{"total":156,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235,"area":"mechinterp"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2202.08816","title":"Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning","created":"2022-02-17","cited_by_count":79,"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":"2301.07255","title":"Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations","created":"2023-01-18","cited_by_count":73,"area":null},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65,"area":null},{"id":"2205.02894","title":"Interactive Model Cards: A Human-Centered Approach to Model Documentation","created":"2022-05-05","cited_by_count":61,"area":null},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2409.01659","title":"Interpreting and Improving Large Language Models in Arithmetic Calculation","created":"2024-09-03","cited_by_count":45,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2403.14680","title":"Trust in AI: Progress, Challenges, and Future Directions","created":"2024-03-12","cited_by_count":35,"area":null},{"id":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35,"area":null},{"id":"2311.05014","title":"Interpreting Pretrained Language Models via Concept Bottlenecks","created":"2023-11-08","cited_by_count":33,"area":null},{"id":"2403.05846","title":"Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines","created":"2024-03-09","cited_by_count":30,"area":"diffusion"},{"id":"2407.14962","title":"Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives","created":"2024-07-20","cited_by_count":30,"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":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25,"area":null},{"id":"2205.14108","title":"Scalable Interpretability via Polynomials","created":"2022-05-27","cited_by_count":25,"area":null},{"id":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25,"area":"rag"},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2301.08912","title":"Rationalization for Explainable NLP: A Survey","created":"2023-01-21","cited_by_count":22,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2311.11258","title":"Tensor networks for interpretable and efficient quantum-inspired machine learning","created":"2023-11-19","cited_by_count":17,"area":null},{"id":"2401.12576","title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","created":"2024-01-23","cited_by_count":16,"area":null},{"id":"2302.14220","title":"Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation","created":"2023-02-28","cited_by_count":15,"area":null},{"id":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2410.11627","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","created":"2024-10-15","cited_by_count":14,"area":null},{"id":"2210.07222","title":"Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2310.11884","title":"From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2305.18011","title":"Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2412.00631","title":"ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning","created":"2024-12-01","cited_by_count":10,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2310.17903","title":"Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey","created":"2023-10-27","cited_by_count":9,"area":null},{"id":"2310.18696","title":"Probing LLMs for Joint Encoding of Linguistic Categories","created":"2023-10-28","cited_by_count":9,"area":null},{"id":"2311.05085","title":"Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2409.07123","title":"Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem","created":"2024-09-11","cited_by_count":9,"area":"lr"},{"id":"2302.14062","title":"Explanations for Automatic Speech Recognition","created":"2023-02-27","cited_by_count":8,"area":null},{"id":"2303.03124","title":"IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models","created":"2023-03-06","cited_by_count":8,"area":null},{"id":"2206.06029","title":"Mediators: Conversational Agents Explaining NLP Model Behavior","created":"2022-06-13","cited_by_count":7,"area":null},{"id":"2310.01188","title":"Quantifying the Plausibility of Context Reliance in Neural Machine Translation","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2403.07279","title":"A Survey of Explainable Knowledge Tracing","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2403.20322","title":"Towards a Framework for Evaluating Explanations in Automated Fact Verification","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2502.04695","title":"Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2502.11100","title":"Towards Achieving Concept Completeness for Textual Concept Bottleneck Models","created":"2025-02-16","cited_by_count":7,"area":null},{"id":"2504.08001","title":"Linguistic Interpretability of Transformer-based Language Models: a systematic review","created":"2025-04-09","cited_by_count":7,"area":"mechinterp"},{"id":"2203.13693","title":"UKP-SQUARE: An Online Platform for Question Answering Research","created":"2022-03-25","cited_by_count":6,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2210.08430","title":"Explainable Causal Analysis of Mental Health on Social Media Data","created":"2022-10-16","cited_by_count":6,"area":null},{"id":"2305.17055","title":"Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2310.15372","title":"EpiK-Eval: Evaluation for Language Models as Epistemic Models","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2411.01710","title":"SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation","created":"2024-11-03","cited_by_count":6,"area":null},{"id":"2501.00777","title":"FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation","created":"2025-01-01","cited_by_count":6,"area":null},{"id":"2310.07819","title":"Faithfulness Measurable Masked Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2311.08614","title":"XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs","created":"2023-11-15","cited_by_count":5,"area":"lr"},{"id":"2401.16458","title":"Credit Risk Meets Large Language Models: Building a Risk Indicator from Loan Descriptions in P2P Lending","created":"2024-01-29","cited_by_count":5,"area":null},{"id":"2404.01361","title":"LLM Attributor: Interactive Visual Attribution for LLM Generation","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2406.17931","title":"CAT: Interpretable Concept-based Taylor Additive Models","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2407.20990","title":"From Feature Importance to Natural Language Explanations Using LLMs with RAG","created":"2024-07-30","cited_by_count":5,"area":null},{"id":"2411.02461","title":"Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2505.06032","title":"Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification","created":"2025-05-09","cited_by_count":5,"area":null},{"id":"2505.13972","title":"Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2508.08274","title":"Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2601.00282","title":"Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations","created":"2026-01-01","cited_by_count":5,"area":null},{"id":"2207.13018","title":"Is Attention Interpretation? A Quantitative Assessment On Sets","created":"2022-07-26","cited_by_count":4,"area":null},{"id":"2305.02679","title":"Neighboring Words Affect Human Interpretation of Saliency Explanations","created":"2023-05-04","cited_by_count":4,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2310.05619","title":"Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2402.03043","title":"SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approach","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2405.05348","title":"The Effect of Model Size on LLM Post-hoc Explainability via LIME","created":"2024-05-08","cited_by_count":4,"area":null},{"id":"2410.19920","title":"Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting","created":"2024-10-25","cited_by_count":4,"area":"agents"},{"id":"2412.11187","title":"Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models","created":"2024-12-15","cited_by_count":4,"area":null},{"id":"2505.21657","title":"Explaining Large Language Models with gSMILE","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2604.16042","title":"Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures","created":"2026-04-17","cited_by_count":4,"area":"mechinterp"},{"id":"2206.05148","title":"Weakly-supervised segmentation using inherently-explainable classification models and their application to brain tumour classification","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2208.10228","title":"Review of Natural Language Processing in Pharmacology","created":"2022-08-22","cited_by_count":3,"area":null},{"id":"2210.13236","title":"Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2306.00976","title":"TopEx: Topic-based Explanations for Model Comparison","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2311.08240","title":"Investigating the Encoding of Words in BERT's Neurons using Feature Textualization","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2403.19424","title":"The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2503.02078","title":"Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation","created":"2025-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2504.12151","title":"Towards Explainable Fusion and Balanced Learning in Multimodal Sentiment Analysis","created":"2025-04-16","cited_by_count":3,"area":null},{"id":"2505.01198","title":"Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods","created":"2025-05-02","cited_by_count":3,"area":null}],"next_cursor":"100"}