{"total":90,"rows":[{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611,"area":"lr"},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113,"area":"agents"},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2311.07466","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","created":"2023-11-13","cited_by_count":73,"area":"lr"},{"id":"2506.04133","title":"TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems","created":"2025-06-04","cited_by_count":59,"area":"agents"},{"id":"2402.17385","title":"Determinants of LLM-assisted Decision-Making","created":"2024-02-27","cited_by_count":56,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2403.18344","title":"LC-LLM: Explainable Lane-Change Intention and Trajectory Predictions with Large Language Models","created":"2024-03-27","cited_by_count":35,"area":null},{"id":"2404.02937","title":"Towards Explainable Traffic Flow Prediction with Large Language Models","created":"2024-04-03","cited_by_count":20,"area":null},{"id":"2502.17898","title":"VeriPlan: Integrating Formal Verification and LLMs into End-User Planning","created":"2025-02-25","cited_by_count":20,"area":null},{"id":"2402.04678","title":"FaithLM: Towards Faithful Explanations for Large Language Models","created":"2024-02-07","cited_by_count":19,"area":null},{"id":"2403.12388","title":"Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models","created":"2024-03-19","cited_by_count":19,"area":null},{"id":"2503.02239","title":"V2X-LLM: Enhancing V2X Integration and Understanding in Connected Vehicle Corridors","created":"2025-03-04","cited_by_count":13,"area":null},{"id":"2404.13752","title":"Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models","created":"2024-04-21","cited_by_count":12,"area":"mechinterp"},{"id":"2407.00219","title":"Evaluating Human Alignment and Model Faithfulness of LLM Rationale","created":"2024-06-28","cited_by_count":12,"area":null},{"id":"2403.14459","title":"Multi-Level Explanations for Generative Language Models","created":"2024-03-21","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":"2409.06741","title":"Generative AI for Requirements Engineering: A Systematic Literature Review","created":"2024-09-10","cited_by_count":11,"area":null},{"id":"2406.02524","title":"CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks","created":"2024-06-04","cited_by_count":10,"area":null},{"id":"2407.11004","title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators","created":"2024-06-25","cited_by_count":10,"area":null},{"id":"2505.09056","title":"A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias","created":"2025-05-14","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":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"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":"2406.02018","title":"Why Would You Suggest That? Human Trust in Language Model Responses","created":"2024-06-04","cited_by_count":9,"area":null},{"id":"2410.13826","title":"Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2412.13942","title":"A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2502.11919","title":"From Text to Trust: Empowering AI-assisted Decision Making with Adaptive LLM-powered Analysis","created":"2025-02-17","cited_by_count":9,"area":null},{"id":"2402.12038","title":"Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations","created":"2024-02-19","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2411.02018","title":"Shortcut Learning in In-Context Learning: A Survey","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2505.21740","title":"Counterfactual Simulatability of LLM Explanations for Generation Tasks","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2510.15987","title":"AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2312.05468","title":"Image and Data Mining in Reticular Chemistry Using GPT-4V","created":"2023-12-09","cited_by_count":6,"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":"2409.11589","title":"ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering","created":"2024-09-17","cited_by_count":5,"area":null},{"id":"2503.11248","title":"Reasoning-Grounded Natural Language Explanations for Language Models","created":"2025-03-14","cited_by_count":5,"area":"lr"},{"id":"2504.01911","title":"Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning","created":"2025-04-02","cited_by_count":5,"area":"lr"},{"id":"2504.13700","title":"Exploring Multimodal Prompt for Visualization Authoring with Large Language Models","created":"2025-04-18","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":"2407.01384","title":"Free-text Rationale Generation under Readability Level Control","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2409.10504","title":"DILA: Dictionary Label Attention for Mechanistic Interpretability in High-dimensional Multi-label Medical Coding Prediction","created":"2024-09-16","cited_by_count":4,"area":"mechinterp"},{"id":"2504.20020","title":"Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2505.15793","title":"HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving","created":"2025-05-21","cited_by_count":4,"area":"driving"},{"id":"2505.22848","title":"LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2402.14293","title":"Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2408.02584","title":"Leveraging the Power of LLMs: A Fine-Tuning