{"list":"other","total":87,"rows":[{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"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":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"2303.11305","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","created":"2023-03-20","cited_by_count":338},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234},{"id":"2010.11918","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","created":"2020-10-22","cited_by_count":224},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159},{"id":"2109.05687","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","created":"2021-09-13","cited_by_count":146},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144},{"id":"1803.04386","title":"Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches","created":"2018-03-12","cited_by_count":133},{"id":"2212.10650","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","created":"2022-12-20","cited_by_count":133},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115},{"id":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100},{"id":"2311.11696","title":"Sparse Low-rank Adaptation of Pre-trained Language Models","created":"2023-11-20","cited_by_count":96},{"id":"2004.12406","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","created":"2020-04-26","cited_by_count":93},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67},{"id":"1608.06884","title":"Towards Bayesian Deep Learning: A Framework and Some Existing Methods","created":"2016-08-24","cited_by_count":58},{"id":"1812.03973","title":"Bayesian Layers: A Module for Neural Network Uncertainty","created":"2018-12-10","cited_by_count":57},{"id":"2010.10604","title":"Bayesian Attention Modules","created":"2020-10-20","cited_by_count":51},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37},{"id":"1611.00448","title":"Natural-Parameter Networks: A Class of Probabilistic Neural Networks","created":"2016-11-02","cited_by_count":34},{"id":"2211.07443","title":"Calibrated Interpretation: Confidence Estimation in Semantic Parsing","created":"2022-11-14","cited_by_count":33},{"id":"1906.05323","title":"Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayes","created":"2019-06-12","cited_by_count":32},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25},{"id":"1701.03208","title":"Gaussian variational approximation with a factor covariance structure","created":"2017-01-12","cited_by_count":22},{"id":"2102.04754","title":"Bayesian Transformer Language Models for Speech Recognition","created":"2021-02-09","cited_by_count":22},{"id":"2303.02444","title":"Calibrating Transformers via Sparse Gaussian Processes","created":"2023-03-04","cited_by_count":21},{"id":"2304.02902","title":"Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry","created":"2023-04-06","cited_by_count":21},{"id":"2405.03425","title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","created":"2024-05-06","cited_by_count":20},{"id":"2202.03628","title":"Graph-Relational Domain Adaptation","created":"2022-02-08","cited_by_count":19},{"id":"1605.05622","title":"Gaussian variational approximation with sparse precision matrices","created":"2016-05-18","cited_by_count":15},{"id":"2110.04020","title":"Pathologies in priors and inference for Bayesian transformers","created":"2021-10-08","cited_by_count":13},{"id":"1902.02037","title":"Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling","created":"2019-02-06","cited_by_count":11},{"id":"2404.03514","title":"Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models","created":"2024-04-04","cited_by_count":9},{"id":"2306.12497","title":"Density Uncertainty Layers for Reliable Uncertainty Estimation","created":"2023-06-21","cited_by_count":4},{"id":"2310.16587","title":"Adaptive Uncertainty Estimation via High-Dimensional Testing on Latent Representations","created":"2023-10-25","cited_by_count":2},{"id":"2104.15010","title":"Degenerate Gaussian factors for probabilistic inference","created":"2021-04-30","cited_by_count":1}],"next_cursor":null}