{"list":"other","total":77,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"1604.00772","title":"The CMA Evolution Strategy: A Tutorial","created":"2016-04-04","cited_by_count":377},{"id":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"id":"1702.07464","title":"Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning","created":"2017-02-24","cited_by_count":334},{"id":"1706.03691","title":"Certified Defenses for Data Poisoning Attacks","created":"2017-06-09","cited_by_count":303},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"1902.04742","title":"Uniform convergence may be unable to explain generalization in deep learning","created":"2019-02-13","cited_by_count":224},{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222},{"id":"2310.19156","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","created":"2023-10-29","cited_by_count":159},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2402.19255","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","created":"2024-02-29","cited_by_count":158},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133},{"id":"2311.14455","title":"Universal Jailbreak Backdoors from Poisoned Human Feedback","created":"2023-11-24","cited_by_count":128},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116},{"id":"2311.06062","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","created":"2023-11-10","cited_by_count":98},{"id":"2503.22342","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","created":"2025-03-28","cited_by_count":96},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95},{"id":"2307.06865","title":"Effective Prompt Extraction from Language Models","created":"2023-07-13","cited_by_count":85},{"id":"2305.15594","title":"Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models","created":"2023-05-24","cited_by_count":83},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76},{"id":"2210.00038","title":"Differentially Private Optimization on Large Model at Small Cost","created":"2022-09-30","cited_by_count":65},{"id":"2405.18137","title":"Exploiting LLM Quantization","created":"2024-05-28","cited_by_count":65},{"id":"2305.14907","title":"Coverage-based Example Selection for In-Context Learning","created":"2023-05-24","cited_by_count":59},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53},{"id":"2210.00036","title":"Differentially Private Bias-Term Fine-tuning of Foundation Models","created":"2022-09-30","cited_by_count":48},{"id":"2403.09162","title":"Unveiling the Generalization Power of Fine-Tuned Large Language Models","created":"2024-03-14","cited_by_count":36},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35},{"id":"2204.07667","title":"Just Fine-tune Twice: Selective Differential Privacy for Large Language Models","created":"2022-04-15","cited_by_count":32},{"id":"2410.20625","title":"LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization","created":"2024-10-27","cited_by_count":32},{"id":"1703.03334","title":"Fast Genetic Algorithms","created":"2017-03-09","cited_by_count":29},{"id":"2410.08105","title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?","created":"2024-10-10","cited_by_count":29},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22},{"id":"2403.15638","title":"Differentially Private Next-Token Prediction of Large Language Models","created":"2024-03-22","cited_by_count":22},{"id":"2404.00473","title":"Privacy Backdoors: Stealing Data with Corrupted Pretrained Models","created":"2024-03-30","cited_by_count":22},{"id":"2301.12767","title":"Compression, Generalization and Learning","created":"2023-01-30","cited_by_count":21},{"id":"2408.05212","title":"Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions","created":"2024-08-10","cited_by_count":15},{"id":"2010.04542","title":"Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking","created":"2020-10-08","cited_by_count":14},{"id":"2410.02912","title":"Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation","created":"2024-10-03","cited_by_count":14},{"id":"1902.02588","title":"Self-Adjusting Mutation Rates with Provably Optimal Success Rules","created":"2019-02-07","cited_by_count":13},{"id":"2406.11715","title":"Measuring memorization in RLHF for code completion","created":"2024-06-17","cited_by_count":13},{"id":"2203.14383","title":"Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions","created":"2022-03-27","cited_by_count":11},{"id":"2204.01275","title":"Direct search based on probabilistic descent in reduced spaces","created":"2022-04-04","cited_by_count":7},{"id":"2502.13441","title":"The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?","created":"2025-02-19","cited_by_count":7},{"id":"1606.05551","title":"Self-adaptation of Mutation Rates in Non-elitist Populations","created":"2016-06-17","cited_by_count":6},{"id":"2501.01336","title":"Aligning Large Language Models for Faithful Integrity Against Opposing Argument","created":"2025-01-02","cited_by_count":6},{"id":"1808.05566","title":"The linear hidden subset problem for the (1+1) EA with scheduled and adaptive mutation rates","created":"2018-08-16","cited_by_count":3},{"id":"2410.11330","title":"Evolutionary Retrofitting","created":"2024-10-15","cited_by_count":2},{"id":"2412.04291","title":"Evolutionary Pre-Prompt Optimization for Mathematical Reasoning","created":"2024-12-05","cited_by_count":2}],"next_cursor":null}