{"total":111,"rows":[{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876,"area":null},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2101.08231","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","created":"2021-01-20","cited_by_count":186,"area":null},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126,"area":null},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2403.00824","title":"Information Flow Routes: Automatically Interpreting Language Models at Scale","created":"2024-02-27","cited_by_count":95,"area":null},{"id":"2308.01862","title":"Wider and Deeper LLM Networks are Fairer LLM Evaluators","created":"2023-08-03","cited_by_count":94,"area":null},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2505.20063","title":"SAEs Are Good for Steering -- If You Select the Right Features","created":"2025-05-26","cited_by_count":78,"area":"mechinterp"},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2207.14251","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","created":"2022-07-28","cited_by_count":57,"area":null},{"id":"2205.07237","title":"Discovering Latent Concepts Learned in BERT","created":"2022-05-15","cited_by_count":56,"area":null},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2109.06105","title":"NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternatives","created":"2021-09-13","cited_by_count":46,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40,"area":null},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","cited_by_count":38,"area":null},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36,"area":null},{"id":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34,"area":null},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"area":"alignment"},{"id":"2105.15179","title":"How transfer learning impacts linguistic knowledge in deep NLP models?","created":"2021-05-31","cited_by_count":32,"area":null},{"id":"2410.06672","title":"Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures","created":"2024-10-09","cited_by_count":31,"area":"ssm"},{"id":"2303.13731","title":"How Does Attention Work in Vision Transformers? A Visual Analytics Attempt","created":"2023-03-24","cited_by_count":30,"area":null},{"id":"2305.19911","title":"Neuron to Graph: Interpreting Language Model Neurons at Scale","created":"2023-05-31","cited_by_count":27,"area":null},{"id":"2401.01814","title":"Large Language Models Relearn Removed Concepts","created":"2024-01-03","cited_by_count":27,"area":null},{"id":"2404.18923","title":"Holmes: A Benchmark to Assess the Linguistic Competence of Language Models","created":"2024-04-29","cited_by_count":26,"area":null},{"id":"2406.11193","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","created":"2024-06-17","cited_by_count":26,"area":"mllm"},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2206.15465","title":"Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values","created":"2022-06-30","cited_by_count":25,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2310.12611","title":"Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model","created":"2023-10-19","cited_by_count":22,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2112.03245","title":"GAM Changer: Editing Generalized Additive Models with Interactive Visualization","created":"2021-12-06","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":"2305.13386","title":"Can LLMs facilitate interpretation of pre-trained language models?","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2103.13678","title":"Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation","created":"2021-03-25","cited_by_count":15,"area":null},{"id":"2410.22330","title":"Vision-Language Models Create Cross-Modal Task Representations","created":"2024-10-29","cited_by_count":15,"area":"mllm"},{"id":"2412.06966","title":"Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research","created":"2024-12-09","cited_by_count":15,"area":"safety"},{"id":"2502.11856","title":"LLMs as a synthesis between symbolic and distributed approaches to language","created":"2025-02-17","cited_by_count":13,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2202.07184","title":"On the Origins of the Block Structure Phenomenon in Neural Network Representations","created":"2022-02-15","cited_by_count":10,"area":null},{"id":"2410.16930","title":"Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2605.01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","created":"2026-05-01","cited_by_count":10,"area":null},{"id":"2107.00439","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2102.09235","title":"Deep Residual Networks Learn the Geodesic Curve in the Wasserstein Space","created":"2021-02-18","cited_by_count":8,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2104.07456","title":"Effect of Post-processing on Contextualized Word Representations","created":"2021-04-15","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":"2108.01335","title":"Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability","created":"2021-08-03","cited_by_count":6,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2601.03115","title":"Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2103.08820","title":"EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2201.08214","title":"A Latent-Variable Model for Intrinsic Probing","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2307.04343","title":"Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2409.05910","title":"Property Neurons in Self-Supervised Speech Transformers","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2105.08039","title":"Fine-grained Interpretation and Causation Analysis in Deep NLP Models","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2210.12553","title":"Understanding Domain Learning in Language Models Through Subpopulation Analysis","created":"2022-10-22","cited_by_count":4,"area":null},{"id":"2304.12918","title":"N2G: A Scalable Approach for Quantifying Interpretable Neuron Representations in Large Language Models","created":"2023-04-22","cited_by_count":4,"area":"mechinterp"},{"id":"2401.10016","title":"Gender Bias in Machine Translation and The Era of Large Language Models","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2406.12347","title":"Interpreting Bias in Large Language Models: A Feature-Based Approach","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2412.11187","title":"Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models","created":"2024-12-15","cited_by_count":4,"area":null},{"id":"2502.17355","title":"On Relation-Specific Neurons in Large Language Models","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2210.12206","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2304.03427","title":"Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts","created":"2023-04-07","cited_by_count":3,"area":null},{"id":"2404.02650","title":"Towards detecting unanticipated bias in Large Language Models","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2407.12881","title":"BinaryAlign: Word Alignment as Binary Sequence Labeling","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2502.11806","title":"Exploring the Translation Mechanism of Large Language Models","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2506.23951","title":"Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders","created":"2025-06-30","cited_by_count":3,"area":"mechinterp"},{"id":"2510.24942","title":"Finding Culture-Sensitive Neurons in Vision-Language Models","created":"2025-10-28","cited_by_count":3,"area":"mllm"},{"id":"2606.02398","title":"A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2106.04935","title":"Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2110.03067","title":"On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2301.09611","title":"Explaining Deep Learning Hidden Neuron Activations using Concept Induction","created":"2023-01-23","cited_by_count":2,"area":null},{"id":"2312.04024","title":"k* Distribution: Evaluating the Latent Space of Deep Neural Networks using Local Neighborhood Analysis","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2403.02327","title":"Model Lakes","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2504.14766","title":"Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2506.02696","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2603.17231","title":"Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2210.09990","title":"Post-hoc analysis of Arabic transformer models","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2303.03019","title":"NxPlain: Web-based Tool for Discovery of Latent Concepts","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2305.00875","title":"Redundancy and Concept Analysis for Code-trained Language Models","created":"2023-05-01","cited_by_count":1,"area":null},{"id":"2608.08772","title":"Multilingual Emotion Neurons in Large Audio-Language Models","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2108.12124","title":"Canoe : A System for Collaborative Learning for Neural Nets","created":"2021-08-27","cited_by_count":0,"area":null},{"id":"2211.04198","title":"Third-Party Aligner for Neural Word Alignments","created":"2022-11-08","cited_by_count":0,"area":null},{"id":"2303.15072","title":"Exposing the Functionalities of Neurons for Gated Recurrent Unit Based Sequence-to-Sequence Model","created":"2023-03-27","cited_by_count":0,"area":null},{"id":"2307.14581","title":"Explainable Techniques for Analyzing Flow Cytometry Cell Transformers","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2310.17951","title":"Understanding Parameter Saliency via Extreme Value Theory","created":"2023-10-27","cited_by_count":0,"area":null}],"next_cursor":"100"}