{"total":125,"rows":[{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"area":null},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"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":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70,"area":null},{"id":"2208.07852","title":"Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models","created":"2022-08-16","cited_by_count":70,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2207.04154","title":"TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations","created":"2022-07-08","cited_by_count":66,"area":null},{"id":"2101.05303","title":"Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making","created":"2021-01-13","cited_by_count":58,"area":null},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53,"area":null},{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50,"area":null},{"id":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50,"area":null},{"id":"2212.08109","title":"An Empirical Study of Deep Learning Models for Vulnerability Detection","created":"2022-12-15","cited_by_count":46,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2104.01477","title":"Exploring the Role of BERT Token Representations to Explain Sentence Probing Results","created":"2021-04-03","cited_by_count":29,"area":null},{"id":"2111.05498","title":"Attention Approximates Sparse Distributed Memory","created":"2021-11-10","cited_by_count":29,"area":null},{"id":"2402.10524","title":"LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models","created":"2024-02-16","cited_by_count":29,"area":null},{"id":"2103.14625","title":"Dodrio: Exploring Transformer Models with Interactive Visualization","created":"2021-03-26","cited_by_count":28,"area":null},{"id":"2204.12130","title":"LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models","created":"2022-04-26","cited_by_count":28,"area":null},{"id":"2402.15350","title":"Farsight: Fostering Responsible AI Awareness During AI Application Prototyping","created":"2024-02-23","cited_by_count":28,"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":"2311.16842","title":"RELIC: Investigating Large Language Model Responses using Self-Consistency","created":"2023-11-28","cited_by_count":23,"area":"lr"},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18,"area":null},{"id":"2206.09355","title":"A Unified Understanding of Deep NLP Models for Text Classification","created":"2022-06-19","cited_by_count":18,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2111.01582","title":"LMdiff: A Visual Diff Tool to Compare Language Models","created":"2021-11-02","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":"2404.07004","title":"LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models","created":"2024-04-10","cited_by_count":16,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2104.07605","title":"SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization","created":"2021-04-15","cited_by_count":13,"area":null},{"id":"2108.13587","title":"T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP","created":"2021-08-31","cited_by_count":11,"area":null},{"id":"2108.13961","title":"Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools","created":"2021-08-31","cited_by_count":11,"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":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","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":"2303.00732","title":"R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents","created":"2023-03-01","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":"2108.05525","title":"Clustering with UMAP: Why and How Connectivity Matters","created":"2021-08-12","cited_by_count":9,"area":null},{"id":"2207.06897","title":"Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language","created":"2022-07-14","cited_by_count":9,"area":null},{"id":"2301.04528","title":"The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2305.00034","title":"Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation","created":"2023-04-28","cited_by_count":9,"area":null},{"id":"2403.08904","title":"Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics","created":"2024-03-13","cited_by_count":9,"area":"rag"},{"id":"2104.05807","title":"Does My Representation Capture X? Probe-Ably","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2302.07371","title":"BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models","created":"2023-02-14","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":"2402.03715","title":"Clarify: Improving Model Robustness With Natural Language Corrections","created":"2024-02-06","cited_by_count":8,"area":null},{"id":"2405.00708","title":"Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis","created":"2024-04-23","cited_by_count":8,"area":null},{"id":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2202.08176","title":"Bias and unfairness in machine learning models: a systematic literature review","created":"2022-02-16","cited_by_count":7,"area":null},{"id":"2206.06029","title":"Mediators: Conversational Agents Explaining NLP Model Behavior","created":"2022-06-13","cited_by_count":7,"area":null},{"id":"2303.05392","title":"Automatically Summarizing Evidence from Clinical Trials: A Prototype Highlighting Current Challenges","created":"2023-03-07","cited_by_count":7,"area":null},{"id":"2403.04758","title":"KnowledgeVIS: Interpreting Language Models by Comparing Fill-in-the-Blank Prompts","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2202.11086","title":"StickyLand: