{"total":191,"rows":[{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691,"area":null},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"area":"mechinterp"},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553,"area":null},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214,"area":null},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"area":null},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209,"area":"mechinterp"},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174,"area":null},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"area":null},{"id":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97,"area":null},{"id":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"area":null},{"id":"2405.08366","title":"Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control","created":"2024-05-14","cited_by_count":86,"area":"mechinterp"},{"id":"2311.17030","title":"Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching","created":"2023-11-28","cited_by_count":80,"area":"mechinterp"},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"area":"lr"},{"id":"2405.12241","title":"Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning","created":"2024-05-17","cited_by_count":67,"area":"mechinterp"},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59,"area":null},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"area":null},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2104.08666","title":"Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models","created":"2021-04-18","cited_by_count":52,"area":null},{"id":"2406.04236","title":"Understanding Information Storage and Transfer in Multi-modal Large Language Models","created":"2024-06-06","cited_by_count":49,"area":"mllm"},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"id":"2406.17759","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","created":"2024-06-25","cited_by_count":43,"area":"mechinterp"},{"id":"2107.14202","title":"Human Trajectory Prediction via Counterfactual Analysis","created":"2021-07-29","cited_by_count":42,"area":null},{"id":"2105.14002","title":"What if This Modified That? Syntactic Interventions via Counterfactual Embeddings","created":"2021-05-28","cited_by_count":39,"area":null},{"id":"2309.14356","title":"COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs","created":"2023-09-23","cited_by_count":39,"area":null},{"id":"2402.15390","title":"Explorations of Self-Repair in Language Models","created":"2024-02-23","cited_by_count":39,"area":null},{"id":"2410.04962","title":"Activation Scaling for Steering and Interpreting Language Models","created":"2024-10-07","cited_by_count":35,"area":null},{"id":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34,"area":null},{"id":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29,"area":"lr"},{"id":"2410.09223","title":"The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling","created":"2024-10-11","cited_by_count":28,"area":"mechinterp"},{"id":"2411.16679","title":"Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?","created":"2024-11-25","cited_by_count":28,"area":"lr"},{"id":"2312.03656","title":"Interpretability Illusions in the Generalization of Simplified Models","created":"2023-12-06","cited_by_count":25,"area":null},{"id":"2310.18913","title":"Debiasing Algorithm through Model Adaptation","created":"2023-10-29","cited_by_count":24,"area":null},{"id":"2312.06581","title":"Grokking Group Multiplication with Cosets","created":"2023-12-11","cited_by_count":24,"area":null},{"id":"2210.12365","title":"NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2407.00886","title":"Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition","created":"2024-07-01","cited_by_count":23,"area":"mechinterp"},{"id":"2305.14695","title":"A Causal View of Entity Bias in (Large) Language Models","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2408.10646","title":"Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs","created":"2024-08-20","cited_by_count":21,"area":null},{"id":"2505.16002","title":"Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions","created":"2025-05-21","cited_by_count":21,"area":null},{"id":"2502.11812","title":"Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis","created":"2025-02-17","cited_by_count":20,"area":null},{"id":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19,"area":null},{"id":"2205.06303","title":"Using Natural Sentences for Understanding Biases in Language Models","created":"2022-05-12","cited_by_count":19,"area":null},{"id":"2412.04703","title":"Transformers Struggle to Learn to Search","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2503.08588","title":"BiasEdit: Debiasing Stereotyped Language Models via Model Editing","created":"2025-03-11","cited_by_count":18,"area":null},{"id":"2506.10922","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","created":"2025-06-12","cited_by_count":18,"area":null},{"id":"2410.10626","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts","created":"2024-10-14","cited_by_count":17,"area":"moe"},{"id":"2110.02802","title":"Self-conditioning pre-trained language