{"total":15,"rows":[{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2106.02596","title":"Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model","created":"2021-06-04","cited_by_count":23,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2210.12170","title":"Discovering Differences in the Representation of People using Contextualized Semantic Axes","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2301.04704","title":"SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2401.06112","title":"Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings","created":"2024-01-11","cited_by_count":6,"area":null},{"id":"2202.11748","title":"The Need for Interpretable Features: Motivation and Taxonomy","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2411.16527","title":"Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings","created":"2024-11-25","cited_by_count":3,"area":null},{"id":"2111.01023","title":"Interpretable contrastive word mover's embedding","created":"2021-11-01","cited_by_count":2,"area":null},{"id":"2209.13023","title":"Lex2Sent: A bagging approach to unsupervised sentiment analysis","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2607.27824","title":"STEREODISCO: Discovering Stereotypicality in LLMs","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2212.07126","title":"Explainability of Text Processing and Retrieval Methods: A Survey","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2410.10332","title":"Disentangling Hate Across Target Identities","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2411.00653","title":"Rethinking Node Representation Interpretation through Relation Coherence","created":"2024-11-01","cited_by_count":0,"area":null}],"next_cursor":null}