{"total":12,"rows":[{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691,"area":null},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2303.09435","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","created":"2023-03-16","cited_by_count":90,"area":null},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88,"area":null},{"id":"2510.13290","title":"To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2206.03529","title":"How to Dissect a Muppet: The Structure of Transformer Embedding Spaces","created":"2022-06-07","cited_by_count":20,"area":null},{"id":"2310.06977","title":"Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2510.20800","title":"Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2109.13304","title":"On Isotropy Calibration of Transformers","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2303.13072","title":"Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition","created":"2023-03-23","cited_by_count":0,"area":null},{"id":"2406.15940","title":"Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models","created":"2024-06-22","cited_by_count":0,"area":null}],"next_cursor":null}