{"total":143,"rows":[{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399,"area":null},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230,"area":null},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218,"area":null},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86,"area":null},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"area":null},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"area":null},{"id":"2106.07171","title":"Examining and Combating Spurious Features under Distribution Shift","created":"2021-06-14","cited_by_count":65,"area":null},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65,"area":null},{"id":"2107.00758","title":"The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models","created":"2021-07-01","cited_by_count":63,"area":null},{"id":"2102.12206","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","created":"2021-02-24","cited_by_count":61,"area":null},{"id":"2106.06142","title":"DORO: Distributional and Outlier Robust Optimization","created":"2021-06-11","cited_by_count":56,"area":null},{"id":"2408.14037","title":"Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning","created":"2024-08-26","cited_by_count":47,"area":"offlinerl"},{"id":"2301.09819","title":"Model Agnostic Sample Reweighting for Out-of-Distribution Learning","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39,"area":null},{"id":"2306.04949","title":"Robust Learning with Progressive Data Expansion Against Spurious Correlation","created":"2023-06-08","cited_by_count":39,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2111.14923","title":"Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models","created":"2021-11-29","cited_by_count":36,"area":null},{"id":"2202.05436","title":"Minimax Regret Optimization for Robust Machine Learning under Distribution Shift","created":"2022-02-11","cited_by_count":31,"area":null},{"id":"2202.07241","title":"Learning to Solve Routing Problems via Distributionally Robust Optimization","created":"2022-02-15","cited_by_count":31,"area":null},{"id":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30,"area":null},{"id":"2103.10282","title":"Modeling the Second Player in Distributionally Robust Optimization","created":"2021-03-18","cited_by_count":29,"area":null},{"id":"2201.12293","title":"Understanding Why Generalized Reweighting Does Not Improve Over ERM","created":"2022-01-28","cited_by_count":29,"area":null},{"id":"2109.13986","title":"Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics","created":"2021-09-28","cited_by_count":27,"area":null},{"id":"2206.00437","title":"What a Creole Wants, What a Creole Needs","created":"2022-06-01","cited_by_count":27,"area":null},{"id":"2210.11075","title":"Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise","created":"2022-10-20","cited_by_count":22,"area":null},{"id":"2501.11039","title":"Model Predictive Task Sampling for Efficient and Robust Adaptation","created":"2025-01-19","cited_by_count":21,"area":null},{"id":"2210.15212","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","created":"2022-10-27","cited_by_count":20,"area":null},{"id":"2303.00442","title":"Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization","created":"2023-03-01","cited_by_count":20,"area":null},{"id":"2406.02764","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","created":"2024-06-04","cited_by_count":20,"area":"alignment"},{"id":"2203.12788","title":"Evaluating Distributional Distortion in Neural Language Modeling","created":"2022-03-24","cited_by_count":19,"area":null},{"id":"2109.04020","title":"Distributionally Robust Multilingual Machine Translation","created":"2021-09-09","cited_by_count":18,"area":null},{"id":"2109.06074","title":"On Language Models for Creoles","created":"2021-09-13","cited_by_count":17,"area":null},{"id":"2204.06340","title":"Distributionally Robust Models with Parametric Likelihood Ratios","created":"2022-04-13","cited_by_count":17,"area":null},{"id":"2212.13669","title":"Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond","created":"2022-12-28","cited_by_count":17,"area":null},{"id":"2506.03850","title":"Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning","created":"2025-06-04","cited_by_count":17,"area":"alignment"},{"id":"2105.12628","title":"Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers","created":"2021-05-26","cited_by_count":16,"area":null},{"id":"2203.14276","title":"Example-based Hypernetworks for Out-of-Distribution Generalization","created":"2022-03-27","cited_by_count":16,"area":null},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2406.10973","title":"ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts","created":"2024-06-16","cited_by_count":16,"area":null},{"id":"2110.08413","title":"Invariant Language Modeling","created":"2021-10-16","cited_by_count":15,"area":null},{"id":"2111.04986","title":"Unified Group Fairness on Federated Learning","created":"2021-11-09","cited_by_count":15,"area":null},{"id":"2203.13225","title":"Distributionally Robust Optimization via Ball Oracle Acceleration","created":"2022-03-24","cited_by_count":14,"area":null},{"id":"2209.01754","title":"Learning from a Biased Sample","created":"2022-09-05","cited_by_count":14,"area":null},{"id":"2309.07438","title":"Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2210.09644","title":"Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2108.12250","title":"A comparison of approaches to improve worst-case predictive model performance over patient subpopulations","created":"2021-08-27","cited_by_count":12,"area":null},{"id":"2303.13360","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","created":"2023-03-16","cited_by_count":12,"area":null},{"id":"2203.02745","title":"The