{"total":32,"rows":[{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431,"area":null},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267,"area":null},{"id":"2109.06129","title":"Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color","created":"2021-09-13","cited_by_count":119,"area":null},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2302.14367","title":"BrainBERT: Self-supervised representation learning for intracranial recordings","created":"2023-02-28","cited_by_count":72,"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":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48,"area":null},{"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":"2310.13620","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","created":"2023-10-20","cited_by_count":26,"area":null},{"id":"2506.00085","title":"COSMIC: Generalized Refusal Direction Identification in LLM Activations","created":"2025-05-30","cited_by_count":19,"area":null},{"id":"2310.04861","title":"Uncovering hidden geometry in Transformers via disentangling position and context","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2410.08113","title":"Robust AI-Generated Text Detection by Restricted Embeddings","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2410.01444","title":"Geometric Signatures of Compositionality Across a Language Model's Lifetime","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2310.17715","title":"Outlier Dimensions Encode Task-Specific Knowledge","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2406.09200","title":"Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations","created":"2024-06-13","cited_by_count":14,"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":"2509.13281","title":"RepIt: Steering Language Models with Concept-Specific Refusal Vectors","created":"2025-09-16","cited_by_count":12,"area":null},{"id":"2109.11491","title":"Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords","created":"2021-09-23","cited_by_count":9,"area":null},{"id":"2301.04528","title":"The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2406.17513","title":"Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models","created":"2024-06-25","cited_by_count":8,"area":null},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2502.12055","title":"Designing Role Vectors to Improve LLM Inference Behaviour","created":"2025-02-17","cited_by_count":6,"area":null},{"id":"2408.09794","title":"AutoML-guided Fusion of Entity and LLM-based Representations for Document Classification","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2506.10855","title":"Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2605.01381","title":"A framework for analyzing concept representations in neural models","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2204.12024","title":"Reprint: a randomized extrapolation based on principal components for data augmentation","created":"2022-04-26","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":"2505.07783","title":"Relative Overfitting and Accept-Reject Framework","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2601.19926","title":"The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2606.07631","title":"Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2610.16273","title":"Deep Speech Representations Track Word Timing along a Low-Dimensional Circular Trajectory","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}