Breaking the Linear Presentation of Computational Notebooks","created":"2022-02-22","cited_by_count":6,"area":null},{"id":"2208.08010","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2211.06642","title":"ConceptX: A Framework for Latent Concept Analysis","created":"2022-11-12","cited_by_count":6,"area":null},{"id":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2403.04760","title":"iScore: Visual Analytics for Interpreting How Language Models Automatically Score Summaries","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2404.07498","title":"Interactive Prompt Debugging with Sequence Salience","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2410.01088","title":"Exploring Empty Spaces: Human-in-the-Loop Data Augmentation","created":"2024-10-01","cited_by_count":6,"area":"safety"},{"id":"2412.16089","title":"The Evolution of LLM Adoption in Industry Data Curation Practices","created":"2024-12-20","cited_by_count":6,"area":null},{"id":"2305.16937","title":"Finspector: A Human-Centered Visual Inspection Tool for Exploring and Comparing Biases among Foundation Models","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2309.13965","title":"May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability","created":"2023-09-25","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":"2408.00211","title":"Penzai + Treescope: A Toolkit for Interpreting, Visualizing, and Editing Models As Data","created":"2024-08-01","cited_by_count":5,"area":null},{"id":"2106.06247","title":"FedNLP: An interpretable NLP System to Decode Federal Reserve Communications","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2108.01879","title":"Summary Explorer: Visualizing the State of the Art in Text Summarization","created":"2021-08-04","cited_by_count":4,"area":null},{"id":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2211.17046","title":"Rationale-Guided Few-Shot Classification to Detect Abusive Language","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2212.08216","title":"Azimuth: Systematic Error Analysis for Text Classification","created":"2022-12-16","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":"2305.11364","title":"Visualizing Linguistic Diversity of Text Datasets Synthesized by Large Language Models","created":"2023-05-19","cited_by_count":4,"area":null},{"id":"2309.11987","title":"Predictability and Comprehensibility in Post-Hoc XAI Methods: A User-Centered Analysis","created":"2023-09-21","cited_by_count":4,"area":null},{"id":"2601.12913","title":"Actionable Interpretability Must Be Defined in Terms of Symmetries","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2107.05693","title":"Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2203.04408","title":"iSEA: An Interactive Pipeline for Semantic Error Analysis of NLP Models","created":"2022-03-08","cited_by_count":3,"area":null},{"id":"2305.03039","title":"SuperNOVA: Design Strategies and Opportunities for Interactive Visualization in Computational Notebooks","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2405.11880","title":"Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs","created":"2024-05-20","cited_by_count":3,"area":"lr"},{"id":"2104.03364","title":"EXPATS: A Toolkit for Explainable Automated Text Scoring","created":"2021-04-07","cited_by_count":2,"area":null},{"id":"2112.12444","title":"More Than Words: Towards Better Quality Interpretations of Text Classifiers","created":"2021-12-23","cited_by_count":2,"area":null},{"id":"2207.06591","title":"A methodology to characterize bias and harmful stereotypes in natural language processing in Latin America","created":"2022-07-14","cited_by_count":2,"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":"2303.09545","title":"WebSHAP: Towards Explaining Any Machine Learning Models Anywhere","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2307.12382","title":"CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models","created":"2023-07-23","cited_by_count":2,"area":"lr"},{"id":"2311.12418","title":"Visual Analytics for Generative Transformer Models","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2402.16611","title":"Understanding the Dataset Practitioners Behind Large Language Model Development","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2409.18764","title":"Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations","created":"2024-09-27","cited_by_count":2,"area":"synth"},{"id":"2412.15748","title":"Critique of Impure Reason: Unveiling the reasoning behaviour of medical Large Language Models","created":"2024-12-20","cited_by_count":2,"area":"lr"},{"id":"2502.03418","title":"Which Words Matter Most in Zero-Shot Prompts?","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2505.08064","title":"Justified Evidence Collection for Argument-based AI Fairness Assurance","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2104.12717","title":"TrustyAI Explainability Toolkit","created":"2021-04-26","cited_by_count":1,"area":null},{"id":"2201.06444","title":"Black-box Error Diagnosis in Deep Neural Networks for Computer Vision: a Survey of Tools","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2303.03019","title":"NxPlain: Web-based Tool for Discovery of Latent Concepts","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2402.03137","title":"Sociolinguistically Informed Interpretability: A Case Study on Hinglish Emotion Classification","created":"2024-02-05","cited_by_count":1,"area":null}],"next_cursor":"100"}