{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"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":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2208.10264","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","created":"2022-08-18","cited_by_count":515},{"id":"1908.09203","title":"Release Strategies and the Social Impacts of Language Models","created":"2019-08-24","cited_by_count":513},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2311.04892","title":"Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs","created":"2023-11-08","cited_by_count":199},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195},{"id":"2310.17976","title":"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews","created":"2023-10-27","cited_by_count":179},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144},{"id":"1811.09310","title":"Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack","created":"2018-11-22","cited_by_count":125},{"id":"2206.07550","title":"Evaluating and Inducing Personality in Pre-trained Language Models","created":"2022-05-20","cited_by_count":123},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116},{"id":"2305.08809","title":"Interpretability at Scale: Identifying Causal Mechanisms in Alpaca","created":"2023-05-15","cited_by_count":103},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67},{"id":"2406.02888","title":"HYDRA: Model Factorization Framework for Black-Box LLM Personalization","created":"2024-06-05","cited_by_count":60},{"id":"2307.16180","title":"Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models","created":"2023-07-30","cited_by_count":56},{"id":"2403.07809","title":"pyvene: A Library for Understanding and Improving PyTorch Models via Interventions","created":"2024-03-12","cited_by_count":54},{"id":"2402.13717","title":"Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent","created":"2024-02-21","cited_by_count":52},{"id":"2309.08163","title":"Self-Assessment Tests are Unreliable Measures of LLM Personality","created":"2023-09-15","cited_by_count":39},{"id":"2402.12366","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","created":"2024-02-19","cited_by_count":36},{"id":"2112.06346","title":"ValueNet: A New Dataset for Human Value Driven Dialogue System","created":"2021-12-12","cited_by_count":34},{"id":"2311.09433","title":"Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment","created":"2023-11-15","cited_by_count":30},{"id":"2312.07401","title":"On Diversified Preferences of Large Language Model Alignment","created":"2023-12-12","cited_by_count":26},{"id":"2405.12739","title":"SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling","created":"2024-05-21","cited_by_count":21},{"id":"2402.10151","title":"ControlLM: Crafting Diverse Personalities for Language Models","created":"2024-02-15","cited_by_count":15},{"id":"2307.10569","title":"Deceptive Alignment Monitoring","created":"2023-07-20","cited_by_count":14},{"id":"2304.01665","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","created":"2023-04-04","cited_by_count":12},{"id":"2305.17147","title":"Heterogeneous Value Alignment Evaluation for Large Language Models","created":"2023-05-26","cited_by_count":7},{"id":"2404.07084","title":"Dynamic Generation of Personalities with Large Language Models","created":"2024-04-10","cited_by_count":4}],"next_cursor":null}