{"total":95,"rows":[{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288,"area":"agents"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"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":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213,"area":"rag"},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2411.14405","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","created":"2024-11-21","cited_by_count":144,"area":"lr"},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122,"area":"alignment"},{"id":"2502.12134","title":"SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs","created":"2025-02-17","cited_by_count":116,"area":"lr"},{"id":"2311.00262","title":"Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents","created":"2023-11-01","cited_by_count":77,"area":"agents"},{"id":"2502.16923","title":"A Systematic Survey of Automatic Prompt Optimization Techniques","created":"2025-02-24","cited_by_count":63,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62,"area":null},{"id":"2402.05121","title":"Large Language Model for Table Processing: A Survey","created":"2024-02-04","cited_by_count":52,"area":null},{"id":"2403.01432","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","created":"2024-03-03","cited_by_count":50,"area":"rag"},{"id":"2310.08184","title":"Learning from models beyond fine-tuning","created":"2023-10-12","cited_by_count":48,"area":null},{"id":"2312.16171","title":"Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4","created":"2023-12-26","cited_by_count":48,"area":null},{"id":"2405.10431","title":"Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models","created":"2024-05-16","cited_by_count":45,"area":"lr"},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"id":"2402.10466","title":"Large Language Models as Zero-shot Dialogue State Tracker through Function Calling","created":"2024-02-16","cited_by_count":34,"area":"agents"},{"id":"2306.09821","title":"Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System","created":"2023-06-16","cited_by_count":32,"area":null},{"id":"2406.05374","title":"Planning Like Human: A Dual-process Framework for Dialogue Planning","created":"2024-06-08","cited_by_count":32,"area":null},{"id":"2404.04442","title":"Exploring Autonomous Agents through the Lens of Large Language Models: A Review","created":"2024-04-05","cited_by_count":31,"area":"agents"},{"id":"2312.02436","title":"MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following","created":"2023-12-05","cited_by_count":30,"area":null},{"id":"2401.09002","title":"AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models","created":"2024-01-17","cited_by_count":28,"area":"safety"},{"id":"2406.19237","title":"FlowVQA: Mapping Multimodal Logic in Visual Question Answering with Flowcharts","created":"2024-06-27","cited_by_count":28,"area":"lr"},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27,"area":null},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2510.02453","title":"How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models","created":"2025-10-02","cited_by_count":24,"area":null},{"id":"2407.04118","title":"MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization","created":"2024-07-04","cited_by_count":21,"area":null},{"id":"2409.12699","title":"PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)","created":"2024-09-19","cited_by_count":19,"area":null},{"id":"2409.13093","title":"Guided Profile Generation Improves Personalization with LLMs","created":"2024-09-19","cited_by_count":19,"area":null},{"id":"2502.11027","title":"On the Effect of Sampling Diversity in Scaling LLM Inference","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2406.04344","title":"Verbalized Machine Learning: Revisiting Machine Learning with Language Models","created":"2024-06-06","cited_by_count":17,"area":null},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"area":"lr"},{"id":"2405.12461","title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2312.09601","title":"Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models","created":"2023-12-15","cited_by_count":13,"area":null},{"id":"2303.11108","title":"CHATEDIT: Towards Multi-turn Interactive Facial Image Editing via Dialogue","created":"2023-03-20","cited_by_count":12,"area":null},{"id":"2402.03719","title":"Empowering Language Models with Active Inquiry for Deeper Understanding","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2403.08950","title":"Exploring Prompt Engineering Practices in the Enterprise","created":"2024-03-13","cited_by_count":11,"area":null},{"id":"2409.14195","title":"The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends","created":"2024-09-21","cited_by_count":11,"area":null},{"id":"2401.05707","title":"CAT-LLM: Style-enhanced Large Language Models with Text Style Definition for Chinese Article-style Transfer","created":"2024-01-11","cited_by_count":10,"area":null},{"id":"2402.17717","title":"AmbigNLG: Addressing Task Ambiguity in Instruction for NLG","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2405.20252","title":"Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimization","created":"2024-05-30","cited_by_count":10,"area":"agents"},{"id":"2402.14871","title":"LLM Based Multi-Agent Generation of Semi-structured Documents from Semantic Templates in the Public Administration Domain","created":"2024-02-21","cited_by_count":9,"area":"agents"},{"id":"2410.20707","title":"DisasterQA: A Benchmark for Assessing the performance of LLMs in Disaster Response","created":"2024-10-09","cited_by_count":9,"area":null},{"id":"2411.00427","title":"DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems","created":"2024-11-01","cited_by_count":9,"area":"agents"},{"id":"2309.08949","title":"Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals","created":"2023-09-16","cited_by_count":8,"area":null},{"id":"2307.05538","title":"Advancements in Scientific Controllable Text Generation Methods","created":"2023-07-08","cited_by_count":7,"area":null},{"id":"2503.17482","title":"What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2506.12266","title":"The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs","created":"2025-06-13","cited_by_count":6,"area":"agents"},{"id":"2602.15143","title":"Protecting