{"list":"other","total":94,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"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":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"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":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486},{"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":"2202.01197","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","created":"2022-02-02","cited_by_count":300},{"id":"2406.18629","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","created":"2024-06-26","cited_by_count":273},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252},{"id":"2404.12358","title":"From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function","created":"2024-04-18","cited_by_count":242},{"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":"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":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"2306.09301","title":"OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection","created":"2023-06-15","cited_by_count":179},{"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":"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":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135},{"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":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127},{"id":"2406.14852","title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models","created":"2024-06-21","cited_by_count":113},{"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":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106},{"id":"2109.14162","title":"Can multi-label classification networks know what they don't know?","created":"2021-09-29","cited_by_count":100},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99},{"id":"2406.14283","title":"Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning","created":"2024-06-20","cited_by_count":97},{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96},{"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":"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":"2406.10858","title":"Step-level Value Preference Optimization for Mathematical Reasoning","created":"2024-06-16","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":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","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":"2401.14295","title":"Demystifying Chains, Trees, and Graphs of Thoughts","created":"2024-01-25","cited_by_count":63},{"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":"2402.03502","title":"How Does Unlabeled Data Provably Help Out-of-Distribution Detection?","created":"2024-02-05","cited_by_count":36},{"id":"2407.21794","title":"Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey","created":"2024-07-31","cited_by_count":36},{"id":"2407.00782","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","created":"2024-06-30","cited_by_count":35},{"id":"2410.10014","title":"Safety-Aware Fine-Tuning of Large Language Models","created":"2024-10-13","cited_by_count":34},{"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":"2402.14968","title":"Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment","created":"2024-02-22","cited_by_count":31},{"id":"2405.16802","title":"AutoPSV: Automated Process-Supervised Verifier","created":"2024-05-27","cited_by_count":30},{"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":"2405.02501","title":"PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning","created":"2024-05-03","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":"2410.03782","title":"DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation","created":"2024-10-03","cited_by_count":19},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15},{"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":"2405.01468","title":"Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models","created":"2024-05-02","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":"2404.04865","title":"On the Learnability of Out-of-distribution Detection","created":"2024-04-07","cited_by_count":8},{"id":"1509.08065","title":"Detecting Overlapping Communities from Local Spectral Subspaces","created":"2015-09-27","cited_by_count":6},{"id":"2405.18635","title":"When and How Does In-Distribution Label Help Out-of-Distribution Detection?","created":"2024-05-28","cited_by_count":6},{"id":"2408.07772","title":"Out-of-Distribution Learning with Human Feedback","created":"2024-08-14","cited_by_count":6},{"id":"2401.17514","title":"How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?","created":"2024-01-31","cited_by_count":5},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5},{"id":"2408.04851","title":"Your Classifier Can Be Secretly a Likelihood-Based OOD Detector","created":"2024-08-09","cited_by_count":4}],"next_cursor":null}