{"total":96,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737,"area":null},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721,"area":null},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2310.09716","title":"Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting","created":"2023-10-15","cited_by_count":69,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2310.16523","title":"Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting","created":"2023-10-25","cited_by_count":46,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2310.17110","title":"LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?","created":"2023-10-26","cited_by_count":40,"area":null},{"id":"2308.11764","title":"Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2310.14393","title":"Merging Generated and Retrieved Knowledge for Open-Domain QA","created":"2023-10-22","cited_by_count":36,"area":null},{"id":"2410.03765","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","created":"2024-10-02","cited_by_count":35,"area":null},{"id":"2308.00304","title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","created":"2023-08-01","cited_by_count":33,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2305.14386","title":"Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation","created":"2023-05-22","cited_by_count":29,"area":null},{"id":"2311.07961","title":"The ART of LLM Refinement: Ask, Refine, and Trust","created":"2023-11-14","cited_by_count":29,"area":null},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"area":null},{"id":"2404.15846","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","created":"2024-04-24","cited_by_count":27,"area":null},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2303.11341","title":"What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring","created":"2023-03-20","cited_by_count":21,"area":null},{"id":"2311.01555","title":"Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers","created":"2023-11-02","cited_by_count":19,"area":null},{"id":"2402.01729","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15,"area":null},{"id":"2310.02527","title":"CITING: Large Language Models Create Curriculum for Instruction Tuning","created":"2023-10-04","cited_by_count":14,"area":null},{"id":"2310.06547","title":"Rationale-Enhanced Language Models are Better Continual Relation Learners","created":"2023-10-10","cited_by_count":13,"area":null},{"id":"2401.08664","title":"Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges","created":"2023-12-27","cited_by_count":13,"area":null},{"id":"2402.13098","title":"ELAD: Explanation-Guided Large Language Models Active Distillation","created":"2024-02-20","cited_by_count":12,"area":null},{"id":"2403.00354","title":"Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy","created":"2024-03-01","cited_by_count":12,"area":null},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2502.16612","title":"MemeIntel: Explainable Detection of Propagandistic and Hateful Memes","created":"2025-02-23","cited_by_count":10,"area":null},{"id":"2305.13829","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2405.13014","title":"QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models","created":"2024-05-14","cited_by_count":8,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2312.12472","title":"A Performance Evaluation of a Quantized Large Language Model on Various Smartphones","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2404.02204","title":"Emergent Abilities in Reduced-Scale Generative Language Models","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2307.05082","title":"OntoChatGPT Information System: Ontology-Driven Structured Prompts for ChatGPT Meta-Learning","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2308.04386","title":"Learning Evaluation Models from Large Language Models for Sequence Generation","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2309.08922","title":"Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models","created":"2023-09-16","cited_by_count":6,"area":null},{"id":"2305.11480","title":"CCGen: Explainable Complementary Concept Generation in E-Commerce","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2407.05682","title":"Retrieved In-Context Principles from Previous Mistakes","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2412.13698","title":"Towards Efficient and Explainable Hate Speech Detection via Model Distillation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2310.07488","title":"KwaiYiiMath: Technical Report","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2411.06672","title":"What Should Baby Models Read? Exploring Sample-Efficient Data Composition on Model Performance","created":"2024-11-11","cited_by_count":4,"area":null},{"id":"2402.07543","title":"Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models","created":"2024-02-12","cited_by_count":3,"area":null},{"id":"2504.16394","title":"ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2507.14871","title":"Tiny language models","created":"2025-07-20","cited_by_count":3,"area":null},{"id":"2508.15478","title":"SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2301.10521","title":"ExaRanker: Explanation-Augmented Neural Ranker","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2305.11991","title":"Evaluation of medium-large Language Models at zero-shot closed book generative question answering","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2309.04663","title":"FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2406.04926","title":"Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2407.20248","title":"LAPIS: Language Model-Augmented Police Investigation System","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2408.03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2409.19533","title":"Mixed Chain-of-Psychotherapies for Emotional Support Chatbot","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2410.02297","title":"Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysis","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2501.05465","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","created":"2025-01-03","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":"2602.00166","title":"Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2411.03307","title":"LLMs for Domain Generation Algorithm Detection","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2411.06175","title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs","created":"2024-11-09","cited_by_count":1,"area":null},{"id":"2411.13053","title":"MEGL: Multimodal Explanation-Guided Learning","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2502.11779","title":"Efficient Response Generation Strategy Selection for Fine-Tuning Large Language Models Through Self-Aligned Perplexity","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2504.02521","title":"UNDO: Understanding Distillation as Optimization","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2505.24147","title":"Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2507.07421","title":"SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2510.12032","title":"Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2605.18829","title":"Lossless Anti-Distillation Sampling","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2609.19553","title":"From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2406.06571","title":"SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2409.00347","title":"Chatting Up Attachment: Using LLMs to Predict Adult Bonds","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2502.03129","title":"Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2601.08844","title":"Emissions and Performance Trade-off Between Small and Large Language Models","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2601.09306","title":"On-Device Large Language Models for Sequential Recommendation","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2603.16137","title":"SIA: A Synthesize-Inject-Align Framework for Knowledge-Grounded and Secure E-commerce Search LLMs with Industrial Deployment","created":"2026-03-17","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":"2604.16845","title":"DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.01111","title":"When Less is Enough: Efficient Inference via Collaborative Reasoning","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.07613","title":"Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.14084","title":"CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.04412","title":"LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.20450","title":"ShriNep@EEUCA 2026: RAKSHAK - Multi-Task DeBERTa with Rationale Distillation and Jigsaw-Augmented Training for Toxic Intent Classification","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.28788","title":"EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.01130","title":"When Do Surrogate Updates Improve Decisions? A Local Theory of Trajectory-Wise Transfer","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.20927","title":"MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.09567","title":"Positional task conditioning for scalable defect detection across product families in large product catalogs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.12419","title":"MInTRL: Off-policy Intervention can boost On-policy RL","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.04825","title":"DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.15501","title":"Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}