{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"2406.18629","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","created":"2024-06-26","cited_by_count":273},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"id":"2403.19159","title":"Disentangling Length from Quality in Direct Preference Optimization","created":"2024-03-28","cited_by_count":196},{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188},{"id":"2005.12729","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","created":"2020-05-25","cited_by_count":186},{"id":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144},{"id":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109},{"id":"2411.01111","title":"Rule Based Rewards for Language Model Safety","created":"2024-11-02","cited_by_count":108},{"id":"2305.08844","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","created":"2023-05-15","cited_by_count":105},{"id":"2308.04592","title":"Shepherd: A Critic for Language Model Generation","created":"2023-08-08","cited_by_count":97},{"id":"2407.08639","title":"$\\beta$-DPO: Direct Preference Optimization with Dynamic $\\beta$","created":"2024-07-11","cited_by_count":90},{"id":"1907.01752","title":"On the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2019-07-03","cited_by_count":82},{"id":"2305.13735","title":"Aligning Large Language Models through Synthetic Feedback","created":"2023-05-23","cited_by_count":75},{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71},{"id":"2410.04350","title":"TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights","created":"2024-10-06","cited_by_count":42},{"id":"2401.06081","title":"Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint","created":"2024-01-11","cited_by_count":39},{"id":"2311.04072","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","created":"2023-11-07","cited_by_count":35},{"id":"2312.02614","title":"Prompt Optimization via Adversarial In-Context Learning","created":"2023-12-05","cited_by_count":33},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31},{"id":"2311.03648","title":"Instruct Me More! Random Prompting for Visual In-Context Learning","created":"2023-11-07","cited_by_count":30},{"id":"2311.08045","title":"Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game","created":"2023-11-14","cited_by_count":27},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21},{"id":"2405.12739","title":"SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling","created":"2024-05-21","cited_by_count":21},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21},{"id":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19},{"id":"2502.13775","title":"VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare","created":"2025-02-19","cited_by_count":17},{"id":"2312.14591","title":"Reasons to Reject? Aligning Language Models with Judgments","created":"2023-12-22","cited_by_count":15},{"id":"2406.02756","title":"Aligning Large Language Models via Fine-grained Supervision","created":"2024-06-04","cited_by_count":13},{"id":"2407.10233","title":"Visual Prompt Selection for In-Context Learning Segmentation","created":"2024-07-14","cited_by_count":13},{"id":"2406.14955","title":"ICLEval: Evaluating In-Context Learning Ability of Large Language Models","created":"2024-06-21","cited_by_count":12},{"id":"2411.07618","title":"Constrain Alignment with Sparse Autoencoders","created":"2024-11-12","cited_by_count":12},{"id":"2406.07657","title":"OPTune: Efficient Online Preference Tuning","created":"2024-06-11","cited_by_count":10},{"id":"2309.10015","title":"SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language Feedback","created":"2023-09-18","cited_by_count":6},{"id":"2407.05693","title":"Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation","created":"2024-07-08","cited_by_count":4}],"next_cursor":null}