{"list":"other","total":58,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2305.03495","title":"Automatic Prompt Optimization with \"Gradient Descent\" and Beam Search","created":"2023-05-04","cited_by_count":653},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2510.04618","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","created":"2025-10-06","cited_by_count":398},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2405.10369","title":"Reinforcement learning","created":"2024-05-16","cited_by_count":247},{"id":"2105.08209","title":"BookSum: A Collection of Datasets for Long-form Narrative Summarization","created":"2021-05-18","cited_by_count":184},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176},{"id":"2411.03350","title":"A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness","created":"2024-11-04","cited_by_count":127},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"2310.19488","title":"CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation","created":"2023-10-30","cited_by_count":100},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90},{"id":"2502.11211","title":"A Survey of LLM-based Agents in Medicine: How far are we from Baymax?","created":"2025-02-16","cited_by_count":85},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83},{"id":"2402.12984","title":"Can GNN be Good Adapter for LLMs?","created":"2024-02-20","cited_by_count":71},{"id":"2503.21322","title":"HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation","created":"2025-03-27","cited_by_count":68},{"id":"2507.21892","title":"Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning","created":"2025-07-29","cited_by_count":52},{"id":"2406.02746","title":"RATT: A Thought Structure for Coherent and Correct LLM Reasoning","created":"2024-06-04","cited_by_count":41},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37},{"id":"2312.02614","title":"Prompt Optimization via Adversarial In-Context Learning","created":"2023-12-05","cited_by_count":33},{"id":"2510.02453","title":"How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models","created":"2025-10-02","cited_by_count":24},{"id":"2407.10725","title":"CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses","created":"2024-07-15","cited_by_count":23},{"id":"2501.18922","title":"KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search","created":"2025-01-31","cited_by_count":22},{"id":"2509.09708","title":"Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal","created":"2025-09-07","cited_by_count":19},{"id":"2503.16874","title":"MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization","created":"2025-03-21","cited_by_count":15},{"id":"2505.10981","title":"Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory","created":"2025-05-16","cited_by_count":10},{"id":"2503.13208","title":"Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach","created":"2025-03-17","cited_by_count":9},{"id":"2510.16932","title":"Prompt-MII: Meta-Learning Instruction Induction for LLMs","created":"2025-10-19","cited_by_count":9},{"id":"2406.16767","title":"The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories","created":"2024-06-24","cited_by_count":8},{"id":"2406.12382","title":"From Instance Training to Instruction Learning: Task Adapters Generation from Instructions","created":"2024-06-18","cited_by_count":4},{"id":"2508.02458","title":"From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning","created":"2025-08-04","cited_by_count":3},{"id":"2506.16389","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","created":"2025-06-19","cited_by_count":2},{"id":"2507.18618","title":"TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards","created":"2025-07-24","cited_by_count":2},{"id":"2505.19430","title":"Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation","created":"2025-05-26","cited_by_count":1},{"id":"2510.20252","title":"Individualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods","created":"2025-10-23","cited_by_count":1}],"next_cursor":null}