Provide.ai https://validator.w3.org/feed/docs/rss2.html Talent or Luck? Evaluating Attribution Bias in Large Language Models Multimodal LLMs are not all you need for Pediatric Speech Language Pathology Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine Translating Under Pressure: Domain-Aware LLMs for Crisis Communication Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models Zero-Shot to Full-Resource: Cross-lingual Transfer Strategies for Aspect-Based Sentiment Analysis Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token’s Nature OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling When Annotators Disagree, Topology Explains: Mapper, a Topological Tool for Exploring Text Embedding Geometry and Ambiguity Differentially-Private Text Rewriting reshapes Linguistic Style Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomy Safety Is Not Universal: The Selective Safety Trap in LLM Alignment Swap distance minimization shapes the order of subject, object and verb in languages of the world Verified Critical Step Optimization for LLM Agents Domain-Adapted Small Language Models for Reliable Clinical Triage Thinking with Drafting: Optical Decompression via Logical Reconstruction Decoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation HalluCiteChecker: A Lightweight Toolkit for Hallucinated Citation Detection and Verification in the Era of AI Scientists SciMDR: Advancing Scientific Multimodal Document Reasoning What Kind of Language is Easy to Language-Model Under Curriculum Learning? Reasoning Gets Harder for LLMs Inside A Dialogue MoRFI: Monotonic Sparse Autoencoder Feature Identification Why Attend to Everything? Focus is the Key HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering Diffusion Language Models for Speech Recognition ClawGym: A Scalable Framework for Building Effective Claw Agents A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression Select to Think: Unlocking SLM Potential with Local Sufficiency How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models A Scoping Review of LLM-as-a-Judge in Healthcare and the MedJUDGE Framework Identifying the Achilles’ Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models A Quantitative Confirmation of the Currier Language Distinction Crime Hotspot Prediction Using Deep Graph Convolutional Networks SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent Vibe Check: Understanding the Effects of LLM-Based Conversational Agents’ Personality and Alignment on User Perceptions in Goal-Oriented Tasks AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech Evaluation of Automatic Speech Recognition Using Generative Large Language Models Auto-ARGUE: LLM-Based Report Generation Evaluation Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards Beyond Screenshots: Evaluating VLMs’ Understanding of UI Animations Mapping the maturation of TCM as an adjuvant to radiotherapy Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio