{"total":268,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240,"area":"safety"},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226,"area":null},{"id":"2309.08532","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","created":"2023-09-15","cited_by_count":193,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2311.08734","title":"Thread of Thought Unraveling Chaotic Contexts","created":"2023-11-15","cited_by_count":72,"area":"lr"},{"id":"2405.06373","title":"LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play","created":"2024-05-10","cited_by_count":66,"area":null},{"id":"2402.07688","title":"CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge","created":"2024-02-12","cited_by_count":55,"area":"rag"},{"id":"2310.12860","title":"Probing LLMs for hate speech detection: strengths and vulnerabilities","created":"2023-10-19","cited_by_count":52,"area":null},{"id":"2401.05799","title":"Designing Heterogeneous LLM Agents for Financial Sentiment Analysis","created":"2024-01-11","cited_by_count":48,"area":"agents"},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46,"area":null},{"id":"2409.16191","title":"HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models","created":"2024-09-24","cited_by_count":44,"area":null},{"id":"2311.09022","title":"Exploring the Potential of Large Language Models in Computational Argumentation","created":"2023-11-15","cited_by_count":42,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2503.01013","title":"TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop","created":"2025-03-02","cited_by_count":39,"area":null},{"id":"2402.03659","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","created":"2024-02-06","cited_by_count":36,"area":null},{"id":"2410.02724","title":"Large Language Models as Markov Chains","created":"2024-10-03","cited_by_count":35,"area":null},{"id":"2310.15556","title":"TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction","created":"2023-10-24","cited_by_count":34,"area":"rag"},{"id":"2308.13911","title":"A Wide Evaluation of ChatGPT on Affective Computing Tasks","created":"2023-08-26","cited_by_count":30,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2310.11374","title":"DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations","created":"2023-10-17","cited_by_count":30,"area":null},{"id":"2410.14731","title":"MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection","created":"2024-10-16","cited_by_count":29,"area":"inference"},{"id":"2403.04260","title":"Can Small Language Models be Good Reasoners for Sequential Recommendation?","created":"2024-03-07","cited_by_count":26,"area":"lr"},{"id":"2404.04633","title":"Context versus Prior Knowledge in Language Models","created":"2024-04-06","cited_by_count":26,"area":null},{"id":"2311.18580","title":"FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity","created":"2023-11-30","cited_by_count":25,"area":null},{"id":"2408.04638","title":"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective","created":"2024-07-30","cited_by_count":25,"area":null},{"id":"2406.06027","title":"HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs","created":"2024-06-10","cited_by_count":24,"area":null},{"id":"2406.18966","title":"DataGen: Unified Synthetic Dataset Generation via Large Language Models","created":"2024-06-27","cited_by_count":23,"area":"synth"},{"id":"2407.16893","title":"The Price of Prompting: Profiling Energy Use in Large Language Models Inference","created":"2024-07-04","cited_by_count":23,"area":null},{"id":"2501.13772","title":"Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models","created":"2025-01-23","cited_by_count":23,"area":"safety"},{"id":"2310.06046","title":"LLM for SoC Security: A Paradigm Shift","created":"2023-10-09","cited_by_count":22,"area":null},{"id":"2405.02764","title":"Assessing Adversarial Robustness of Large Language Models: An Empirical Study","created":"2024-05-04","cited_by_count":21,"area":null},{"id":"2401.15071","title":"From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities","created":"2024-01-26","cited_by_count":19,"area":"mllm"},{"id":"2402.11958","title":"Understanding the Therapeutic Relationship between Counselors and Clients in Online Text-based Counseling using LLMs","created":"2024-02-19","cited_by_count":19,"area":null},{"id":"2412.04509","title":"Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection","created":"2024-12-04","cited_by_count":19,"area":null},{"id":"2310.09036","title":"MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks","created":"2023-10-13","cited_by_count":18,"area":"mllm"},{"id":"2412.17837","title":"Evaluating the Capabilities of Large Language Models for Multi-label Emotion Understanding","created":"2024-12-17","cited_by_count":17,"area":"lr"},{"id":"2310.13571","title":"Why Can Large Language Models Generate Correct Chain-of-Thoughts?","created":"2023-10-20","cited_by_count":16,"area":"lr"},{"id":"2406.01806","title":"Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation","created":"2024-06-03","cited_by_count":16,"area":null},{"id":"2406.08068","title":"Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey","created":"2024-06-12","cited_by_count":16,"area":null},{"id":"2309.14379","title":"Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligence","created":"2023-09-24","cited_by_count":15,"area":null},{"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":"2504.04462","title":"An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability","created":"2025-04-06","cited_by_count":15,"area":null},{"id":"2504.16405","title":"EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment","created":"2025-04-23","cited_by_count":15,"area":"mllm"},{"id":"2505.12567","title":"A Survey of Attacks on Large Language Models","created":"2025-05-18","cited_by_count":15,"area":"agents"},{"id":"2505.16491","title":"LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing","created":"2025-05-22","cited_by_count":15,"area":null},{"id":"2410.07053","title":"Robots in the Middle: Evaluating LLMs in Dispute Resolution","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2410.13153","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2403.07260","title":"LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristics","created":"2024-03-12","cited_by_count":13,"area":null},{"id":"2503.06982","title":"Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2507.16248","title":"FinResearchBench: A Logic Tree based Agent-as-a-Judge Evaluation Framework for Financial Research Agents","created":"2025-07-22","cited_by_count":12,"area":"agents"},{"id":"2509.19406","title":"TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding","created":"2025-09-23","cited_by_count":12,"area":null},{"id":"2308.07505","title":"Data Race Detection Using Large Language Models","created":"2023-08-15","cited_by_count":11,"area":null},{"id":"2311.01876","title":"Sentiment Analysis through LLM Negotiations","created":"2023-11-03","cited_by_count":11,"area":null},{"id":"2407.18454","title":"Fairness Definitions in Language Models Explained","created":"2024-07-26","cited_by_count":11,"area":null},{"id":"2411.11235","title":"MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis","created":"2024-11-18","cited_by_count":11,"area":"mllm"},{"id":"2307.04251","title":"ChatGPT in the Age of Generative AI and Large Language Models: A Concise Survey","created":"2023-07-09","cited_by_count":10,"area":null},{"id":"2404.05213","title":"Evaluation of an LLM in Identifying Logical Fallacies: A Call for Rigor When Adopting LLMs in HCI Research","created":"2024-04-08","cited_by_count":10,"area":null},{"id":"2506.01001","title":"FedQuad: Adaptive Layer-wise LoRA Deployment and Activation Quantization for Federated Fine-Tuning","created":"2025-06-01","cited_by_count":10,"area":null},{"id":"2309.12881","title":"Affect Recognition in Conversations Using Large Language Models","created":"2023-09-22","cited_by_count":9,"area":null},{"id":"2310.19626","title":"Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2407.02340","title":"RVISA: Reasoning and Verification for Implicit Sentiment Analysis","created":"2024-07-02","cited_by_count":9,"area":"lr"},{"id":"2502.13044","title":"Do we still need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Prediction","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2508.07959","title":"Large Language Models for Subjective Language Understanding: A Survey","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2404.04361","title":"Deciphering Political Entity Sentiment in News with Large Language Models: Zero-Shot and Few-Shot Strategies","created":"2024-04-05","cited_by_count":8,"area":null},{"id":"2404.07546","title":"Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning","created":"2024-04-11","cited_by_count":8,"area":"lr"},{"id":"2408.08545","title":"SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models","created":"2024-08-16","cited_by_count":8,"area":null},{"id":"2409.13317","title":"JMedBench: A Benchmark for Evaluating Japanese Biomedical Large Language Models","created":"2024-09-20","cited_by_count":8,"area":null},{"id":"2411.02476","title":"A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2412.01377","title":"Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2311.09569","title":"Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisation","created":"2023-11-16","cited_by_count":7,"area":null},{"id":"2404.08681","title":"EFSA: Towards Event-Level Financial Sentiment Analysis","created":"2024-04-08","cited_by_count":7,"area":null},{"id":"2406.06576","title":"OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step","created":"2024-06-04","cited_by_count":7,"area":"lr"},{"id":"2410.09343","title":"ELICIT: LLM Augmentation via External In-Context Capability","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2412.09415","title":"Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2504.13199","title":"Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Tasks","created":"2025-04-14","cited_by_count":7,"area":"mllm"},{"id":"2505.19776","title":"Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2507.03194","title":"Quantifying Cognitive Bias Induction in LLM-Generated Content","created":"2025-07-03","cited_by_count":7,"area":null},{"id":"2307.04648","title":"Can ChatGPT's Responses Boost Traditional Natural Language Processing?","created":"2023-07-06","cited_by_count":6,"area":null},{"id":"2312.08725","title":"A Comparative Analysis of Fine-Tuned LLMs and Few-Shot Learning of LLMs for Financial Sentiment Analysis","created":"2023-12-14","cited_by_count":6,"area":null},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2408.11546","title":"Memorization in In-Context Learning","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2410.11711","title":"Zero-shot Model-based Reinforcement Learning using Large Language Models","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2502.14718","title":"Entity Framing and Role Portrayal in the News","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2511.07322","title":"FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation","created":"2025-11-10","cited_by_count":6,"area":"agents"},{"id":"2311.08306","title":"On-the-Fly Fusion of Large Language Models and Machine Translation","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2402.08472","title":"Large Language Models for the Automated Analysis of Optimization Algorithms","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2403.00881","title":"FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission","created":"2024-03-01","cited_by_count":5,"area":null},{"id":"2408.03359","title":"LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification","created":"2024-08-06","cited_by_count":5,"area":null},{"id":"2409.13054","title":"LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models","created":"2024-09-19","cited_by_count":5,"area":"safety"},{"id":"2412.02279","title":"A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysis","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2412.12564","title":"Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2503.11655","title":"Explainable Sentiment Analysis with DeepSeek-R1: Performance, Efficiency, and Few-Shot Learning","created":"2025-02-03","cited_by_count":5,"area":"lr"}],"next_cursor":"100"}