{"list":"other","total":96,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"2301.09633","title":"Prediction-Powered Inference","created":"2023-01-23","cited_by_count":220},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2105.12806","title":"A Universal Law of Robustness via Isoperimetry","created":"2021-05-26","cited_by_count":151},{"id":"2404.01413","title":"Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data","created":"2024-04-01","cited_by_count":151},{"id":"2411.00640","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","created":"2024-11-01","cited_by_count":148},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144},{"id":"2402.10978","title":"Language Models with Conformal Factuality Guarantees","created":"2024-02-15","cited_by_count":131},{"id":"2402.08925","title":"MaxMin-RLHF: Alignment with Diverse Human Preferences","created":"2024-02-14","cited_by_count":123},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95},{"id":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72},{"id":"2306.01694","title":"Evaluating Language Models for Mathematics through Interactions","created":"2023-06-02","cited_by_count":70},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60},{"id":"2503.01067","title":"All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning","created":"2025-03-03","cited_by_count":59},{"id":"2404.01245","title":"A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules","created":"2024-04-01","cited_by_count":57},{"id":"2405.10301","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","created":"2024-05-16","cited_by_count":54},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54},{"id":"2402.09733","title":"Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States","created":"2024-02-15","cited_by_count":52},{"id":"2503.23674","title":"Large Language Models Pass the Turing Test","created":"2025-03-31","cited_by_count":48},{"id":"2409.05816","title":"Improving Pretraining Data Using Perplexity Correlations","created":"2024-09-09","cited_by_count":46},{"id":"2404.03163","title":"Uncertainty in Language Models: Assessment through Rank-Calibration","created":"2024-04-04","cited_by_count":41},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37},{"id":"2411.13868","title":"Robust Detection of Watermarks for Large Language Models Under Human Edits","created":"2024-11-21","cited_by_count":31},{"id":"2409.07032","title":"From optimal score matching to optimal sampling","created":"2024-09-11","cited_by_count":28},{"id":"2409.19605","title":"The Crucial Role of Samplers in Online Direct Preference Optimization","created":"2024-09-29","cited_by_count":27},{"id":"2410.22812","title":"Universality of the $\\pi^2/6$ Pathway in Avoiding Model Collapse","created":"2024-10-30","cited_by_count":26},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25},{"id":"2502.17814","title":"An Overview of Large Language Models for Statisticians","created":"2025-02-25","cited_by_count":24},{"id":"2503.10990","title":"Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium","created":"2025-03-14","cited_by_count":23},{"id":"2504.14154","title":"SConU: Selective Conformal Uncertainty in Large Language Models","created":"2025-04-19","cited_by_count":23},{"id":"2505.14827","title":"Text Generation Beyond Discrete Token Sampling","created":"2025-05-20","cited_by_count":21},{"id":"2406.07457","title":"Estimating the Hallucination Rate of Generative AI","created":"2024-06-11","cited_by_count":20},{"id":"2502.04270","title":"PILAF: Optimal Human Preference Sampling for Reward Modeling","created":"2025-02-06","cited_by_count":20},{"id":"2406.16829","title":"Understanding and Mitigating Tokenization Bias in Language Models","created":"2024-06-24","cited_by_count":18},{"id":"2410.04555","title":"$\\texttt{dattri}$: A Library for Efficient Data Attribution","created":"2024-10-06","cited_by_count":18},{"id":"2402.15481","title":"Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency","created":"2024-02-23","cited_by_count":15},{"id":"2405.02225","title":"Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks","created":"2024-05-03","cited_by_count":14},{"id":"2307.02792","title":"What Should Data Science Education Do with Large Language Models?","created":"2023-07-06","cited_by_count":13},{"id":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13},{"id":"2502.03688","title":"A Comparison of DeepSeek and Other LLMs","created":"2025-02-06","cited_by_count":10},{"id":"2406.11214","title":"Problematic Tokens: Tokenizer Bias in Large Language Models","created":"2024-06-17","cited_by_count":8},{"id":"2410.20418","title":"Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models","created":"2024-10-27","cited_by_count":8},{"id":"2501.02547","title":"Transformers Simulate MLE for Sequence Generation in Bayesian Networks","created":"2025-01-05","cited_by_count":8},{"id":"2504.07426","title":"Conditional Data Synthesis Augmentation","created":"2025-04-10","cited_by_count":8},{"id":"2501.01312","title":"Learning Spectral Methods by Transformers","created":"2025-01-02","cited_by_count":6},{"id":"2504.13629","title":"Divergent LLM Adoption and Heterogeneous Convergence Paths in Research Writing","created":"2025-04-18","cited_by_count":5},{"id":"2410.09649","title":"Learning the Bitter Lesson: Empirical Evidence from 20 Years of CVPR Proceedings","created":"2024-10-12","cited_by_count":4},{"id":"2112.09741","title":"Envisioning Future Deep Learning Theories: Some Basic Concepts and Characteristics","created":"2021-12-17","cited_by_count":3},{"id":"2409.10580","title":"Veridical Data Science for Medical Foundation Models","created":"2024-09-15","cited_by_count":2},{"id":"2501.02441","title":"A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models","created":"2025-01-05","cited_by_count":2},{"id":"2504.12335","title":"You've Changed: Detecting Modification of Black-Box Large Language Models","created":"2025-04-14","cited_by_count":2}],"next_cursor":null}