{"total":97,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223,"area":"lr"},{"id":"2309.17428","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","created":"2023-09-29","cited_by_count":129,"area":null},{"id":"2505.15778","title":"Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space","created":"2025-05-21","cited_by_count":117,"area":"lr"},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2407.00128","title":"When Search Engine Services meet Large Language Models: Visions and Challenges","created":"2024-06-28","cited_by_count":59,"area":null},{"id":"2411.18478","title":"Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS","created":"2024-11-27","cited_by_count":54,"area":"lr"},{"id":"2505.20161","title":"Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2306.10512","title":"Position: AI Evaluation Should Learn from How We Test Humans","created":"2023-06-18","cited_by_count":36,"area":null},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35,"area":null},{"id":"2406.03712","title":"A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions","created":"2024-06-06","cited_by_count":34,"area":null},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2402.06599","title":"On the Out-Of-Distribution Generalization of Multimodal Large Language Models","created":"2024-02-09","cited_by_count":30,"area":"mllm"},{"id":"2502.15871","title":"A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare","created":"2025-02-21","cited_by_count":27,"area":null},{"id":"2405.16747","title":"Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective","created":"2024-05-27","cited_by_count":22,"area":null},{"id":"2403.01874","title":"A Survey on Evaluation of Out-of-Distribution Generalization","created":"2024-03-04","cited_by_count":21,"area":null},{"id":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18,"area":"alignment"},{"id":"2410.19265","title":"A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation","created":"2024-10-25","cited_by_count":17,"area":null},{"id":"2412.02186","title":"VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding","created":"2024-12-03","cited_by_count":17,"area":"lr"},{"id":"2501.17858","title":"Improving Your Model Ranking on Chatbot Arena by Vote Rigging","created":"2025-01-29","cited_by_count":17,"area":null},{"id":"2409.12969","title":"Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models","created":"2024-09-02","cited_by_count":15,"area":"mllm"},{"id":"2504.00509","title":"Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?","created":"2025-04-01","cited_by_count":15,"area":"lr"},{"id":"2501.05382","title":"Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2507.21160","title":"Handling Out-of-Distribution Data: A Survey","created":"2025-07-25","cited_by_count":14,"area":null},{"id":"2311.13258","title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","created":"2023-11-22","cited_by_count":13,"area":"mllm"},{"id":"2402.11417","title":"LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models","created":"2024-02-18","cited_by_count":12,"area":null},{"id":"2407.03036","title":"SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2511.17938","title":"SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization","created":"2025-11-22","cited_by_count":12,"area":"lr"},{"id":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","cited_by_count":11,"area":null},{"id":"2502.16184","title":"Robustness and Cybersecurity in the EU Artificial Intelligence Act","created":"2025-02-22","cited_by_count":11,"area":null},{"id":"2606.25447","title":"The Interplay of Harness Design and Post-Training in LLM Agents","created":"2026-06-24","cited_by_count":10,"area":"agents"},{"id":"2311.09006","title":"Data Similarity is Not Enough to Explain Language Model Performance","created":"2023-11-15","cited_by_count":9,"area":null},{"id":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2601.05106","title":"Token-Level LLM Collaboration via FusionRoute","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2402.08225","title":"Improving Black-box Robustness with In-Context Rewriting","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2504.05262","title":"Do Large Language Models Truly Grasp Addition? A Rule-Focused Diagnostic Using Two-Integer Arithmetic","created":"2025-04-07","cited_by_count":8,"area":null},{"id":"2508.18797","title":"CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks","created":"2025-08-26","cited_by_count":8,"area":"agents"},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2408.01460","title":"LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models","created":"2024-07-27","cited_by_count":7,"area":null},{"id":"2512.07497","title":"How Do LLMs Fail In Agentic Scenarios? A Qualitative Analysis of Success and Failure Scenarios of Various LLMs in Agentic Simulations","created":"2025-12-08","cited_by_count":7,"area":"agents"},{"id":"2501.00418","title":"Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2502.10742","title":"The Philosophical Foundations of Growing AI Like A Child","created":"2025-02-15","cited_by_count":6,"area":"lr"},{"id":"2508.17079","title":"Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation","created":"2025-08-23","cited_by_count":6,"area":"mllm"},{"id":"2311.09694","title":"Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2403.15250","title":"Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach","created":"2024-03-22","cited_by_count":5,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2512.09756","title":"MOA: Multi-Objective Alignment for Role-Playing