new Abstract: Large language models produce fluent text but struggle with systematic reasoning, often hallucinating confident but unfounded claims. When Apple researchers added irrelevant context to mathematical problems, LLM performance degraded by 65% Apple Machine Learning Research,...
Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting
arXiv:2604.05540v1 Announce Type: new Abstract: Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring that the model can use...
Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion
arXiv:2604.05688v1 Announce Type: new Abstract: Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention (SWA) can alleviate this bound, but...
From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
arXiv:2604.05348v1 Announce Type: new Abstract: Hallucinations in medical large language models (LLMs) remain a safety-critical issue, particularly when available evidence is insufficient or conflicting. We study this problem in diabetic retinopathy (DR) decision settings and introduce RETINA-SAFE, an evidence-grounded benchmark...
Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition
arXiv:2604.05279v1 Announce Type: new Abstract: Large language models exhibit sycophancy, the tendency to shift their stated positions toward perceived user preferences or authority cues regardless of evidence. Standard alignment methods fail to correct this because scalar reward models conflate two...
Territory Paint Wars: Diagnosing and Mitigating Failure Modes in Competitive Multi-Agent PPO
arXiv:2604.04983v1 Announce Type: new Abstract: We present Territory Paint Wars, a minimal competitive multi-agent reinforcement learning environment implemented in Unity, and use it to systematically investigate failure modes of Proximal Policy Optimisation (PPO) under self-play. A first agent trained for...
EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents
arXiv:2604.05557v1 Announce Type: new Abstract: Scientific research follows multi-turn, multi-step workflows that require proactively searching the literature, consulting figures and tables, and integrating evidence across papers to align experimental settings and support reproducible conclusions. This joint capability is not systematically...
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning
arXiv:2604.05517v1 Announce Type: new Abstract: A fundamental challenge in creative writing lies in reconciling the inherent tension between maintaining global coherence in long-form narratives and preserving local expressiveness in short-form texts. While long-context generation necessitates explicit macroscopic planning, short-form creativity...
Controllable Image Generation with Composed Parallel Token Prediction
arXiv:2604.05730v1 Announce Type: new Abstract: Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked generation (absorbing diffusion) as a special case. Our...
HYVE: Hybrid Views for LLM Context Engineering over Machine Data
arXiv:2604.05400v1 Announce Type: new Abstract: Machine data is central to observability and diagnosis in modern computing systems, appearing in logs, metrics, telemetry traces, and configuration snapshots. When provided to large language models (LLMs), this data typically arrives as a mixture...
Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling
arXiv:2604.05345v1 Announce Type: new Abstract: In today's artificial intelligence driven world, modern systems communicate with people from diverse backgrounds and skill levels. For human-machine interaction to be meaningful, systems must be aware of context and user expertise. This study proposes...
YoNER: A New Yor\`ub\'a Multi-domain Named Entity Recognition Dataset
arXiv:2604.05624v1 Announce Type: new Abstract: Named Entity Recognition (NER) is a foundational NLP task, yet research in Yor\`ub\'a has been constrained by limited and domain-specific resources. Existing resources, such as MasakhaNER (a manually annotated news-domain corpus) and WikiAnn (automatically created...
Adaptive Serverless Resource Management via Slot-Survival Prediction and Event-Driven Lifecycle Control
arXiv:2604.05465v1 Announce Type: new Abstract: Serverless computing eliminates infrastructure management overhead but introduces significant challenges regarding cold start latency and resource utilization. Traditional static resource allocation often leads to inefficiencies under variable workloads, resulting in performance degradation or excessive costs....
Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation
arXiv:2604.05083v1 Announce Type: new Abstract: While Large Language Models (LLMs) are increasingly adopted as automated judges for evaluating generated text, their outputs are often costly, and highly sensitive to prompt design, language, and aggregation strategies, severely, which limits reproducibility. To...
Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue
arXiv:2604.05552v1 Announce Type: new Abstract: Large Language Models demonstrate outstanding performance in many language tasks but still face fundamental challenges in managing the non-linear flow of human conversation. The prevalent approach of treating dialogue history as a flat, linear sequence...
Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
arXiv:2604.05339v1 Announce Type: new Abstract: As LLMs become increasingly integrated into human society, evaluating their orientations on human values from social science has drawn growing attention. Nevertheless, it is still unclear why human values matter for LLMs, especially in LLM-based...
OntoTKGE: Ontology-Enhanced Temporal Knowledge Graph Extrapolation
arXiv:2604.05468v1 Announce Type: new Abstract: Temporal knowledge graph (TKG) extrapolation is an important task that aims to predict future facts through historical interaction information within KG snapshots. A key challenge for most existing TKG extrapolation models is handling entities with...
Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning
arXiv:2604.05483v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorrect responses, limiting their applications if there is no...
What Makes a Good Response? An Empirical Analysis of Quality in Qualitative Interviews
arXiv:2604.05163v1 Announce Type: new Abstract: Qualitative interviews provide essential insights into human experiences when they elicit high-quality responses. While qualitative and NLP researchers have proposed various measures of interview quality, these measures lack validation that high-scoring responses actually contribute to...
Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series
arXiv:2604.05064v1 Announce Type: new Abstract: Synthetic data is essential for training foundation models for time series (FMTS), but most generators assume static correlations, and are typically missing realistic inter-channel dependencies. We introduce DynLMC, a Dynamic Linear Model of Coregionalization, that...
Reasoning Through Chess: How Reasoning Evolves from Data Through Fine-Tuning and Reinforcement Learning
arXiv:2604.05134v1 Announce Type: new Abstract: How can you get a language model to reason in a task it natively struggles with? We study how reasoning evolves in a language model -- from supervised fine-tuning (SFT) to reinforcement learning (RL) --...