{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"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":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192},{"id":"2311.09528","title":"HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM","created":"2023-11-16","cited_by_count":142},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111},{"id":"1912.00903","title":"ZuCo 2.0: A Dataset of Physiological Recordings During Natural Reading and Annotation","created":"2019-12-02","cited_by_count":66},{"id":"2409.10164","title":"Quantile Regression for Distributional Reward Models in RLHF","created":"2024-09-16","cited_by_count":60},{"id":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57},{"id":"2010.07891","title":"Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention","created":"2020-10-15","cited_by_count":45},{"id":"2307.12950","title":"RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment","created":"2023-07-24","cited_by_count":43},{"id":"2010.06396","title":"Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension","created":"2020-10-13","cited_by_count":29},{"id":"2104.05433","title":"Multilingual Language Models Predict Human Reading Behavior","created":"2021-04-12","cited_by_count":29},{"id":"1902.10068","title":"Entity Recognition at First Sight: Improving NER with Eye Movement Information","created":"2019-02-26","cited_by_count":26},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22},{"id":"2205.10226","title":"Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?","created":"2022-04-25","cited_by_count":20},{"id":"1701.05581","title":"Leveraging Cognitive Features for Sentiment Analysis","created":"2017-01-19","cited_by_count":19},{"id":"2304.10784","title":"Eyettention: An Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading","created":"2023-04-21","cited_by_count":19},{"id":"1904.02682","title":"Advancing NLP with Cognitive Language Processing Signals","created":"2019-04-04","cited_by_count":18},{"id":"2403.08309","title":"HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback","created":"2024-03-13","cited_by_count":15},{"id":"2310.15587","title":"ScanDL: A Diffusion Model for Generating Synthetic Scanpaths on Texts","created":"2023-10-24","cited_by_count":14},{"id":"2410.01532","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","created":"2024-10-02","cited_by_count":12},{"id":"2106.05544","title":"CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals","created":"2021-06-10","cited_by_count":11},{"id":"2112.15471","title":"A Survey on Using Gaze Behaviour for Natural Language Processing","created":"2021-12-21","cited_by_count":11},{"id":"1810.04839","title":"Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour","created":"2018-10-11","cited_by_count":9},{"id":"2005.12078","title":"Happy Are Those Who Grade without Seeing: A Multi-Task Learning Approach to Grade Essays Using Gaze Behaviour","created":"2020-05-25","cited_by_count":9},{"id":"2402.14096","title":"EyeTrans: Merging Human and Machine Attention for Neural Code Summarization","created":"2024-02-21","cited_by_count":9},{"id":"2310.14676","title":"Pre-Trained Language Models Augmented with Synthetic Scanpaths for Natural Language Understanding","created":"2023-10-23","cited_by_count":8},{"id":"2104.07244","title":"TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction","created":"2021-04-15","cited_by_count":7},{"id":"2204.13311","title":"The Copenhagen Corpus of Eye Tracking Recordings from Natural Reading of Danish Texts","created":"2022-04-28","cited_by_count":7},{"id":"2312.10175","title":"UniAR: A Unified model for predicting human Attention and Responses on visual content","created":"2023-12-15","cited_by_count":7},{"id":"2303.17876","title":"WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset","created":"2023-03-31","cited_by_count":6},{"id":"2310.05216","title":"Probing Large Language Models from A Human Behavioral Perspective","created":"2023-10-08","cited_by_count":5},{"id":"2403.00506","title":"PoTeC: A German Naturalistic Eye-tracking-while-reading Corpus","created":"2024-03-01","cited_by_count":5},{"id":"2408.04289","title":"EMTeC: A Corpus of Eye Movements on Machine-Generated Texts","created":"2024-08-08","cited_by_count":5},{"id":"2404.00620","title":"Reporting Eye-Tracking Data Quality: Towards a New Standard","created":"2024-03-31","cited_by_count":4},{"id":"2311.00159","title":"Longer Fixations, More Computation: Gaze-Guided Recurrent Neural Networks","created":"2023-10-31","cited_by_count":3},{"id":"2405.09691","title":"Modeling User Preferences via Brain-Computer Interfacing","created":"2024-05-15","cited_by_count":1}],"next_cursor":null}