{"list":"other","total":99,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2305.03495","title":"Automatic Prompt Optimization with \"Gradient Descent\" and Beam Search","created":"2023-05-04","cited_by_count":653},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","created":"2025-07-25","cited_by_count":542},{"id":"2402.04788","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark","created":"2024-02-07","cited_by_count":372},{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"2406.11695","title":"Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs","created":"2024-06-17","cited_by_count":291},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238},{"id":"2310.16427","title":"PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization","created":"2023-10-25","cited_by_count":233},{"id":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2309.08532","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","created":"2023-09-15","cited_by_count":193},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172},{"id":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149},{"id":"2203.07281","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","created":"2022-03-14","cited_by_count":127},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105},{"id":"2403.17804","title":"Improving Text-to-Image Consistency via Automatic Prompt Optimization","created":"2024-03-26","cited_by_count":90},{"id":"2505.10320","title":"J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning","created":"2025-05-15","cited_by_count":75},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70},{"id":"2306.03082","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","created":"2023-06-05","cited_by_count":68},{"id":"2311.18702","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","created":"2023-11-30","cited_by_count":66},{"id":"2502.16923","title":"A Systematic Survey of Automatic Prompt Optimization Techniques","created":"2025-02-24","cited_by_count":63},{"id":"2311.05661","title":"Prompt Engineering a Prompt Engineer","created":"2023-11-09","cited_by_count":53},{"id":"2305.09993","title":"Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling","created":"2023-05-17","cited_by_count":47},{"id":"2401.08189","title":"PRewrite: Prompt Rewriting with Reinforcement Learning","created":"2024-01-16","cited_by_count":45},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41},{"id":"2510.27106","title":"Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks","created":"2025-10-31","cited_by_count":38},{"id":"2210.17041","title":"GPS: Genetic Prompt Search for Efficient Few-shot Learning","created":"2022-10-31","cited_by_count":37},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37},{"id":"2502.11689","title":"Improve LLM-as-a-Judge Ability as a General Ability","created":"2025-02-17","cited_by_count":37},{"id":"2309.05950","title":"Language Models as Black-Box Optimizers for Vision-Language Models","created":"2023-09-12","cited_by_count":36},{"id":"2405.18369","title":"PromptWizard: Task-Aware Prompt Optimization Framework","created":"2024-05-28","cited_by_count":36},{"id":"2310.15428","title":"ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles","created":"2023-10-24","cited_by_count":33},{"id":"2312.02614","title":"Prompt Optimization via Adversarial In-Context Learning","created":"2023-12-05","cited_by_count":33},{"id":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32},{"id":"2402.08702","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","created":"2024-02-13","cited_by_count":32},{"id":"2409.11239","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","created":"2024-09-17","cited_by_count":32},{"id":"2307.07415","title":"AutoHint: Automatic Prompt Optimization with Hint Generation","created":"2023-07-13","cited_by_count":30},{"id":"2310.02905","title":"Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers","created":"2023-10-02","cited_by_count":30},{"id":"2404.02319","title":"Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization","created":"2024-04-02","cited_by_count":30},{"id":"2408.08808","title":"Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge","created":"2024-08-16","cited_by_count":30},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30},{"id":"2406.15708","title":"Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization","created":"2024-06-22","cited_by_count":29},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29},{"id":"2410.20774","title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation","created":"2024-10-28","cited_by_count":29},{"id":"2308.12033","title":"PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine","created":"2023-08-23","cited_by_count":28},{"id":"2406.14449","title":"APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking","created":"2024-06-20","cited_by_count":28},{"id":"2310.01467","title":"FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models","created":"2023-10-02","cited_by_count":26},{"id":"2408.09235","title":"Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA","created":"2024-08-17","cited_by_count":25},{"id":"2311.07811","title":"In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax","created":"2023-11-13","cited_by_count":22},{"id":"2505.14268","title":"Think-J: Learning to Think for Generative LLM-as-a-Judge","created":"2025-05-20","cited_by_count":21},{"id":"2308.10088","title":"PACE: Improving Prompt with Actor-Critic Editing for Large Language Model","created":"2023-08-19","cited_by_count":20},{"id":"2305.13954","title":"Robust Prompt Optimization for Large Language Models Against Distribution Shifts","created":"2023-05-23","cited_by_count":19},{"id":"2406.10504","title":"Task Facet Learning: A Structured Approach to Prompt Optimization","created":"2024-06-15","cited_by_count":19},{"id":"2410.02748","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","created":"2024-10-03","cited_by_count":18},{"id":"2310.12774","title":"Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning","created":"2023-10-19","cited_by_count":17},{"id":"2410.08601","title":"StraGo: Harnessing Strategic Guidance for Prompt Optimization","created":"2024-10-11","cited_by_count":17},{"id":"2402.11711","title":"MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization","created":"2024-02-18","cited_by_count":16},{"id":"2407.00256","title":"One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts","created":"2024-06-28","cited_by_count":16},{"id":"2311.10117","title":"Automatic Engineering of Long Prompts","created":"2023-11-16","cited_by_count":14},{"id":"2410.15397","title":"IPO: Interpretable Prompt Optimization for Vision-Language Models","created":"2024-10-20","cited_by_count":14},{"id":"2402.13764","title":"CriticEval: Evaluating Large Language Model as Critic","created":"2024-02-21","cited_by_count":13},{"id":"2405.20701","title":"Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement","created":"2024-05-31","cited_by_count":13},{"id":"2408.13704","title":"DHP Benchmark: Are LLMs Good NLG Evaluators?","created":"2024-08-25","cited_by_count":12},{"id":"2410.08696","title":"AMPO: Automatic Multi-Branched Prompt Optimization","created":"2024-10-11","cited_by_count":11},{"id":"2410.09652","title":"Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution","created":"2024-10-12","cited_by_count":9},{"id":"2411.10670","title":"IntentGPT: Few-shot Intent Discovery with Large Language Models","created":"2024-11-16","cited_by_count":8},{"id":"2402.11811","title":"FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema","created":"2024-02-19","cited_by_count":6},{"id":"2407.14733","title":"Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL","created":"2024-07-20","cited_by_count":6},{"id":"2410.06154","title":"GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models","created":"2024-10-08","cited_by_count":6},{"id":"2412.18196","title":"Auto-Prompt Generation is Not Robust: Prompt Optimization Driven by Pseudo Gradient","created":"2024-12-24","cited_by_count":6},{"id":"2406.13443","title":"Dual-Phase Accelerated Prompt Optimization","created":"2024-06-19","cited_by_count":4},{"id":"2408.12910","title":"Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance","created":"2024-08-23","cited_by_count":4},{"id":"2406.11706","title":"Prompts as Auto-Optimized Training Hyperparameters: Training Best-in-Class IR Models from Scratch with 10 Gold Labels","created":"2024-06-17","cited_by_count":3}],"next_cursor":null}