#Natural Language Processing
Latest news articles tagged with "Natural Language Processing". Follow the timeline of events, related topics, and entities.
Articles (30)
-
🇺🇸 FMI@SU ToxHabits: Evaluating LLMs Performance on Toxic Habit Extraction in Spanish Clinical Texts
[USA]
arXiv:2604.06403v1 Announce Type: cross Abstract: The paper presents an approach for the recognition of toxic habits named entities in Spanish clinical texts. The approach was developed for the ToxHa...
Related: #Artificial Intelligence, #Healthcare Technology -
🇺🇸 HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
[USA]
arXiv:2604.06845v1 Announce Type: cross Abstract: Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely...
Related: #Artificial Intelligence, #Human-Computer Interaction -
🇺🇸 STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems
[USA]
arXiv:2604.07100v1 Announce Type: cross Abstract: Empathetic dialogue requires not only recognizing a user's emotional state but also making strategy-aware, context-sensitive decisions throughout res...
Related: #Artificial Intelligence, #Human-Computer Interaction -
🇺🇸 Severity-Aware Weighted Loss for Arabic Medical Text Generation
[USA]
arXiv:2604.06346v1 Announce Type: cross Abstract: Large language models have shown strong potential for Arabic medical text generation; however, traditional fine-tuning objectives treat all medical c...
Related: #Artificial Intelligence, #Healthcare Technology -
🇺🇸 Team Fusion@ SU@ BC8 SympTEMIST track: transformer-based approach for symptom recognition and linking
[USA]
arXiv:2604.06424v1 Announce Type: cross Abstract: This paper presents a transformer-based approach to solving the SympTEMIST named entity recognition (NER) and entity linking (EL) tasks. For NER, we ...
Related: #Artificial Intelligence, #Healthcare Technology -
🇺🇸 Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries
[USA]
arXiv:2604.06416v1 Announce Type: cross Abstract: Although LLM context lengths have grown, there is evidence that their ability to integrate information across long-form texts has not kept pace. We e...
Related: #Artificial Intelligence, #Cognitive Science -
🇺🇸 A Severity-Based Curriculum Learning Strategy for Arabic Medical Text Generation
[USA]
arXiv:2604.06365v1 Announce Type: cross Abstract: Arabic medical text generation is increasingly needed to help users interpret symptoms and access general health guidance in their native language. N...
Related: #Artificial Intelligence, #Healthcare Technology, #Medical Informatics -
🇺🇸 FrameNet Semantic Role Classification by Analogy
[USA]
arXiv:2603.19825v1 Announce Type: cross Abstract: In this paper, we adopt a relational view of analogies applied to Semantic Role Classification in FrameNet. We define analogies as formal relations o...
Related: #Computational Linguistics -
🇺🇸 Improving Automatic Summarization of Radiology Reports through Mid-Training of Large Language Models
[USA]
arXiv:2603.19275v1 Announce Type: cross Abstract: Automatic summarization of radiology reports is an essential application to reduce the burden on physicians. Previous studies have widely used the "p...
Related: #AI in Healthcare -
🇺🇸 From Topic to Transition Structure: Unsupervised Concept Discovery at Corpus Scale via Predictive Associative Memory
[USA]
arXiv:2603.18420v1 Announce Type: new Abstract: Embedding models group text by semantic content, what text is about. We show that temporal co-occurrence within texts discovers a different kind of str...
Related: #AI Research -
🇺🇸 GenLie: A Global-Enhanced Lie Detection Network under Sparsity and Semantic Interference
[USA]
arXiv:2603.16935v1 Announce Type: cross Abstract: Video-based lie detection aims to identify deceptive behaviors from visual cues. Despite recent progress, its core challenge lies in learning sparse ...
Related: #AI Detection -
🇺🇸 A Family of LLMs Liberated from Static Vocabularies
[USA]
arXiv:2603.15953v1 Announce Type: cross Abstract: Tokenization is a central component of natural language processing in current large language models (LLMs), enabling models to convert raw text into ...
Related: #AI Innovation -
🇺🇸 Optimizing LLM Annotation of Classroom Discourse through Multi-Agent Orchestration
[USA]
arXiv:2603.13353v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly positioned as scalable tools for annotating educational data, including classroom discourse, interaction ...
Related: #AI in Education -
🇺🇸 Semantic Invariance in Agentic AI
[USA]
arXiv:2603.13173v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly serve as autonomous reasoning agents in decision support, scientific problem-solving, and multi-agent coordin...
Related: #AI Reliability -
🇺🇸 MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries
[USA]
arXiv:2603.11223v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) over Knowledge Graphs (KGs) suffers from the fact that indexing approaches may lose important contextual nuance ...
Related: #Question Answering -
🇺🇸 Mindstorms in Natural Language-Based Societies of Mind
[USA]
arXiv:2305.17066v2 Announce Type: replace Abstract: Both Minsky's "society of mind" and Schmidhuber's "learning to think" inspire diverse societies of large multimodal neural networks (NNs) that solv...
