{"total":31,"rows":[{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267,"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":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87,"area":null},{"id":"2305.10204","title":"Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25,"area":null},{"id":"2402.06900","title":"Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric","created":"2024-02-10","cited_by_count":23,"area":null},{"id":"2506.00823","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2408.15510","title":"How Reliable are Causal Probing Interventions?","created":"2024-08-28","cited_by_count":11,"area":null},{"id":"2305.14016","title":"Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation","created":"2023-05-23","cited_by_count":10,"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":"2210.10689","title":"Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information","created":"2022-10-19","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":"2305.16863","title":"Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2404.09601","title":"Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression","created":"2024-04-15","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":"2410.02472","title":"Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2303.00333","title":"Competence-Based Analysis of Language Models","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2506.10641","title":"Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2506.10703","title":"Preserving Task-Relevant Information Under Linear Concept Removal","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2402.11608","title":"Metric Learning Encoding Models: A Multivariate Framework for Interpreting Neural Representations","created":"2024-02-18","cited_by_count":3,"area":null},{"id":"2410.14315","title":"Optimizing importance weighting in the presence of sub-population shifts","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2306.11072","title":"Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes","created":"2023-06-19","cited_by_count":1,"area":null},{"id":"2509.25260","title":"Internal Planning in Language Models: Characterizing Horizon and Branch Awareness","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2602.17036","title":"LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2608.08266","title":"On the Robustness of LLMs' Internal Representation of Code Correctness","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2602.00459","title":"What Matters to an LLM? Behavioral and Computational Evidences from Summarization","created":"2026-01-31","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":"2605.11237","title":"DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.28319","title":"Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.36307","title":"Cheap and Powerful Tests for Supervised Subspaces: Per-Component Inference for PLS","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.07798","title":"Thin Evidence, Thick Priors: How Language Models Substitute Identity for Missing Financial Facts","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}