{"list":"other","total":62,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"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},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160},{"id":"2309.14717","title":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","created":"2023-09-26","cited_by_count":155},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126},{"id":"2402.17834","title":"Stable LM 2 1.6B Technical Report","created":"2024-02-27","cited_by_count":90},{"id":"2402.16694","title":"HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization","created":"2024-02-26","cited_by_count":86},{"id":"2307.07889","title":"LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models","created":"2023-07-15","cited_by_count":71},{"id":"2305.18465","title":"Federated Learning of Gboard Language Models with Differential Privacy","created":"2023-05-29","cited_by_count":66},{"id":"2305.12907","title":"Meta-in-context learning in large language models","created":"2023-05-22","cited_by_count":59},{"id":"2304.14999","title":"Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs","created":"2023-04-28","cited_by_count":38},{"id":"2404.03828","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","created":"2024-04-04","cited_by_count":38},{"id":"2404.03647","title":"Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra","created":"2024-04-04","cited_by_count":37},{"id":"2312.05693","title":"Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge","created":"2023-12-09","cited_by_count":33},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33},{"id":"2311.12275","title":"Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesis","created":"2023-11-21","cited_by_count":20},{"id":"2405.17822","title":"Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action","created":"2024-05-28","cited_by_count":19},{"id":"2404.00457","title":"MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks","created":"2024-03-30","cited_by_count":14},{"id":"2309.14488","title":"When Automated Assessment Meets Automated Content Generation: Examining Text Quality in the Era of GPTs","created":"2023-09-25","cited_by_count":13},{"id":"2310.02277","title":"Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs \"Difficult\" Downstream Tasks in LLMs","created":"2023-09-29","cited_by_count":13},{"id":"2405.04700","title":"Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures","created":"2024-05-07","cited_by_count":12},{"id":"2402.06696","title":"FL-NAS: Towards Fairness of NAS for Resource Constrained Devices via Large Language Models","created":"2024-02-09","cited_by_count":9},{"id":"2201.06219","title":"An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets","created":"2022-01-17","cited_by_count":8},{"id":"2404.01353","title":"Efficiently Distilling LLMs for Edge Applications","created":"2024-04-01","cited_by_count":5},{"id":"2403.09727","title":"Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems","created":"2024-03-12","cited_by_count":4},{"id":"2012.00822","title":"Open-Ended Multi-Modal Relational Reasoning for Video Question Answering","created":"2020-12-01","cited_by_count":2}],"next_cursor":null}