{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"2310.02238","title":"Who's Harry Potter? Approximate Unlearning in LLMs","created":"2023-10-03","cited_by_count":381},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119},{"id":"2308.07074","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","created":"2023-08-14","cited_by_count":109},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80},{"id":"2406.10890","title":"RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models","created":"2024-06-16","cited_by_count":78},{"id":"2402.05119","title":"A Closer Look at the Limitations of Instruction Tuning","created":"2024-02-03","cited_by_count":77},{"id":"2310.07931","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","created":"2023-10-11","cited_by_count":69},{"id":"2502.19301","title":"Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond","created":"2025-02-26","cited_by_count":61},{"id":"2305.09246","title":"Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning","created":"2023-05-16","cited_by_count":58},{"id":"2410.08109","title":"A Closer Look at Machine Unlearning for Large Language Models","created":"2024-10-10","cited_by_count":56},{"id":"2311.08182","title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","created":"2023-11-14","cited_by_count":52},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52},{"id":"2308.10524","title":"Dataset Quantization","created":"2023-08-21","cited_by_count":48},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40},{"id":"2303.02011","title":"Diagnosing Model Performance Under Distribution Shift","created":"2023-03-03","cited_by_count":39},{"id":"2403.08254","title":"Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects","created":"2024-03-13","cited_by_count":32},{"id":"2406.09179","title":"Towards Effective Evaluations and Comparisons for LLM Unlearning Methods","created":"2024-06-13","cited_by_count":27},{"id":"2407.01920","title":"To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models","created":"2024-07-02","cited_by_count":26},{"id":"2412.14922","title":"RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response","created":"2024-12-19","cited_by_count":24},{"id":"2501.12147","title":"Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities","created":"2025-01-21","cited_by_count":23},{"id":"2302.13959","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","created":"2023-02-27","cited_by_count":19},{"id":"2302.00674","title":"Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data","created":"2023-02-01","cited_by_count":13},{"id":"2408.04140","title":"UNLEARN Efficient Removal of Knowledge in Large Language Models","created":"2024-08-08","cited_by_count":10},{"id":"2411.01195","title":"Transfer Learning for Finetuning Large Language Models","created":"2024-11-02","cited_by_count":5},{"id":"2401.07598","title":"MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models","created":"2024-01-15","cited_by_count":3},{"id":"2407.08475","title":"Investigating Public Fine-Tuning Datasets: A Complex Review of Current Practices from a Construction Perspective","created":"2024-07-11","cited_by_count":3}],"next_cursor":null}