Impact of Differential Privacy on Group Disparity Mitigation","created":"2022-03-05","cited_by_count":11,"area":null},{"id":"2205.12753","title":"An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation","created":"2022-05-25","cited_by_count":11,"area":null},{"id":"2402.17729","title":"Towards Fairness-Aware Adversarial Learning","created":"2024-02-27","cited_by_count":11,"area":null},{"id":"2403.03562","title":"Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond","created":"2024-03-06","cited_by_count":11,"area":null},{"id":"2410.15661","title":"Scalable Data Ablation Approximations for Language Models through Modular Training and Merging","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2109.07591","title":"On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation","created":"2021-09-15","cited_by_count":10,"area":null},{"id":"2110.05838","title":"Balancing Average and Worst-case Accuracy in Multitask Learning","created":"2021-10-12","cited_by_count":10,"area":null},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","cited_by_count":10,"area":null},{"id":"2402.04676","title":"Group Distributionally Robust Dataset Distillation with Risk Minimization","created":"2024-02-07","cited_by_count":10,"area":null},{"id":"2506.07899","title":"MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs","created":"2025-06-09","cited_by_count":10,"area":null},{"id":"2112.08321","title":"Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics","created":"2021-12-15","cited_by_count":9,"area":null},{"id":"2302.02931","title":"Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts","created":"2023-02-06","cited_by_count":9,"area":null},{"id":"2211.00384","title":"The future is different: Large pre-trained language models fail in prediction tasks","created":"2022-11-01","cited_by_count":8,"area":null},{"id":"2305.04547","title":"Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias","created":"2023-05-08","cited_by_count":8,"area":"safety"},{"id":"2403.13870","title":"ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2409.17691","title":"Efficient Bias Mitigation Without Privileged Information","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2506.00569","title":"AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs","created":"2025-05-31","cited_by_count":8,"area":"alignment"},{"id":"2210.12262","title":"Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2306.01922","title":"Agnostic Multi-Group Active Learning","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2402.11039","title":"Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domains","created":"2024-02-16","cited_by_count":7,"area":null},{"id":"2602.08470","title":"Learning Credal Ensembles via Distributionally Robust Optimization","created":"2026-02-09","cited_by_count":7,"area":null},{"id":"2104.08453","title":"R&R: Metric-guided Adversarial Sentence Generation","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2106.07847","title":"Learning Stable Classifiers by Transferring Unstable Features","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2201.03668","title":"Towards Group Robustness in the presence of Partial Group Labels","created":"2022-01-10","cited_by_count":6,"area":null},{"id":"2210.13533","title":"Sufficient Invariant Learning for Distribution Shift","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2309.06717","title":"Bias Amplification Enhances Minority Group Performance","created":"2023-09-13","cited_by_count":6,"area":null},{"id":"2310.13008","title":"DavIR: Data Selection via Implicit Reward for Large Language Models","created":"2023-10-16","cited_by_count":6,"area":"alignment"},{"id":"2410.04579","title":"Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets","created":"2024-10-06","cited_by_count":6,"area":null},{"id":"2508.06533","title":"The Art of Breaking Words: Rethinking Multilingual Tokenizer Design","created":"2025-08-03","cited_by_count":6,"area":"lr"},{"id":"2308.10103","title":"ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations","created":"2023-08-19","cited_by_count":5,"area":null},{"id":"2411.14055","title":"DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2109.10432","title":"Beyond Discriminant Patterns: On the Robustness of Decision Rule Ensembles","created":"2021-09-21","cited_by_count":4,"area":null},{"id":"2212.07026","title":"Improving group robustness under noisy labels using predictive uncertainty","created":"2022-12-14","cited_by_count":4,"area":null},{"id":"2306.00026","title":"Efficient Stochastic Approximation of Minimax Excess Risk Optimization","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2212.08967","title":"Foundation models in brief: A historical, socio-technical focus","created":"2022-12-17","cited_by_count":3,"area":null},{"id":"2302.01385","title":"Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2305.18503","title":"From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2312.00486","title":"REDUCR: Robust Data Downsampling Using Class Priority Reweighting","created":"2023-12-01","cited_by_count":3,"area":null},{"id":"2410.14315","title":"Optimizing importance weighting in the presence of sub-population shifts","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2411.01644","title":"Achieving Domain-Independent Certified Robustness via Knowledge Continuity","created":"2024-11-03","cited_by_count":3,"area":null},{"id":"2510.06048","title":"BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2512.01766","title":"On the Unreasonable Effectiveness of Last-layer Retraining","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2512.10445","title":"Maximum Risk Minimization with Random Forests","created":"2025-12-11","cited_by_count":3,"area":null}],"next_cursor":"100"}