数据来源：ArXiv Domain LLM Domain Papers1. Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement LearningAbstract:Large language models (LLMs) trained predominantly on English data encode substantial world knowledge, yet often fail to express it reliably in other languages, a phenomenon known as cross-lingual factual inconsistency. To study and address this, we introduce PolyFact, a large-scale parallel multilingual factual QA dataset containing 100K Wikidata-grounded facts ac ...

数据来源：ArXiv Domain LLM Domain Papers1. EDEN: A Large-Scale Corpus of Clinical Notes for ItalianAbstract:We present EDEN (Emergency Department Electronic Notes), a new and unique large-scale corpus of clinical notes produced in Emergency Departments of Italian hospitals. The corpus, in its current version, is composed of approximately 4 million clinical notes fully anonymized, covering diverse phases of patient care during the stay in the emergency department. In addition, a subset of about six ...

数据来源：ArXiv Domain LLM Domain Papers1. MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local RevisionAbstract:Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework ...

数据来源：ArXiv Domain LLM Domain Papers1. Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path AggregationAbstract:Large Language Models (LLMs) exhibit representational and syntactic biases that are difficult to evaluate due to the stochastic nature of text generation. Standard auditing methods rely on a single output inspection or static automated metrics. These approaches obscure the underlying probability distributions and fail to capture biases hidden in lower-probability g ...

数据来源：ArXiv Domain LLM Domain Papers1. HierBias: Context-Conditioned Hierarchical Media Bias Detection with Multi-Task Type ClassificationAbstract:Media bias detection is a critical task for ensuring fair and balanced information dissemination, yet existing sentence-level approaches classify each sentence independently, ignoring inter-sentence contextual signals that human annotators naturally exploit. We present \textbf{HierBias}, a hierarchical context-conditioned media bias detector that for ...

数据来源：ArXiv Domain LLM Domain Papers1. Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMsAbstract:We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchmark scores and reveal representational failures that benchmark accuracy masks. Existing evaluations conflate representation quality with model capacity. Therefore, failures cannot be attributed to the representation rather tha ...

数据来源：ArXiv Domain LLM Domain Papers1. Persona Without Substrate: Regime-Dependence and the LLM Individuation ProblemAbstract:Beckmann & Butlin’s (2026) ontological framework for the LLM individuation problem inherits an unargued cross-regime co-reference assumption from the persona-vectors literature: that the same direction picks out the same content under prompt-conditioning, gradient-descent fine-tuning, and inference-time steering. We present four empirical wedges from persona-topology ...

数据来源：ArXiv Domain LLM Domain Papers1. TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language ModelsAbstract:Understanding how Large Language Models (LLMs) make token-level decisions during code generation remains a major challenge for both researchers and practitioners. While recent tools provide insights into model internals or generation outcomes, they often lack decoding-time signals, fine-grained uncertainty measures, and interactive mechanism ...

数据来源：ArXiv Domain LLM Domain Papers1. How Personas Can Influence Agents to Play Split or StealAbstract:Personas are often employed to guide large language model agents, yet their effectiveness in shaping strategic behavior in social dilemma settings remains uncertain. To address this, we examined the impact of persona prompts in an iterated Split or Steal game where persona-driven agents interacted with a Virtual Human (VH) controlled by a fixed prompt. Agents were instantiated from four open ...

数据来源：ArXiv Domain LLM Domain Papers1. Unveiling Public Opinion: A Study of Sentiment Analysis Using LSTM and Traditional ModelsAbstract:In this age of social media, sites like Twitter have become meeting places for people to share their views and feelings on a wide range of issues and current events as they unfold in real time. Sentiment analysis, a critical application of NLP, has become indispensable due to the massive influx of user-generated content, enabling the extraction of meaningful i ...

数据来源：ArXiv Domain LLM Domain Papers1. HALO: Hybrid Adaptive Latent Reasoning for Language ModelsAbstract:We study how to improve a frozen pretrained language model with a small amount of adaptive extra computation. A simple approach is to add additional refinement steps on top of the backbone hidden states, but fixed extra refinement can be wasteful: a one-step refinement head may be too weak, while forcing a second full-sequence refinement step everywhere can increase compute without improvin ...

数据来源：ArXiv Domain LLM Domain Papers1. Scaling Point-in-Time Language ModelsAbstract:Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests and causal inference in finance and the social sciences. Point-in-time language models—trained exclusively on text available up to each calendar date—eliminate this leakage by construction, but existing efforts typically produce models ...

数据来源：ArXiv Domain LLM Domain Papers1. FixItFlow: Automated Troubleshooting Guide Generation from Cloud IncidentsAbstract:Cloud services experience frequent incidents that require rapid diagnosis and resolution. Troubleshooting guides help engineers respond consistently, but creating them manually is labor-intensive, resulting in incomplete coverage and outdated documentation. We present FixItFlow, an automated system that generates troubleshooting guides from historical incident data using lar ...

数据来源：ArXiv Domain LLM Domain Papers1. Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMsAbstract:Deploying Vision-Language Models (VLMs) in real-world settings requires not only strong visual reasoning but also stability under sustained conversational pressure. We introduce Just Keep Prompting (JKP), a multi-turn evaluation framework that measures VLM epistemic stability when users repeatedly challenge, question, or contradict a model’s answer. JKP probes models for up to 10 ...

数据来源：ArXiv Domain LLM Domain Papers1. Large Language Models as Unified Multimodal Learners for Clinical PredictionAbstract:Electronic health records combine free-text clinical narratives with structured measurements such as vital signs, laboratory values, and comorbidities. Yet most clinical prediction systems still rely on task-specific fusion architectures, pairing dedicated encoders for each modality with learned combination mechanisms that must be re-engineered for every new task and clini ...