{"total":24,"rows":[{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528,"area":null},{"id":"2301.09785","title":"Transformer-Patcher: One Mistake worth One Neuron","created":"2023-01-24","cited_by_count":197,"area":null},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"area":null},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132,"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":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125,"area":null},{"id":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124,"area":null},{"id":"2311.04897","title":"Future Lens: Anticipating Subsequent Tokens from a Single Hidden State","created":"2023-11-08","cited_by_count":121,"area":null},{"id":"2308.01544","title":"Multimodal Neurons in Pretrained Text-Only Transformers","created":"2023-08-03","cited_by_count":49,"area":null},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"area":null},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2310.03084","title":"Discovering Knowledge-Critical Subnetworks in Pretrained Language Models","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2302.12480","title":"Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?","created":"2023-02-24","cited_by_count":13,"area":null},{"id":"2211.11052","title":"Convexifying Transformers: Improving optimization and understanding of transformer networks","created":"2022-11-20","cited_by_count":12,"area":null},{"id":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2409.00844","title":"Report Cards: Qualitative Evaluation of Language Models Using Natural Language Summaries","created":"2024-09-01","cited_by_count":6,"area":null},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2211.05485","title":"Understanding Text Classification Data and Models Using Aggregated Input Salience","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2303.13850","title":"Towards Learning and Explaining Indirect Causal Effects in Neural Networks","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2311.12418","title":"Visual Analytics for Generative Transformer Models","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2505.17260","title":"The Rise of Parameter Specialization for Knowledge Storage in Large Language Models","created":"2025-05-22","cited_by_count":1,"area":null}],"next_cursor":null}