{"list":"other","total":62,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"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":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2010.11784","title":"Self-Alignment Pretraining for Biomedical Entity Representations","created":"2020-10-22","cited_by_count":237},{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232},{"id":"1609.06038","title":"Enhanced LSTM for Natural Language Inference","created":"2016-09-20","cited_by_count":200},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178},{"id":"2008.12009","title":"A Survey of Evaluation Metrics Used for NLG Systems","created":"2020-08-27","cited_by_count":164},{"id":"2307.15343","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","created":"2023-07-28","cited_by_count":157},{"id":"2309.17012","title":"Benchmarking Cognitive Biases in Large Language Models as Evaluators","created":"2023-09-29","cited_by_count":150},{"id":"2403.00409","title":"Provably Robust DPO: Aligning Language Models with Noisy Feedback","created":"2024-03-01","cited_by_count":135},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124},{"id":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85},{"id":"1909.06694","title":"Beyond BLEU: Training Neural Machine Translation with Semantic Similarity","created":"2019-09-14","cited_by_count":84},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57},{"id":"1808.10192","title":"Towards a Better Metric for Evaluating Question Generation Systems","created":"2018-08-30","cited_by_count":52},{"id":"2008.11293","title":"Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization","created":"2020-08-25","cited_by_count":52},{"id":"2012.12573","title":"Automated Lay Language Summarization of Biomedical Scientific Reviews","created":"2020-12-23","cited_by_count":46},{"id":"2404.04656","title":"Binary Classifier Optimization for Large Language Model Alignment","created":"2024-04-06","cited_by_count":45},{"id":"2402.00856","title":"Towards Efficient Exact Optimization of Language Model Alignment","created":"2024-02-01","cited_by_count":37},{"id":"2004.14667","title":"NUBIA: NeUral Based Interchangeability Assessor for Text Generation","created":"2020-04-30","cited_by_count":34},{"id":"2204.00447","title":"Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation","created":"2022-04-01","cited_by_count":33},{"id":"1604.00400","title":"Revisiting Summarization Evaluation for Scientific Articles","created":"2016-04-01","cited_by_count":31},{"id":"2208.08408","title":"Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models","created":"2022-08-17","cited_by_count":30},{"id":"2406.05882","title":"Distributional Preference Alignment of LLMs via Optimal Transport","created":"2024-06-09","cited_by_count":26},{"id":"2107.00176","title":"Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards","created":"2021-07-01","cited_by_count":22},{"id":"2408.08566","title":"Overview of the BioLaySumm 2024 Shared Task on the Lay Summarization of Biomedical Research Articles","created":"2024-08-16","cited_by_count":18},{"id":"2404.00530","title":"Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization","created":"2024-03-31","cited_by_count":15},{"id":"2303.03948","title":"A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization","created":"2023-03-07","cited_by_count":14},{"id":"2204.03035","title":"Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding","created":"2022-04-06","cited_by_count":13},{"id":"2305.17364","title":"An Investigation of Evaluation Metrics for Automated Medical Note Generation","created":"2023-05-27","cited_by_count":10},{"id":"1907.12679","title":"Machine Translation Evaluation with BERT Regressor","created":"2019-07-29","cited_by_count":6},{"id":"2203.02951","title":"Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","created":"2022-03-06","cited_by_count":6},{"id":"2211.12118","title":"HaRiM$^+$: Evaluating Summary Quality with Hallucination Risk","created":"2022-11-22","cited_by_count":6}],"next_cursor":null}