Approach for High-Quality Aspect-Based Summarization","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2410.18357","title":"The Impact of Generative Artificial Intelligence on Ideation and the performance of Innovation Teams (Preprint)","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2502.06316","title":"Can AI Examine Novelty of Patents?: Novelty Evaluation Based on the Correspondence between Patent Claim and Prior Art","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2505.21342","title":"PEDANTIC: A Dataset for the Automatic Examination of Definiteness in Patent Claims","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2512.00163","title":"Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification","created":"2025-11-28","cited_by_count":3,"area":"lr"},{"id":"2604.19775","title":"From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents","created":"2026-03-27","cited_by_count":3,"area":"agents"},{"id":"2408.08217","title":"RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Classifiers for Computational Social Science","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2412.00281","title":"Streamlining the review process: AI-generated annotations in research manuscripts","created":"2024-11-29","cited_by_count":2,"area":null},{"id":"2502.05242","title":"Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2605.31514","title":"If LLMs Have Human-Like Attributes, Then So Does Age of Empires II","created":"2026-05-29","cited_by_count":2,"area":"agents"},{"id":"2406.03843","title":"POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Models","created":"2024-06-06","cited_by_count":1,"area":"lr"},{"id":"2410.03296","title":"A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2410.21353","title":"Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics","created":"2024-10-28","cited_by_count":1,"area":"lr"},{"id":"2503.19607","title":"Enabling Rapid Shared Human-AI Mental Model Alignment via the After-Action Review","created":"2025-03-25","cited_by_count":1,"area":"alignment"},{"id":"2506.08427","title":"Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2509.22363","title":"Investigating Faithfulness in Large Audio Language Models","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2511.21742","title":"EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational Assistants","created":"2025-11-21","cited_by_count":1,"area":"agents"},{"id":"2602.14536","title":"Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2606.01148","title":"Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales","created":"2026-05-31","cited_by_count":1,"area":"synth"},{"id":"2406.16985","title":"Unveiling LLM Mechanisms Through Neural ODEs and Control Theory","created":"2024-06-23","cited_by_count":0,"area":null},{"id":"2408.04689","title":"Design of a Quality Management System based on the EU Artificial Intelligence Act","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2408.11863","title":"Unraveling Text Generation in LLMs: A Stochastic Differential Equation Approach","created":"2024-08-17","cited_by_count":0,"area":null},{"id":"2410.12195","title":"Sparse Prototype Network for Explainable Pedestrian Behavior Prediction","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2411.03131","title":"Machine Learning Innovations in CPR: A Comprehensive Survey on Enhanced Resuscitation Techniques","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2506.09277","title":"NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2509.21241","title":"Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2511.19719","title":"Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.07288","title":"Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.12869","title":"ERA-IT: Aligning Semantic Models with Revealed Economic Preference for Real-Time and Explainable Patent Valuation","created":"2025-12-14","cited_by_count":0,"area":"alignment"},{"id":"2512.22508","title":"Predicting LLM Correctness in Prosthodontics Using Metadata and Hallucination Signals","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.14002","title":"The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2603.22735","title":"Explanation Generation for Contradiction Reconciliation with LLMs","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.14325","title":"Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.14641","title":"Learning to Draw ASCII Improves Spatial Reasoning in Language Models","created":"2026-04-16","cited_by_count":0,"area":"lr"},{"id":"2605.12139","title":"BoolXLLM: LLM-Assisted Explainability for Boolean Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.24727","title":"Fundamental Limitation in Explaining AI","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.28615","title":"What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.15957","title":"From Plausible to Actionable: A Position on LLM Self-Explanations","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.26062","title":"Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.00334","title":"Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspective","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.22008","title":"DiaVLo: Diagnosing Behaviours of Vision-Language Models","created":"2026-09-18","cited_by_count":0,"area":"mllm"},{"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"}],"next_cursor":null}