{"list":"other","total":55,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487},{"id":"1802.04633","title":"Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring","created":"2018-02-13","cited_by_count":357},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"2307.15593","title":"Robust Distortion-free Watermarks for Language Models","created":"2023-07-28","cited_by_count":320},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234},{"id":"2306.09194","title":"Undetectable Watermarks for Language Models","created":"2023-05-25","cited_by_count":226},{"id":"2012.00363","title":"Modifying Memories in Transformer Models","created":"2020-12-01","cited_by_count":224},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","created":"2024-04-08","cited_by_count":144},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118},{"id":"2403.01244","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","created":"2024-03-02","cited_by_count":118},{"id":"2108.13888","title":"Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning","created":"2021-08-31","cited_by_count":113},{"id":"2310.10669","title":"Unbiased Watermark for Large Language Models","created":"2023-09-22","cited_by_count":111},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92},{"id":"2406.11813","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","created":"2024-06-17","cited_by_count":90},{"id":"2401.12255","title":"Instructional Fingerprinting of Large Language Models","created":"2024-01-21","cited_by_count":68},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58},{"id":"2210.07543","title":"Watermarking Pre-trained Language Models with Backdooring","created":"2022-10-14","cited_by_count":50},{"id":"2410.13722","title":"Persistent Pre-Training Poisoning of LLMs","created":"2024-10-17","cited_by_count":48},{"id":"2403.09539","title":"Logits of API-Protected LLMs Leak Proprietary Information","created":"2024-03-14","cited_by_count":40},{"id":"2407.10887","title":"Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique","created":"2024-07-15","cited_by_count":37},{"id":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36},{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36},{"id":"2312.04828","title":"HuRef: HUman-REadable Fingerprint for Large Language Models","created":"2023-12-08","cited_by_count":34},{"id":"2210.03312","title":"Distillation-Resistant Watermarking for Model Protection in NLP","created":"2022-10-07","cited_by_count":30},{"id":"2407.01235","title":"A Fingerprint for Large Language Models","created":"2024-07-01","cited_by_count":28},{"id":"2404.05188","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","created":"2024-04-08","cited_by_count":19},{"id":"2408.02871","title":"Hide and Seek: Fingerprinting Large Language Models with Evolutionary Learning","created":"2024-08-06","cited_by_count":18},{"id":"2410.12318","title":"UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identification","created":"2024-10-16","cited_by_count":18},{"id":"2404.12699","title":"SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models","created":"2024-04-19","cited_by_count":17},{"id":"2407.02447","title":"PLeaS -- Merging Models with Permutations and Least Squares","created":"2024-07-02","cited_by_count":16},{"id":"2407.10886","title":"SLIP: Securing LLMs IP Using Weights Decomposition","created":"2024-07-15","cited_by_count":14},{"id":"2411.06611","title":"vTune: Verifiable Fine-Tuning for LLMs Through Backdooring","created":"2024-11-10","cited_by_count":4}],"next_cursor":null}