{"total":62,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"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":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113,"area":"mechinterp"},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91,"area":null},{"id":"2404.14394","title":"A Multimodal Automated Interpretability Agent","created":"2024-04-22","cited_by_count":63,"area":"agents"},{"id":"2305.13749","title":"Goal-Driven Explainable Clustering via Language Descriptions","created":"2023-05-23","cited_by_count":58,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2306.00024","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","created":"2023-05-30","cited_by_count":52,"area":"lr"},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2309.03886","title":"FIND: A Function Description Benchmark for Evaluating Interpretability Methods","created":"2023-09-07","cited_by_count":32,"area":null},{"id":"2407.15248","title":"XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models","created":"2024-07-21","cited_by_count":23,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2406.03198","title":"The Impossibility of Fair LLMs","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2307.10246","title":"Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)","created":"2023-07-17","cited_by_count":21,"area":null},{"id":"2409.08466","title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters","created":"2024-09-13","cited_by_count":21,"area":null},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21,"area":null},{"id":"2403.12451","title":"End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations","created":"2024-03-19","cited_by_count":17,"area":"deeprl"},{"id":"2410.15555","title":"Bayesian Concept Bottleneck Models with LLM Priors","created":"2024-10-21","cited_by_count":17,"area":null},{"id":"2502.05078","title":"Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures","created":"2025-02-07","cited_by_count":16,"area":"lr"},{"id":"2311.04929","title":"An Interdisciplinary Outlook on Large Language Models for Scientific Research","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13,"area":null},{"id":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2404.18533","title":"Evaluating Readability and Faithfulness of Concept-based Explanations","created":"2024-04-29","cited_by_count":10,"area":null},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2509.13316","title":"Do Activation Verbalization Methods Convey Privileged Information?","created":"2025-09-16","cited_by_count":10,"area":"mechinterp"},{"id":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2409.19069","title":"Localizing Memorization in SSL Vision Encoders","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2410.22239","title":"DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2504.13938","title":"Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection","created":"2025-04-15","cited_by_count":8,"area":null},{"id":"2505.16477","title":"Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2312.06718","title":"Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2406.08572","title":"LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2410.00812","title":"Generative causal testing to bridge data-driven models and scientific theories in language neuroscience","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2403.13368","title":"Computational Models to Study Language Processing in the Human Brain: A Survey","created":"2024-03-20","cited_by_count":4,"area":null},{"id":"2502.13606","title":"LaVCa: LLM-assisted Visual Cortex Captioning","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2506.05774","title":"Evaluating Neuron Explanations: A Unified Framework with Sanity Checks","created":"2025-06-06","cited_by_count":4,"area":"mechinterp"},{"id":"2509.23717","title":"Measuring Sparse Autoencoder Feature Sensitivity","created":"2025-09-28","cited_by_count":4,"area":"mechinterp"},{"id":"2405.00489","title":"Explainable Automatic Grading with Neural Additive Models","created":"2024-05-01","cited_by_count":3,"area":null},{"id":"2410.19542","title":"Brain-like Functional Organization within Large Language Models","created":"2024-10-25","cited_by_count":3,"area":null},{"id":"2411.00066","title":"Interpretable Next-token Prediction via the Generalized Induction Head","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2502.17541","title":"Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2504.07831","title":"Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems","created":"2025-04-10","cited_by_count":3,"area":"mechinterp"},{"id":"2510.01048","title":"Interpreting Language Models Through Concept Descriptions: A Survey","created":"2025-10-01","cited_by_count":3,"area":"mechinterp"},{"id":"2602.22719","title":"Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks","created":"2026-02-26","cited_by_count":3,"area":"ssm"},{"id":"2406.17241","title":"Understanding Language Model Circuits through Knowledge Editing","created":"2024-06-25","cited_by_count":2,"area":null},{"id":"2505.12507","title":"Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.23818","title":"Ratas framework: A comprehensive genai-based approach to rubric-based marking of real-world textual exams","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2605.03808","title":"Agentic-imodels: Evolving agentic interpretability tools via autoresearch","created":"2026-05-05","cited_by_count":1,"area":"agents"},{"id":"2606.07007","title":"A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders","created":"2026-06-05","cited_by_count":1,"area":"mechinterp"},{"id":"2507.02241","title":"VERBA: Verbalizing Model Differences Using Large Language Models","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2512.01514","title":"Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2605.16468","title":"Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.13425","title":"Data-Efficient Adaptation of LLMs via Attention Head Reweighting","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.02238","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.03388","title":"Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2609.16372","title":"Register Tokens for Bounded-State Reasoning in Diffusion Language Models","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.23215","title":"Triggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2610.02829","title":"Clinical Concept Centers in LLMs","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}