{"total":74,"rows":[{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236,"area":"diffusion"},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218,"area":"mechinterp"},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"area":"moe"},{"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":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"area":null},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50,"area":null},{"id":"2204.11073","title":"Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps","created":"2022-04-23","cited_by_count":42,"area":null},{"id":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2307.13339","title":"Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions","created":"2023-07-25","cited_by_count":32,"area":"lr"},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"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":"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":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"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":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","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":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17,"area":null},{"id":"2111.01582","title":"LMdiff: A Visual Diff Tool to Compare Language Models","created":"2021-11-02","cited_by_count":17,"area":null},{"id":"2305.16503","title":"IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks","created":"2023-05-25","cited_by_count":15,"area":"safety"},{"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":"2103.00676","title":"Token-Modification Adversarial Attacks for Natural Language Processing: A Survey","created":"2021-03-01","cited_by_count":12,"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":"2205.08696","title":"The Solvability of Interpretability Evaluation Metrics","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2209.07442","title":"Automatic Error Analysis for Document-level Information Extraction","created":"2022-09-15","cited_by_count":10,"area":null},{"id":"2311.18812","title":"What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations","created":"2023-11-30","cited_by_count":10,"area":"lr"},{"id":"2208.06612","title":"Interpreting BERT-based Text Similarity via Activation and Saliency Maps","created":"2022-08-13","cited_by_count":9,"area":null},{"id":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2104.05807","title":"Does My Representation Capture X? Probe-Ably","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2104.08763","title":"Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training","created":"2021-04-18","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":"2401.09972","title":"Better Explain Transformers by Illuminating Important Information","created":"2024-01-18","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":"2310.16607","title":"On the Interplay between Fairness and Explainability","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2412.00800","title":"A Comprehensive Guide to Explainable AI: From Classical Models to LLMs","created":"2024-12-01","cited_by_count":7,"area":null},{"id":"2501.04802","title":"Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrieval","created":"2025-01-08","cited_by_count":7,"area":null},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2102.00238","title":"ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models","created":"2021-01-30","cited_by_count":5,"area":null},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2209.09975","title":"Power of Explanations: Towards automatic debiasing in hate speech detection","created":"2022-09-07","cited_by_count":5,"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":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2410.13792","title":"Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2205.10238","title":"Visualizing and Explaining Language Models","created":"2022-04-30","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":"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":"2306.11386","title":"Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2310.02964","title":"Co-modeling the Sequential and Graphical Routes for Peptide Representation Learning","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2104.11761","title":"Towards Trustworthy Deception Detection: Benchmarking Model Robustness across Domains, Modalities, and Languages","created":"2021-04-23","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":"2208.09316","title":"UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA","created":"2022-08-19","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":"2302.10479","title":"Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2305.13235","title":"SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2311.12418","title":"Visual Analytics for Generative Transformer Models","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2502.03418","title":"Which Words Matter Most in Zero-Shot Prompts?","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2510.26200","title":"Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation","created":"2025-10-30","cited_by_count":2,"area":"diffusion"},{"id":"2211.07713","title":"How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2307.08327","title":"Analyzing the Impact of Adversarial Examples on Explainable Machine Learning","created":"2023-07-17","cited_by_count":1,"area":null},{"id":"2308.02193","title":"Explaining Relation Classification Models with Semantic Extents","created":"2023-08-04","cited_by_count":1,"area":null},{"id":"2312.16291","title":"Observable Propagation: Uncovering Feature Vectors in Transformers","created":"2023-12-26","cited_by_count":1,"area":"mechinterp"},{"id":"2209.09814","title":"PainPoints: A Framework for Language-based Detection of Chronic Pain and Expert-Collaborative Text-Summarization","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2307.13128","title":"Explaining Math Word Problem Solvers","created":"2023-07-24","cited_by_count":0,"area":null},{"id":"2309.03238","title":"Implicit Design Choices and Their Impact on Emotion Recognition Model Development and Evaluation","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2402.19133","title":"Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2407.18467","title":"Machine Unlearning using a Multi-GAN based Model","created":"2024-07-26","cited_by_count":0,"area":"safety"},{"id":"2510.09882","title":"iBERT: Interpretable Embeddings via Sense Decomposition","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2606.22886","title":"Explanation-Guided Medical Named Entity Recognition with Stability and Boundary Awareness for Atopic Dermatitis","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.24524","title":"LumiXAI: A Modular Full-Stack Framework for Feature Attribution","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}