{"total":97,"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":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319,"area":"wm"},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218,"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":"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":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"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":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82,"area":null},{"id":"2106.00085","title":"Language Model Evaluation Beyond Perplexity","created":"2021-05-31","cited_by_count":78,"area":null},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"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":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62,"area":"mechinterp"},{"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":"2501.06346","title":"Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages","created":"2025-01-10","cited_by_count":59,"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":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47,"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":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2105.13818","title":"Language Models Use Monotonicity to Assess NPI Licensing","created":"2021-05-28","cited_by_count":31,"area":null},{"id":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30,"area":"mllm"},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2502.05489","title":"Mechanistic Interpretability of Emotion Inference in Large Language Models","created":"2025-02-08","cited_by_count":27,"area":"mechinterp"},{"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":"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":"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":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","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":"2310.16484","title":"Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2407.04690","title":"Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks","created":"2024-07-05","cited_by_count":23,"area":null},{"id":"2506.03292","title":"HyperSteer: Activation Steering at Scale with Hypernetworks","created":"2025-06-03","cited_by_count":23,"area":"mechinterp"},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","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":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","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":"2109.07848","title":"The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation","created":"2021-09-16","cited_by_count":15,"area":null},{"id":"2410.20008","title":"Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Language Models","created":"2024-10-25","cited_by_count":15,"area":null},{"id":"2306.08193","title":"Operationalising Representation in Natural Language Processing","created":"2023-06-14","cited_by_count":14,"area":null},{"id":"2407.11015","title":"Does ChatGPT Have a Mind?","created":"2024-06-27","cited_by_count":14,"area":null},{"id":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2204.09722","title":"When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2310.11923","title":"Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing","created":"2023-10-18","cited_by_count":12,"area":null},{"id":"2310.15151","title":"Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2406.03707","title":"What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2411.07474","title":"Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models","created":"2024-11-12","cited_by_count":10,"area":null},{"id":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10,"area":"mechinterp"},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2110.07240","title":"Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans","created":"2021-10-14","cited_by_count":8,"area":null},{"id":"2310.15829","title":"Unnatural language processing: How do language models handle machine-generated prompts?","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2207.01736","title":"Probing via Prompting","created":"2022-07-04","cited_by_count":7,"area":null},{"id":"2212.04523","title":"Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement","created":"2022-12-08","cited_by_count":7,"area":null},{"id":"2312.14226","title":"Deep de Finetti: Recovering Topic Distributions from Large Language Models","created":"2023-12-21","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":"2404.12145","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2211.00153","title":"Do LSTMs See Gender? Probing the Ability of LSTMs to Learn Abstract Syntactic Rules","created":"2022-10-31","cited_by_count":6,"area":null},{"id":"2506.04706","title":"Line of Sight: On Linear Representations in VLLMs","created":"2025-06-05","cited_by_count":6,"area":"mechinterp"},{"id":"2604.12493","title":"Latent Planning Emerges with Scale","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2605.05892","title":"Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention","created":"2026-05-07","cited_by_count":6,"area":"mechinterp"},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2104.12847","title":"Morph Call: Probing Morphosyntactic Content of Multilingual Transformers","created":"2021-04-26","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":"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":"2605.03907","title":"Steer Like the LLM: Activation Steering that Mimics Prompting","created":"2026-05-05","cited_by_count":5,"area":"mechinterp"},{"id":"2106.03983","title":"Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2108.06806","title":"What can Neural Referential Form Selectors Learn?","created":"2021-08-15","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":"2312.09890","title":"Grammatical information in BERT sentence embeddings as two-dimensional arrays","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2504.12585","title":"Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2104.12424","title":"Attention vs non-attention for a Shapley-based explanation method","created":"2021-04-26","cited_by_count":3,"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":"2406.15265","title":"Perception of Phonological Assimilation by Neural Speech Recognition Models","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2109.10133","title":"Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement","created":"2021-09-21","cited_by_count":2,"area":null},{"id":"2212.10792","title":"Reconstruction Probing","created":"2022-12-21","cited_by_count":2,"area":null},{"id":"2110.15712","title":"Analysing the Effect of Masking Length Distribution of MLM: An Evaluation Framework and Case Study on Chinese MRC Datasets","created":"2021-09-29","cited_by_count":1,"area":null},{"id":"2409.12435","title":"Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language Models","created":"2024-09-19","cited_by_count":1,"area":null},{"id":"2410.03447","title":"How Language Models Prioritize Contextual Grammatical Cues?","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2410.06022","title":"Can Language Models Induce Grammatical Knowledge from Indirect Evidence?","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2101.00674","title":"Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs","created":"2021-01-03","cited_by_count":0,"area":null},{"id":"2103.03108","title":"An empirical analysis of phrase-based and neural machine translation","created":"2021-03-04","cited_by_count":0,"area":null},{"id":"2105.04707","title":"Accountable Error Characterization","created":"2021-05-10","cited_by_count":0,"area":null},{"id":"2201.12938","title":"Probe-Based Interventions for Modifying Agent Behavior","created":"2022-01-26","cited_by_count":0,"area":null},{"id":"2205.07603","title":"Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2210.04828","title":"Assessing Neural Referential Form Selectors on a Realistic Multilingual Dataset","created":"2022-10-10","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":"2411.02168","title":"Do graph neural network states contain graph properties?","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2411.16618","title":"StructFormer: Document Structure-based Masked Attention and its Impact on Language Model Pre-Training","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2602.10661","title":"Targeted Syntactic Evaluation of Language Models on Georgian Case Alignment","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2606.21203","title":"When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.20251","title":"Exposure is Optional: Learning Unlike Coordination in Language Models","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.22230","title":"List Counting Failures Are Not One Phenomenon","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}