{"total":50,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1245,"area":null},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":629,"area":null},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":471,"area":null},{"id":"2312.05934","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","created":"2023-12-10","cited_by_count":180,"area":null},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":161,"area":null},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":94,"area":null},{"id":"2307.06865","title":"Effective Prompt Extraction from Language Models","created":"2023-07-13","cited_by_count":87,"area":null},{"id":"2311.14736","title":"Data Diversity Matters for Robust Instruction Tuning","created":"2023-11-21","cited_by_count":76,"area":null},{"id":"2308.11696","title":"Efficient Benchmarking of Language Models","created":"2023-08-22","cited_by_count":71,"area":null},{"id":"2410.03608","title":"TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation","created":"2024-10-04","cited_by_count":70,"area":null},{"id":"2309.09150","title":"Can Large Language Models Understand Real-World Complex Instructions?","created":"2023-09-17","cited_by_count":69,"area":null},{"id":"2308.01240","title":"Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation","created":"2023-08-02","cited_by_count":51,"area":null},{"id":"2308.10524","title":"Dataset Quantization","created":"2023-08-21","cited_by_count":48,"area":null},{"id":"2312.00575","title":"Instruction-tuning Aligns LLMs to the Human Brain","created":"2023-12-01","cited_by_count":40,"area":null},{"id":"2402.05129","title":"Best Practices for Text Annotation with Large Language Models","created":"2024-02-05","cited_by_count":37,"area":null},{"id":"2307.10558","title":"Instruction-following Evaluation through Verbalizer Manipulation","created":"2023-07-20","cited_by_count":30,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2406.04845","title":"FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models","created":"2024-06-07","cited_by_count":30,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":29,"area":null},{"id":"2311.00233","title":"Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions","created":"2023-11-01","cited_by_count":24,"area":null},{"id":"2307.10172","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","created":"2023-07-19","cited_by_count":23,"area":null},{"id":"2409.14396","title":"Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape","created":"2024-09-22","cited_by_count":22,"area":null},{"id":"2307.08701","title":"AlpaGasus: Training A Better Alpaca with Fewer Data","created":"2023-07-17","cited_by_count":21,"area":null},{"id":"2310.05015","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","created":"2023-10-08","cited_by_count":19,"area":null},{"id":"2401.16313","title":"Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets","created":"2024-01-29","cited_by_count":19,"area":null},{"id":"2404.08008","title":"Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition","created":"2024-04-10","cited_by_count":19,"area":null},{"id":"2307.02053","title":"Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning","created":"2023-07-05","cited_by_count":18,"area":null},{"id":"2309.16583","title":"GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond","created":"2023-09-28","cited_by_count":14,"area":null},{"id":"2411.05059","title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2407.10153","title":"Look Within, Why LLMs Hallucinate: A Causal Perspective","created":"2024-07-14","cited_by_count":11,"area":null},{"id":"2409.18216","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2508.11847","title":"Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings","created":"2025-08-16","cited_by_count":8,"area":null},{"id":"2309.16119","title":"ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers","created":"2023-09-28","cited_by_count":7,"area":null},{"id":"2410.13618","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2505.09027","title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation","created":"2025-05-13","cited_by_count":6,"area":null},{"id":"2403.15250","title":"Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach","created":"2024-03-22","cited_by_count":5,"area":null},{"id":"2409.00861","title":"Harnessing the Power of Semi-Structured Knowledge and LLMs with Triplet-Based Prefiltering for Question Answering","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2407.21072","title":"Beyond Metrics: A Critical Analysis of the Variability in Large Language Model Evaluation Frameworks","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2505.09246","title":"Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2508.19564","title":"Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2503.21838","title":"MSPLoRA: A Multi-Scale Pyramid Low-Rank Adaptation for Efficient Model Fine-Tuning","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2405.06003","title":"Binary Hypothesis Testing for Softmax Models and Leverage Score Models","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2410.02558","title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2501.12979","title":"FlanEC: Exploring Flan-T5 for Post-ASR Error Correction","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2506.00236","title":"Localized LoRA: A Structured Low-Rank Approximation for Efficient Fine-Tuning","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2508.16647","title":"AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2509.07676","title":"Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2512.08965","title":"Financial Instruction Following Evaluation (FIFE)","created":"2025-12-01","cited_by_count":0,"area":null}],"next_cursor":null}