models","created":"2021-09-30","cited_by_count":16,"area":null},{"id":"2205.10095","title":"How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing","created":"2022-05-20","cited_by_count":16,"area":null},{"id":"2207.10245","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2411.00743","title":"Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models","created":"2024-11-01","cited_by_count":16,"area":"mechinterp"},{"id":"2104.07505","title":"Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2510.00845","title":"Mechanistic Interpretability as Statistical Estimation: A Variance Analysis","created":"2025-10-01","cited_by_count":15,"area":"mechinterp"},{"id":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2306.08193","title":"Operationalising Representation in Natural Language Processing","created":"2023-06-14","cited_by_count":14,"area":null},{"id":"2407.10785","title":"Learning biologically relevant features in a pathology foundation model using sparse autoencoders","created":"2024-07-15","cited_by_count":14,"area":"mechinterp"},{"id":"2410.14155","title":"Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models","created":"2024-10-18","cited_by_count":14,"area":"mechinterp"},{"id":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2403.17333","title":"The Pursuit of Fairness in Artificial Intelligence Models: A Survey","created":"2024-03-26","cited_by_count":13,"area":null},{"id":"2405.19162","title":"Does learning the right latent variables necessarily improve in-context learning?","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2501.06751","title":"Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models","created":"2025-01-12","cited_by_count":13,"area":"diffusion"},{"id":"2504.13752","title":"Learning to Attribute with Attention","created":"2025-04-18","cited_by_count":13,"area":null},{"id":"2310.14805","title":"Cross-Modal Conceptualization in Bottleneck Models","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2402.00322","title":"Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in Political Bias","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2403.14409","title":"Locating and Mitigating Gender Bias in Large Language Models","created":"2024-03-21","cited_by_count":12,"area":null},{"id":"2406.17583","title":"Towards Compositional Interpretability for XAI","created":"2024-06-25","cited_by_count":12,"area":null},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2408.15510","title":"How Reliable are Causal Probing Interventions?","created":"2024-08-28","cited_by_count":11,"area":null},{"id":"2409.13710","title":"You can remove GPT2's LayerNorm by fine-tuning","created":"2024-09-06","cited_by_count":11,"area":"mechinterp"},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2506.12880","title":"Universal Jailbreak Suffixes Are Strong Attention Hijackers","created":"2025-06-15","cited_by_count":10,"area":"safety"},{"id":"2605.07990","title":"Tool Calling is Linearly Readable and Steerable in Language Models","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2310.14508","title":"EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2412.12276","title":"Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective","created":"2024-12-16","cited_by_count":9,"area":null},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9,"area":null},{"id":"2405.00664","title":"Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3","created":"2024-05-01","cited_by_count":8,"area":null},{"id":"2405.10928","title":"The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks","created":"2024-05-17","cited_by_count":8,"area":"mechinterp"},{"id":"2408.14915","title":"Can Transformers Do Enumerative Geometry?","created":"2024-08-27","cited_by_count":8,"area":null},{"id":"2502.01179","title":"Joint Localization and Activation Editing for Low-Resource Fine-Tuning","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2502.13319","title":"Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare","created":"2025-02-18","cited_by_count":8,"area":"mechinterp"},{"id":"2306.00374","title":"CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2505.08546","title":"Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation","created":"2025-05-13","cited_by_count":7,"area":null},{"id":"2511.04638","title":"Addressing divergent representations from causal interventions on neural networks","created":"2025-11-06","cited_by_count":7,"area":"mechinterp"},{"id":"2407.11542","title":"Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2501.06141","title":"Emergent Symbol-like Number Variables in Artificial Neural Networks","created":"2025-01-10","cited_by_count":6,"area":null},{"id":"2511.19265","title":"Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks","created":"2025-11-24","cited_by_count":6,"area":"mechinterp"},{"id":"2404.01903","title":"Understanding How CodeLLMs (Mis)Predict Types with Activation Steering","created":"2024-04-02","cited_by_count":5,"area":"mechinterp"},{"id":"2406.02335","title":"Probing the Category of Verbal Aspect in Transformer Language Models","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2507.12838","title":"Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2605.10815","title":"Probing Cross-modal Information Hubs in Audio-Visual LLMs","created":"2026-05-11","cited_by_count":5,"area":null}],"next_cursor":"100"}