{"total":42,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"area":null},{"id":"2308.13198","title":"Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons","created":"2023-08-25","cited_by_count":56,"area":null},{"id":"2305.15853","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","created":"2023-05-25","cited_by_count":52,"area":null},{"id":"2206.07023","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2402.12865","title":"Backward Lens: Projecting Language Model Gradients into the Vocabulary Space","created":"2024-02-20","cited_by_count":32,"area":null},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2411.15102","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","created":"2024-11-22","cited_by_count":23,"area":null},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2405.14117","title":"Knowledge Localization: Mission Not Accomplished? Enter Query Localization!","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2408.03915","title":"Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation","created":"2024-08-07","cited_by_count":11,"area":null},{"id":"2207.00779","title":"FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales","created":"2022-07-02","cited_by_count":10,"area":null},{"id":"2310.05703","title":"An Attribution Method for Siamese Encoders","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2309.07733","title":"Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2305.10614","title":"Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions","created":"2023-05-17","cited_by_count":6,"area":null},{"id":"2306.02968","title":"Time Interpret: a Unified Model Interpretability Library for Time Series","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2601.16407","title":"Jacobian Scopes: token-level causal attributions in LLMs","created":"2026-01-23","cited_by_count":4,"area":null},{"id":"2208.06096","title":"Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights","created":"2022-08-12","cited_by_count":3,"area":null},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2411.17401","title":"One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2312.10770","title":"Identification of Knowledge Neurons in Protein Language Models","created":"2023-12-17","cited_by_count":2,"area":null},{"id":"2403.18976","title":"\"Sorry, Come Again?\" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2412.03886","title":"Uniform Discretized Integrated Gradients: An effective attribution based method for explaining large language models","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2604.13258","title":"Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2208.03578","title":"Generalizability Analysis of Graph-based Trajectory Predictor with Vectorized Representation","created":"2022-08-06","cited_by_count":1,"area":null},{"id":"2404.13910","title":"Integrated Gradient Correlation: a Dataset-wise Attribution Method","created":"2024-04-22","cited_by_count":1,"area":null},{"id":"2506.01059","title":"XAI-Units: Benchmarking Explainability Methods with Unit Tests","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2312.08157","title":"CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2403.16554","title":"PE: A Poincare Explanation Method for Fast Text Hierarchy Generation","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2410.12511","title":"Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2503.04989","title":"Application of integrated gradients explainability to sociopsychological semantic markers","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2509.07648","title":"Graph-based Integrated Gradients for Explaining Graph Neural Networks","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2510.02629","title":"Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.07477","title":"HEMERA: A Human-Explainable Transformer Model for Estimating Lung Cancer Risk using GWAS Data","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2606.08497","title":"Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.21564","title":"LIG: Layer-wise Integrated Gradients for Within-Layer Flow Analysis in Transformers","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2609.37594","title":"XU-RS: Explaining Credal Width in Random-Set Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00713","title":"WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testing","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.19270","title":"Exploring Interpretability in Deep Learning-Based Forest Classification - Separating Similar Forest Classes using Sentinel-2 Time Series","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}