{"total":151,"rows":[{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876,"area":null},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"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":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"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":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141,"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":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2101.11109","title":"First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT","created":"2021-01-26","cited_by_count":65,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2312.03729","title":"Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?","created":"2023-11-27","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":"2305.06360","title":"Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy","created":"2023-05-10","cited_by_count":51,"area":"safety"},{"id":"2310.14491","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","created":"2023-10-23","cited_by_count":50,"area":"lr"},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"area":null},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","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":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2411.03343","title":"What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks","created":"2024-11-02","cited_by_count":29,"area":"safety"},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2310.18969","title":"Analyzing Vision Transformers for Image Classification in Class Embedding Space","created":"2023-10-29","cited_by_count":26,"area":null},{"id":"2603.17839","title":"How do LLMs Compute Verbal Confidence","created":"2026-03-18","cited_by_count":26,"area":null},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2110.04399","title":"Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors","created":"2021-10-08","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":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"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":"2205.07043","title":"Naturalistic Causal Probing for Morpho-Syntax","created":"2022-05-14","cited_by_count":19,"area":null},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2407.05441","title":"Language Representations Can be What Recommenders Need: Findings and Potentials","created":"2024-07-07","cited_by_count":18,"area":null},{"id":"2104.08197","title":"Probing artificial neural networks: insights from neuroscience","created":"2021-04-16","cited_by_count":17,"area":null},{"id":"2210.06545","title":"GULP: a prediction-based metric between representations","created":"2022-10-12","cited_by_count":17,"area":null},{"id":"2505.13737","title":"Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers","created":"2025-05-19","cited_by_count":16,"area":null},{"id":"2105.13471","title":"Inspecting the concept knowledge graph encoded by modern language models","created":"2021-05-27","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":"2210.01963","title":"COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models","created":"2022-10-05","cited_by_count":15,"area":null},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","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":"2312.01648","title":"Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation","created":"2023-12-04","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":"2303.03951","title":"Probing Graph Representations","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2108.00578","title":"Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning","created":"2021-08-02","cited_by_count":9,"area":null},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2306.06205","title":"Morphosyntactic probing of multilingual BERT models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2205.16001","title":"On the Usefulness of Embeddings, Clusters and Strings for Text Generator Evaluation","created":"2022-05-31","cited_by_count":7,"area":null},{"id":"2207.01736","title":"Probing via Prompting","created":"2022-07-04","cited_by_count":7,"area":null},{"id":"2211.04281","title":"SocioProbe: What, When, and Where Language Models Learn about Sociodemographics","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2212.11672","title":"Trustworthy Social Bias Measurement","created":"2022-12-20","cited_by_count":7,"area":null},{"id":"2312.16257","title":"More than Correlation: Do Large Language Models Learn Causal Representations of Space?","created":"2023-12-26","cited_by_count":7,"area":null},{"id":"2506.16678","title":"Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations","created":"2025-06-20","cited_by_count":7,"area":null},{"id":"2110.08887","title":"Schr\\\"odinger's Tree -- On Syntax and Neural Language Models","created":"2021-10-17","cited_by_count":6,"area":null},{"id":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2310.11991","title":"Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2402.01375","title":"Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization","created":"2024-02-02","cited_by_count":6,"area":null},{"id":"2506.02996","title":"Linear Spatial World Models Emerge in Large Language Models","created":"2025-06-03","cited_by_count":6,"area":"wm"},{"id":"2604.12493","title":"Latent Planning Emerges with Scale","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2201.08214","title":"A Latent-Variable Model for Intrinsic Probing","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2208.12352","title":"OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2304.10346","title":"Interventional Probing in High Dimensions: An NLI Case Study","created":"2023-04-20","cited_by_count":5,"area":null},{"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":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2504.06303","title":"On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions","created":"2025-04-07","cited_by_count":5,"area":null},{"id":"2506.04461","title":"Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2202.12801","title":"On the data requirements of probing","created":"2022-02-25","cited_by_count":4,"area":null},{"id":"2207.03679","title":"Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions","created":"2022-07-08","cited_by_count":4,"area":null},{"id":"2207.03777","title":"Hidden Schema Networks","created":"2022-07-08","cited_by_count":4,"area":null},{"id":"2404.02619","title":"Adjusting Interpretable Dimensions in Embedding Space with Human Judgments","created":"2024-04-03","cited_by_count":4,"area":null},{"id":"2405.17209","title":"How Do Transformers \"Do\" Physics? Investigating the Simple Harmonic Oscillator","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2412.05353","title":"Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models","created":"2024-12-06","cited_by_count":4,"area":null},{"id":"2602.15183","title":"Seeing to Generalize: How Visual Data Corrects Binding Shortcuts","created":"2026-02-16","cited_by_count":4,"area":"mllm"},{"id":"2604.16042","title":"Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures","created":"2026-04-17","cited_by_count":4,"area":"mechinterp"},{"id":"2201.10262","title":"Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language","created":"2022-01-25","cited_by_count":3,"area":null},{"id":"2210.17108","title":"Do Charge Prediction Models Learn Legal Theory?","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2310.03149","title":"Attributing Learned Concepts in Neural Networks to Training Data","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2506.02172","title":"Different Speech Translation Models Encode and Translate Speaker Gender Differently","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2210.17406","title":"Emergent Linguistic Structures in Neural Networks are Fragile","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2404.02389","title":"On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2410.02611","title":"IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2410.12011","title":"Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2410.18527","title":"Probing Ranking LLMs: A Mechanistic Analysis for Information Retrieval","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2510.14262","title":"CAST: Compositional Analysis via Spectral Tracking for Understanding Transformer Layer Functions","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2601.03798","title":"Where meaning lives: Layer-wise accessibility of psycholinguistic features in encoder and decoder language models","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.04074","title":"Stroke Lesions as a Rosetta Stone for Language Model Interpretability","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2604.02459","title":"On the Geometric Structure of Layer Updates in Deep Language Models","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2604.17079","title":"Auditing Support Strategies in LLMs through Grounded Multi-Turn Social Simulation","created":"2026-04-18","cited_by_count":2,"area":null},{"id":"2606.11205","title":"Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention","created":"2026-04-22","cited_by_count":2,"area":"mechinterp"},{"id":"2203.15860","title":"Visualizing the Relationship Between Encoded Linguistic Information and Task Performance","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2301.08998","title":"Syntax-guided Neural Module Distillation to Probe Compositionality in Sentence Embeddings","created":"2023-01-21","cited_by_count":1,"area":null},{"id":"2305.16328","title":"Semantic Composition in Visually Grounded Language Models","created":"2023-05-15","cited_by_count":1,"area":null},{"id":"2310.13856","title":"Implications of Annotation Artifacts in Edge Probing Test Datasets","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2404.14270","title":"What do Transformers Know about Government?","created":"2024-04-22","cited_by_count":1,"area":null},{"id":"2503.09068","title":"Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information","created":"2025-03-12","cited_by_count":1,"area":null}],"next_cursor":"100"}