Related: #Collective Intelligence -
🇺🇸 AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem
[USA]
arXiv:2603.08938v1 Announce Type: new Abstract: The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as ...
Related: #Data Integration -
🇺🇸 Imagine How To Change: Explicit Procedure Modeling for Change Captioning
[USA]
arXiv:2603.05969v1 Announce Type: cross Abstract: Change captioning generates descriptions that explicitly describe the differences between two visually similar images. Existing methods operate on st...
Related: #Computer Vision -
🇺🇸 Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement
[USA]
arXiv:2603.04698v1 Announce Type: cross Abstract: This paper evaluates data augmentation and feature enhancement techniques for hate speech detection, comparing traditional classifiers, e.g., Delta T...
Related: #AI Ethics -
🇺🇸 Decoder-based Sense Knowledge Distillation
[USA]
arXiv:2602.22351v1 Announce Type: cross Abstract: Large language models (LLMs) learn contextual embeddings that capture rich semantic information, yet they often overlook structured lexical knowledge...
Related: #AI Research, #Knowledge Distillation -
🇺🇸 Automating the Detection of Requirement Dependencies Using Large Language Models
[USA]
arXiv:2602.22456v1 Announce Type: cross Abstract: Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpin criti...
Related: #Software Engineering, #Artificial Intelligence -
🇺🇸 Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function
[USA]
arXiv:2602.22255v1 Announce Type: cross Abstract: We introduce a sequence modeling framework in which the latent state is a complex-valued wave function evolving on a finite-dimensional Hilbert space...
Related: #Quantum Computing, #Machine Learning, #Theoretical Computer Science -
🇺🇸 Talking to Yourself: Defying Forgetting in Large Language Models
[USA]
arXiv:2602.20162v1 Announce Type: cross Abstract: Catastrophic forgetting remains a major challenge when fine-tuning large language models (LLMs) on narrow, task-specific data, often degrading their ...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Augmenting Lateral Thinking in Language Models with Humor and Riddle Data for the BRAINTEASER Task
[USA]
arXiv:2405.10385v3 Announce Type: replace-cross Abstract: The SemEval 2024 BRAINTEASER task challenges language models to perform lateral thinking -- a form of creative, non-linear reasoning that rem...
Related: #Artificial Intelligence, #Cognitive Computing -
🇺🇸 Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
[USA]
arXiv:2506.18777v2 Announce Type: replace Abstract: Large language models (LLMs) are typically trained to acquire behaviours from demonstrations or experience, yet much of their training data is decl...
Related: #Machine Learning, #AI Training Efficiency -
🇺🇸 From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation in Production
[USA]
arXiv:2602.20558v1 Announce Type: new Abstract: Large language models (LLMs) are promising backbones for generative recommender systems, yet a key challenge remains underexplored: verbalization, i.e....
Related: #Artificial Intelligence, #Recommendation Systems -
🇺🇸 PVminer: A Domain-Specific Tool to Detect the Patient Voice in Patient Generated Data
[USA]
arXiv:2602.21165v1 Announce Type: cross Abstract: Patient-generated text such as secure messages, surveys, and interviews contains rich expressions of the patient voice (PV), reflecting communicative...
Related: #Healthcare Technology, #Patient-Centered Care -
🇺🇸 Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA
[USA]
arXiv:2602.20492v1 Announce Type: cross Abstract: Decentralized federated learning (DFL) based on low-rank adaptation (LoRA) enables mobile devices with multi-task datasets to collaboratively fine-tu...
Related: #Machine Learning, #Federated Learning, #Wireless Technology -
🇺🇸 Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
[USA]
arXiv:2602.20426v1 Announce Type: new Abstract: The performance of LLM-based agents depends not only on the agent itself but also on the quality of the tool interfaces it consumes. While prior work h...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 CAMEL: Confidence-Gated Reflection for Reward Modeling
[USA]
arXiv:2602.20670v1 Announce Type: cross Abstract: Reward models play a fundamental role in aligning large language models with human preferences. Existing methods predominantly follow two paradigms: ...
Related: #Artificial Intelligence, #Machine Learning
Key Entities (17)
- Large language model (8 news)
- Artificial intelligence (3 news)
- Natural language processing (3 news)
- Catastrophic interference (1 news)
- Natural language (1 news)
- Wave function (1 news)
- Hamiltonian (1 news)
- Machine learning (1 news)
- Curriculum learning (1 news)
- AI alignment (1 news)
- Reinforcement learning (1 news)
- Verbalisation (1 news)
- Software engineering (1 news)
- LoRA (machine learning) (1 news)
- Wireless (1 news)
- BERT (language model) (1 news)
- NLP (1 news)
About the topic: Natural Language Processing
The topic "Natural Language Processing" aggregates 30+ news articles from various countries.