Language Models Against Unauthorized Distillation through Trace Rewriting","created":"2026-02-16","cited_by_count":6,"area":"safety"},{"id":"2307.08813","title":"Comparative Performance Evaluation of Large Language Models for Extracting Molecular Interactions and Pathway Knowledge","created":"2023-07-17","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":"2410.12843","title":"Exploring Prompt Engineering: A Systematic Review with SWOT Analysis","created":"2024-10-09","cited_by_count":5,"area":null},{"id":"2405.15585","title":"Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2410.02741","title":"Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2505.21657","title":"Explaining Large Language Models with gSMILE","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2406.14457","title":"Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue","created":"2024-06-20","cited_by_count":3,"area":"alignment"},{"id":"2407.02750","title":"Learning to Reduce: Towards Improving Performance of Large Language Models on Structured Data","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2410.01457","title":"Verbalized Graph Representation Learning: A Fully Interpretable Graph Model Based on Large Language Models Throughout the Entire Process","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2504.18722","title":"MODP: Multi Objective Directional Prompting","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2604.21251","title":"CAP: Controllable Alignment Prompting for Unlearning in LLMs","created":"2026-04-23","cited_by_count":3,"area":"safety"},{"id":"2312.14262","title":"Exploring the intersection of Generative AI and Software Development","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2402.14195","title":"Learning to Reduce: Optimal Representations of Structured Data in Prompting Large Language Models","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2501.19278","title":"Pheromone-based Learning of Optimal Reasoning Paths","created":"2025-01-31","cited_by_count":2,"area":"lr"},{"id":"2503.00449","title":"Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2503.20320","title":"Iterative Prompting with Persuasion Skills in Jailbreaking Large Language Models","created":"2025-03-26","cited_by_count":2,"area":"safety"},{"id":"2504.08744","title":"ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responses","created":"2025-03-23","cited_by_count":2,"area":"rag"},{"id":"2505.12662","title":"Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering","created":"2025-05-19","cited_by_count":2,"area":"rag"},{"id":"2507.18618","title":"TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards","created":"2025-07-24","cited_by_count":2,"area":"lr"},{"id":"2310.00845","title":"Application of frozen large-scale models to multimodal task-oriented dialogue","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2402.14355","title":"Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?","created":"2024-02-22","cited_by_count":1,"area":"lr"},{"id":"2405.13002","title":"DuetRAG: Collaborative Retrieval-Augmented Generation","created":"2024-05-12","cited_by_count":1,"area":"rag"},{"id":"2406.05369","title":"Venn Diagram Prompting : Accelerating Comprehension with Scaffolding Effect","created":"2024-06-08","cited_by_count":1,"area":null},{"id":"2407.00065","title":"A Personalised Learning Tool for Physics Undergraduate Students Built On a Large Language Model for Symbolic Regression","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2410.03731","title":"Unsupervised Human Preference Learning","created":"2024-09-30","cited_by_count":1,"area":"lr"},{"id":"2410.11239","title":"HR-Agent: A Task-Oriented Dialogue (TOD) LLM Agent Tailored for HR Applications","created":"2024-10-15","cited_by_count":1,"area":"agents"},{"id":"2411.17976","title":"The importance of visual modelling languages in generative software engineering","created":"2024-11-27","cited_by_count":1,"area":null},{"id":"2503.06525","title":"From Motion Signals to Insights: A Unified Framework for Student Behavior Analysis and Feedback in Physical Education Classes","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2507.10326","title":"Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.04626","title":"P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis","created":"2025-08-06","cited_by_count":1,"area":"alignment"},{"id":"2508.13948","title":"Prompt Orchestration Markup Language","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2508.15456","title":"PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2508.18992","title":"Automatic Prompt Optimization with Prompt Distillation","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.16475","title":"Towards Universal Debiasing for Language Models-based Tabular Data Generation","created":"2025-09-20","cited_by_count":1,"area":"alignment"},{"id":"2504.02965","title":"CoLa: Learning to Interactively Collaborate with Large Language Models","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2504.08281","title":"ELSA: A Style Aligned Dataset for Emotionally Intelligent Language Generation","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2507.20423","title":"CodeNER: Code Prompting for Named Entity Recognition","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2512.16272","title":"Beyond Blind Spots: Analytic Hints for Mitigating LLM-Based Evaluation Pitfalls","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.14091","title":"Zero-shot adaptable task planning for autonomous construction robots: a comparative study of lightweight single and multi-AI agent systems","created":"2026-01-20","cited_by_count":0,"area":"agents"},{"id":"2604.09741","title":"ExecTune: Effective Steering of Black-Box LLMs with Guide Models","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.22565","title":"Learning Evidence Highlighting for Frozen LLMs","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.18597","title":"Latent Action Reparameterization for Efficient Agent Inference","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2609.38142","title":"AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2610.13000","title":"Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}