{"list":"other","total":95,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1711.00399","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","created":"2017-11-01","cited_by_count":1089},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1412.3756","title":"Certifying and removing disparate impact","created":"2014-12-11","cited_by_count":715},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"1610.08452","title":"Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment","created":"2016-10-26","cited_by_count":369},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353},{"id":"1804.03599","title":"Understanding disentangling in $\\beta$-VAE","created":"2018-04-10","cited_by_count":335},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"1301.2300","title":"Direct and Indirect Effects","created":"2013-01-10","cited_by_count":280},{"id":"2002.06278","title":"Algorithmic Recourse: from Counterfactual Explanations to Interventions","created":"2020-02-14","cited_by_count":250},{"id":"1911.10500","title":"Causality for Machine Learning","created":"2019-11-24","cited_by_count":243},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205},{"id":"1905.11190","title":"Model-Agnostic Counterfactual Explanations for Consequential Decisions","created":"2019-05-27","cited_by_count":204},{"id":"2010.07922","title":"Representation Learning via Invariant Causal Mechanisms","created":"2020-10-15","cited_by_count":199},{"id":"1706.02744","title":"Avoiding Discrimination through Causal Reasoning","created":"2017-06-08","cited_by_count":194},{"id":"1802.08139","title":"Path-Specific Counterfactual Fairness","created":"2018-02-22","cited_by_count":181},{"id":"2501.16496","title":"Open Problems in Mechanistic Interpretability","created":"2025-01-27","cited_by_count":179},{"id":"1705.10378","title":"Fair Inference On Outcomes","created":"2017-05-29","cited_by_count":144},{"id":"1906.08386","title":"Inherent Tradeoffs in Learning Fair Representations","created":"2019-06-19","cited_by_count":144},{"id":"2311.07361","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","created":"2023-11-13","cited_by_count":112},{"id":"2206.15475","title":"Causal Machine Learning: A Survey and Open Problems","created":"2022-06-30","cited_by_count":110},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107},{"id":"2305.15054","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","created":"2023-05-24","cited_by_count":89},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79},{"id":"1910.12586","title":"PC-Fairness: A Unified Framework for Measuring Causality-based Fairness","created":"2019-10-20","cited_by_count":67},{"id":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62},{"id":"2010.02458","title":"Identifying Spurious Correlations for Robust Text Classification","created":"2020-10-06","cited_by_count":59},{"id":"1905.12744","title":"Fair Decision Making using Privacy-Protected Data","created":"2019-05-29","cited_by_count":58},{"id":"1805.05859","title":"Causal Reasoning for Algorithmic Fairness","created":"2018-05-15","cited_by_count":51},{"id":"2402.11917","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","created":"2024-02-19","cited_by_count":49},{"id":"1505.05723","title":"On the relation between accuracy and fairness in binary classification","created":"2015-05-21","cited_by_count":48},{"id":"2212.05015","title":"Robustness Implies Privacy in Statistical Estimation","created":"2022-12-09","cited_by_count":47},{"id":"1502.02454","title":"A fast PC algorithm for high dimensional causal discovery with multi-core PCs","created":"2015-02-09","cited_by_count":45},{"id":"2011.11878","title":"Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder","created":"2020-11-24","cited_by_count":45},{"id":"2406.17759","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","created":"2024-06-25","cited_by_count":43},{"id":"2406.05972","title":"Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context","created":"2024-06-10","cited_by_count":41},{"id":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39},{"id":"2102.01203","title":"Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Research","created":"2021-02-01","cited_by_count":34},{"id":"2106.02705","title":"Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning","created":"2021-06-04","cited_by_count":34},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31},{"id":"2104.11914","title":"EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case","created":"2021-04-24","cited_by_count":30},{"id":"2212.10534","title":"DISCO: