{"list":"other","total":99,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"2110.00218","title":"On the Importance of Gradients for Detecting Distributional Shifts in the Wild","created":"2021-10-01","cited_by_count":339},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302},{"id":"2202.01197","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","created":"2022-02-02","cited_by_count":300},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252},{"id":"2105.01879","title":"MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space","created":"2021-05-05","cited_by_count":233},{"id":"2206.02336","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","created":"2022-06-06","cited_by_count":233},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"1511.07543","title":"Convergent Learning: Do different neural networks learn the same representations?","created":"2015-11-24","cited_by_count":220},{"id":"2211.13445","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","created":"2022-11-24","cited_by_count":216},{"id":"2306.09301","title":"OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection","created":"2023-06-15","cited_by_count":179},{"id":"2110.14051","title":"A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges","created":"2021-10-26","cited_by_count":154},{"id":"2010.12884","title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints","created":"2020-10-24","cited_by_count":149},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138},{"id":"2303.02966","title":"Non-Parametric Outlier Synthesis","created":"2023-03-06","cited_by_count":129},{"id":"2203.04450","title":"How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?","created":"2022-03-08","cited_by_count":128},{"id":"2210.14707","title":"Is Out-of-Distribution Detection Learnable?","created":"2022-10-26","cited_by_count":109},{"id":"2206.13687","title":"POEM: Out-of-Distribution Detection with Posterior Sampling","created":"2022-06-28","cited_by_count":108},{"id":"2109.14162","title":"Can multi-label classification networks know what they don't know?","created":"2021-09-29","cited_by_count":100},{"id":"2202.03299","title":"Training OOD Detectors in their Natural Habitats","created":"2022-02-07","cited_by_count":86},{"id":"2008.06775","title":"Model Patching: Closing the Subgroup Performance Gap with Data Augmentation","created":"2020-08-15","cited_by_count":83},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79},{"id":"1906.06362","title":"Comparison of Diverse Decoding Methods from Conditional Language Models","created":"2019-06-14","cited_by_count":78},{"id":"2112.00787","title":"Provable Guarantees for Understanding Out-of-distribution Detection","created":"2021-12-01","cited_by_count":78},{"id":"2309.13415","title":"Dream the Impossible: Outlier Imagination with Diffusion Models","created":"2023-09-23","cited_by_count":77},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72},{"id":"2205.12910","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","created":"2022-05-25","cited_by_count":72},{"id":"2203.03800","title":"Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild","created":"2022-03-08","cited_by_count":70},{"id":"2109.05642","title":"On the Impact of Spurious Correlation for Out-of-distribution Detection","created":"2021-09-12","cited_by_count":68},{"id":"2306.12420","title":"LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models","created":"2023-06-21","cited_by_count":60},{"id":"2003.09711","title":"Robust Out-of-distribution Detection for Neural Networks","created":"2020-03-21","cited_by_count":57},{"id":"2306.09158","title":"Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection","created":"2023-06-15","cited_by_count":57},{"id":"2303.13662","title":"Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment","created":"2023-03-23","cited_by_count":48},{"id":"2011.13611","title":"Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving","created":"2020-11-27","cited_by_count":46},{"id":"2212.04055","title":"Mitigating Memorization of Noisy Labels by Clipping the Model Prediction","created":"2022-12-08","cited_by_count":40},{"id":"2306.06048","title":"How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?","created":"2023-06-09","cited_by_count":38},{"id":"2311.01796","title":"Learning to Augment Distributions for Out-of-Distribution Detection","created":"2023-11-03","cited_by_count":38},{"id":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36},{"id":"2305.14934","title":"GRACE: Discriminator-Guided Chain-of-Thought Reasoning","created":"2023-05-24","cited_by_count":35},{"id":"2109.13582","title":"PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding","created":"2021-09-28","cited_by_count":33},{"id":"2209.10365","title":"SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning","created":"2022-09-21","cited_by_count":31},{"id":"2305.03236","title":"A Survey on Out-of-Distribution Detection in NLP","created":"2023-05-05","cited_by_count":31},{"id":"2305.13282","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","created":"2023-05-22","cited_by_count":29},{"id":"2309.16155","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","created":"2023-09-28","cited_by_count":29},{"id":"1803.00909","title":"Understanding the Loss Surface of Neural Networks for Binary Classification","created":"2018-02-19","cited_by_count":27},{"id":"2208.09083","title":"Out-of-distribution Detection via Frequency-regularized Generative Models","created":"2022-08-18","cited_by_count":23},{"id":"2311.03524","title":"A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning","created":"2023-11-06","cited_by_count":22},{"id":"2106.07451","title":"Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions","created":"2021-06-14","cited_by_count":21},{"id":"2201.08984","title":"PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning","created":"2022-01-22","cited_by_count":21},{"id":"2308.05017","title":"When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis","created":"2023-08-09","cited_by_count":21},{"id":"1903.01612","title":"Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search","created":"2019-03-05","cited_by_count":19},{"id":"2303.05809","title":"Distributionally Robust Optimization with Probabilistic Group","created":"2023-03-10","cited_by_count":14},{"id":"1509.07715","title":"Uncovering the Small Community Structure in Large Networks: A Local Spectral Approach","created":"2015-09-25","cited_by_count":10},{"id":"1511.06421","title":"Deep Manifold Traversal: Changing Labels with Convolutional Features","created":"2015-11-19","cited_by_count":9},{"id":"1512.05457","title":"In a World That Counts: Clustering and Detecting Fake Social Engagement at Scale","created":"2015-12-17","cited_by_count":8},{"id":"2207.13083","title":"Task Agnostic and Post-hoc Unseen Distribution Detection","created":"2022-07-26","cited_by_count":8},{"id":"1509.08065","title":"Detecting Overlapping Communities from Local Spectral Subspaces","created":"2015-09-27","cited_by_count":6}],"next_cursor":null}