{"total":59,"rows":[{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267,"area":null},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"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":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2403.19827","title":"Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs","created":"2024-03-28","cited_by_count":65,"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":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","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":"2310.11877","title":"The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models","created":"2023-10-18","cited_by_count":55,"area":null},{"id":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48,"area":null},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2203.09397","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","created":"2022-03-17","cited_by_count":28,"area":null},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25,"area":null},{"id":"2211.09748","title":"Probing for Incremental Parse States in Autoregressive Language Models","created":"2022-11-17","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":"2301.12564","title":"A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction","created":"2023-01-29","cited_by_count":22,"area":null},{"id":"2310.16142","title":"A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing","created":"2023-10-24","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":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","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":"2210.14328","title":"Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models","created":"2022-10-25","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":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2408.15510","title":"How Reliable are Causal Probing Interventions?","created":"2024-08-28","cited_by_count":11,"area":null},{"id":"2601.07220","title":"The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?","created":"2026-01-12","cited_by_count":11,"area":null},{"id":"2204.09168","title":"Analyzing Gender Representation in Multilingual Models","created":"2022-04-20","cited_by_count":10,"area":null},{"id":"2502.07687","title":"Large Language Models as Proxies for Theories of Human Linguistic Cognition","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2407.19789","title":"Interpreting Low-level Vision Models with Causal Effect Maps","created":"2024-07-29","cited_by_count":8,"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":"2306.03882","title":"Causal interventions expose implicit situation models for commonsense language understanding","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2305.14555","title":"All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations","created":"2023-05-23","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":"2502.15277","title":"Analyzing the Inner Workings of Transformers in Compositional Generalization","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2604.12493","title":"Latent Planning Emerges with Scale","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2211.06420","title":"The Architectural Bottleneck Principle","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2404.01903","title":"Understanding How CodeLLMs (Mis)Predict Types with Activation Steering","created":"2024-04-02","cited_by_count":5,"area":"mechinterp"},{"id":"2405.04048","title":"Philosophy of Cognitive Science in the Age of Deep Learning","created":"2024-05-07","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":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2402.11355","title":"A Practical Method for Generating String Counterfactuals","created":"2024-02-17","cited_by_count":4,"area":null},{"id":"2305.18185","title":"Syntax and Semantics Meet in the \"Middle\": Probing the Syntax-Semantics Interface of LMs Through Agentivity","created":"2023-05-29","cited_by_count":3,"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":"2305.16409","title":"Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2310.18862","title":"Counterfactually Probing Language Identity in Multilingual Models","created":"2023-10-29","cited_by_count":2,"area":null},{"id":"2410.13488","title":"Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2410.21353","title":"Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics","created":"2024-10-28","cited_by_count":1,"area":"lr"},{"id":"2508.20944","title":"STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2512.06814","title":"CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2605.06640","title":"Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2508.17576","title":"CausalSent: Interpretable Sentiment Classification with RieszNet","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2605.07631","title":"Inference Time Causal Probing in LLMs","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.29971","title":"Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning","created":"2026-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2607.26179","title":"Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.33883","title":"Lost with a Map: Conversational State and Behavioral Reliability in Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.07270","title":"Does the Model Use the Feature? Separating Steering from Mechanism in LLMs","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}