Agents","created":"2025-12-10","cited_by_count":5,"area":null},{"id":"2309.08316","title":"How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2310.08677","title":"GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2406.08050","title":"Adversarial Evasion Attack Efficiency against Large Language Models","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2409.15290","title":"Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities","created":"2024-09-03","cited_by_count":4,"area":null},{"id":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4,"area":"synth"},{"id":"2504.12991","title":"A Theoretical Framework for OOD Robustness in Transformers using Gevrey Classes","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2507.17695","title":"Symbiotic Agents: A Novel Paradigm for Trustworthy AGI-driven Networks","created":"2025-07-23","cited_by_count":4,"area":"agents"},{"id":"2510.08549","title":"Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2409.02370","title":"Do Large Language Models Possess Sensitive to Sentiment?","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2410.01548","title":"In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2412.20595","title":"Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection","created":"2024-12-29","cited_by_count":3,"area":null},{"id":"2501.10909","title":"Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition","created":"2025-01-19","cited_by_count":3,"area":null},{"id":"2503.14321","title":"COPA: Comparing the incomparable in multi-objective model evaluation","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2503.19828","title":"Contextual Metric Meta-Evaluation by Measuring Local Metric Accuracy","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2505.22355","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2511.08042","title":"Towards a Standard, Enterprise-Relevant Agentic AI Benchmark: Lessons from 5.5 billion tokens' worth of agentic AI evaluations","created":"2025-11-11","cited_by_count":3,"area":"agents"},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2401.07441","title":"Stability Analysis of ChatGPT-based Sentiment Analysis in AI Quality Assurance","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2502.19625","title":"Revealing Treatment Non-Adherence Bias in Clinical Machine Learning Using Large Language Models","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2509.24332","title":"Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2511.23143","title":"Automated Generation of MDPs Using Logic Programming and LLMs for Robotic Applications","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2602.18960","title":"Modularity is the Bedrock of Natural and Artificial Intelligence","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2608.28327","title":"Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers","created":"2026-08-28","cited_by_count":2,"area":null},{"id":"2401.14027","title":"The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2404.11036","title":"Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2408.01459","title":"AgentPeerTalk: Empowering Students through Agentic-AI-Driven Discernment of Bullying and Joking in Peer Interactions in Schools","created":"2024-07-27","cited_by_count":1,"area":"agents"},{"id":"2410.23883","title":"'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2411.19688","title":"SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks","created":"2024-11-29","cited_by_count":1,"area":"mllm"},{"id":"2412.08528","title":"Efficient Continual Learning for Small Language Models with a Discrete Key-Value Bottleneck","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2504.00328","title":"Simple yet Effective Node Property Prediction on Edge Streams under Distribution Shifts","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2504.17070","title":"MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2510.16952","title":"Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2601.04548","title":"Identifying Good and Bad Neurons for Task-Level Controllable LLMs","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2604.17650","title":"Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2605.22641","title":"More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.03606","title":"Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2307.11316","title":"Making Pre-trained Language Models both Task-solvers and Self-calibrators","created":"2023-07-21","cited_by_count":0,"area":null},{"id":"2410.04038","title":"Gamified crowd-sourcing of high-quality data for visual fine-tuning","created":"2024-10-05","cited_by_count":0,"area":"mllm"},{"id":"2501.13598","title":"A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification","created":"2025-01-23","cited_by_count":0,"area":null},{"id":"2507.05307","title":"ASSURE: Metamorphic Testing for AI-powered Browser Extensions","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2511.19996","title":"RankOOD -- Class Ranking-based Out-of-Distribution Detection","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.07832","title":"Do Generalisation Results Generalise?","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.22378","title":"Towards Efficient Post-Training via Fourier-Driven Adapter Architectures","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2601.18739","title":"SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classification","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2606.00014","title":"Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.08296","title":"Revisiting the shutdown problem","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2609.04463","title":"Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning","created":"2026-09-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}