{"total":73,"rows":[{"id":"2412.04862","title":"EXAONE 3.5: Series of Large Language Models for Real-world Use Cases","created":"2024-12-06","cited_by_count":53,"area":null},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2509.08682","title":"Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference","created":"2025-09-10","cited_by_count":18,"area":null},{"id":"2603.21389","title":"Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models","created":"2026-03-22","cited_by_count":15,"area":null},{"id":"2502.08664","title":"Motion Forecasting for Autonomous Vehicles: A Survey","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2504.00623","title":"Efficient Construction of Model Family through Progressive Training Using Model Expansion","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2506.02280","title":"The State of Large Language Models for African Languages: Progress and Challenges","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2504.04569","title":"KnowsLM: A framework for evaluation of small language models for knowledge augmentation and humanised conversations","created":"2025-04-06","cited_by_count":6,"area":null},{"id":"2507.21108","title":"A Survey of Classification Tasks and Approaches for Legal Contracts","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2506.06579","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2511.20104","title":"The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2505.13425","title":"Learnware of Language Models: Specialized Small Language Models Can Do Big","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2509.07324","title":"Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2509.16413","title":"Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research","created":"2025-09-19","cited_by_count":3,"area":null},{"id":"2512.02716","title":"Menta: A Small Language Model for On-Device Mental Health Prediction","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2603.17945","title":"ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2412.14215","title":"Generative AI Toolkit -- a framework for increasing the quality of LLM-based applications over their whole life cycle","created":"2024-12-18","cited_by_count":2,"area":null},{"id":"2506.01698","title":"When LLMs Team Up: The Emergence of Collaborative Affective Computing","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2506.06180","title":"Detecting Voice Phishing with Precision: Fine-Tuning Small Language Models","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2510.05858","title":"DACP: Domain-Adaptive Continual Pre-Training of Large Language Models for Phone Conversation Summarization","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.08601","title":"Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2601.13735","title":"Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2607.09053","title":"An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2504.07989","title":"Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2505.08620","title":"Resource-Efficient Language Models: Quantization for Fast and Accessible Inference","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2506.20018","title":"Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Models","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2510.08152","title":"DACIP-RC: Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension on Business Conversations","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2510.20278","title":"KCM: KAN-Based Collaboration Models Enhance Pretrained Large Models","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2510.21443","title":"Does Model Size Matter? A Comparison of Small and Large Language Models for Requirements Classification","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2511.02647","title":"Federated Attention: A Distributed Paradigm for Collaborative LLM Inference over Edge Networks","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2512.02625","title":"CryptoQA: A Large-scale Question-answering Dataset for AI-assisted Cryptography","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2512.24863","title":"Big AI is accelerating the metacrisis: What can we do?","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2602.21059","title":"An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.06647","title":"Performance Comparison of IBN orchestration using LLM and SLMs","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2606.15974","title":"A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2606.16995","title":"When in Doubt, Plan It Out: Committed Small Language Model Deliberation for Reactive Reinforcement Learning","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2607.03801","title":"Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2608.17183","title":"Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2412.15441","title":"Insights into resource utilization of code small language models serving with runtime engines and execution providers","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2501.01284","title":"Tracing Partisan Bias to Its Emotional Fingerprints: A Computational Approach to Mitigation","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2505.00831","title":"SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2506.07695","title":"Towards a Small Language Model Lifecycle Framework","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2506.12403","title":"Bridging the Digital Divide: Small Language Models as a Pathway for Physics and Photonics Education in Underdeveloped Regions","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2507.23674","title":"TweakLLM: A Routing Architecture for Dynamic Tailoring of Cached Responses","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.16680","title":"CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2509.21192","title":"GEP: A GCG-Based method for extracting personally identifiable information from chatbots built on small language models","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.04032","title":"Small Language Models for Emergency Departments Decision Support: A Benchmark Study","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2511.03466","title":"Kastor: Fine-tuned Small Language Models for Shape-based Active Relation Extraction","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.03542","title":"SOLVE-Med: Specialized Orchestration for Leading Vertical Experts across Medical Specialties","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2601.01037","title":"Multi-Dimensional Prompt Chaining to Improve Open-Domain Dialogue Generation","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2601.02071","title":"FormuLLA: A Large Language Model Approach to Generating Novel 3D Printable Formulations","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.04212","title":"TrueBrief: Faithful Summarization through Small Language Models","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2602.02632","title":"Performance of Small Language Model Pretraining on FABRIC: An Empirical Study","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.21374","title":"Small Language Models for Privacy-Preserving Clinical Information Extraction in Low-Resource Languages","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.02653","title":"AlphaFree: Recommendation Free from Users, IDs, and GNNs","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.28622","title":"Trust-Aware Routing for Distributed Generative AI Inference at the Edge","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.00586","title":"More Human, More Efficient: Aligning Annotations with Quantized SLMs","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.06330","title":"Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysis","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.23913","title":"Can LoRA Fusion Support Cross-Domain Tasks in Cloud-Edge Collaboration?","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.25394","title":"Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.18190","title":"Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.27634","title":"Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.12336","title":"Evaluating Health Misinformation in Low-Resource Languages: Integrating Small Language Models with a Culturally-Sensitive Responsible NLP Framework (Bangla as a Case Study)","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.18034","title":"AdaHome: An Adaptive Smart Home Assistant using Local Small Language Models","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.22556","title":"MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.22624","title":"CHS-SQL: A Text-to-SQL approach based on Confidence-Guided Heuristic Search Schema Linking process","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.24801","title":"Influence of Prompt Engineering on Small Language Models for Guarded Query Routing","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.00042","title":"Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.04488","title":"Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.03702","title":"Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.28765","title":"Reinforcement Learning with Verifiable Rewards for Small Search Agents","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}