Distilling Counterfactuals with Large Language Models","created":"2022-12-20","cited_by_count":30},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30},{"id":"2402.09236","title":"Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models","created":"2024-02-14","cited_by_count":29},{"id":"2405.01744","title":"ALCM: Autonomous LLM-Augmented Causal Discovery Framework","created":"2024-05-02","cited_by_count":29},{"id":"2212.10678","title":"Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias","created":"2022-12-20","cited_by_count":28},{"id":"2008.10797","title":"The Fairness-Accuracy Pareto Front","created":"2020-08-25","cited_by_count":26},{"id":"2410.15319","title":"Causality for Large Language Models","created":"2024-10-20","cited_by_count":25},{"id":"2412.16429","title":"LearnLM: Improving Gemini for Learning","created":"2024-12-21","cited_by_count":25},{"id":"1711.08936","title":"Causal Generative Neural Networks","created":"2017-11-24","cited_by_count":24},{"id":"2305.14695","title":"A Causal View of Entity Bias in (Large) Language Models","created":"2023-05-24","cited_by_count":21},{"id":"2205.13972","title":"Counterfactual Fairness with Partially Known Causal Graph","created":"2022-05-27","cited_by_count":20},{"id":"2303.02186","title":"Causal Deep Learning","created":"2023-03-03","cited_by_count":20},{"id":"1909.12732","title":"Alleviating Privacy Attacks via Causal Learning","created":"2019-09-27","cited_by_count":19},{"id":"2405.04160","title":"A Causal Explainable Guardrails for Large Language Models","created":"2024-05-07","cited_by_count":18},{"id":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14},{"id":"2110.00911","title":"Enhancing Model Robustness and Fairness with Causality: A Regularization Approach","created":"2021-10-03","cited_by_count":11},{"id":"1903.00402","title":"Machine learning in policy evaluation: new tools for causal inference","created":"2019-03-01","cited_by_count":10},{"id":"2106.16091","title":"Exploring the Latent Space of Autoencoders with Interventional Assays","created":"2021-06-30","cited_by_count":10},{"id":"2405.15443","title":"Fairness-Accuracy Trade-Offs: A Causal Perspective","created":"2024-05-24","cited_by_count":10},{"id":"2407.18069","title":"$\\text{C}^2\\text{P}$: Featuring Large Language Models with Causal Reasoning","created":"2024-07-25","cited_by_count":8},{"id":"1405.2292","title":"Statistical Causality from a Decision-Theoretic Perspective","created":"2014-05-09","cited_by_count":7},{"id":"2306.00374","title":"CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation","created":"2023-06-01","cited_by_count":7},{"id":"2410.15828","title":"LLM4GRN: Discovering Causal Gene Regulatory Networks with LLMs -- Evaluation through Synthetic Data Generation","created":"2024-10-21","cited_by_count":7},{"id":"2201.05226","title":"Towards a Data Privacy-Predictive Performance Trade-off","created":"2022-01-13","cited_by_count":6},{"id":"2403.14713","title":"Auditing Fairness under Unobserved Confounding","created":"2024-03-18","cited_by_count":6},{"id":"2404.05545","title":"Evaluating Interventional Reasoning Capabilities of Large Language Models","created":"2024-04-08","cited_by_count":6},{"id":"2201.10683","title":"Promises and Challenges of Causality for Ethical Machine Learning","created":"2022-01-26","cited_by_count":4},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4},{"id":"1806.02380","title":"Causal Interventions for Fairness","created":"2018-06-06","cited_by_count":3},{"id":"2205.09281","title":"Causal Inference from Small High-dimensional Datasets","created":"2022-05-19","cited_by_count":3},{"id":"2310.19391","title":"Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustness","created":"2023-10-30","cited_by_count":3},{"id":"2311.04037","title":"Causal Discovery Under Local Privacy","created":"2023-11-07","cited_by_count":3},{"id":"2406.07685","title":"Test-Time Fairness and Robustness in Large Language Models","created":"2024-06-11","cited_by_count":3},{"id":"2410.23494","title":"Causality-Driven Audits of Model Robustness","created":"2024-10-30","cited_by_count":2},{"id":"2212.00911","title":"Navigating causal deep learning","created":"2022-12-01","cited_by_count":1},{"id":"2407.15012","title":"Transformative Influence of LLM and AI Tools in Student Social Media Engagement: Analyzing Personalization, Communication Efficiency, and Collaborative Learning","created":"2024-06-15","cited_by_count":1}],"next_cursor":null}