{"list":"other","total":62,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2304.08177","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","created":"2023-04-17","cited_by_count":305},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282},{"id":"2104.07857","title":"ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning","created":"2021-04-16","cited_by_count":256},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"1802.01483","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","created":"2018-02-05","cited_by_count":227},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206},{"id":"2302.03241","title":"Continual Pre-training of Language Models","created":"2023-02-07","cited_by_count":198},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"2312.05934","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","created":"2023-12-10","cited_by_count":178},{"id":"2304.06027","title":"Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA","created":"2023-04-12","cited_by_count":141},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"1711.05073","title":"DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications","created":"2017-11-14","cited_by_count":110},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105},{"id":"2010.05444","title":"OCNLI: Original Chinese Natural Language Inference","created":"2020-10-12","cited_by_count":86},{"id":"2012.15504","title":"Continual Learning in Task-Oriented Dialogue Systems","created":"2020-12-31","cited_by_count":83},{"id":"2310.04793","title":"FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets","created":"2023-10-07","cited_by_count":69},{"id":"2403.20046","title":"Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning","created":"2024-03-29","cited_by_count":69},{"id":"2310.15205","title":"DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning","created":"2023-10-23","cited_by_count":64},{"id":"2306.12420","title":"LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models","created":"2023-06-21","cited_by_count":60},{"id":"2310.20246","title":"Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations","created":"2023-10-31","cited_by_count":59},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33},{"id":"2203.10652","title":"Continual Sequence Generation with Adaptive Compositional Modules","created":"2022-03-20","cited_by_count":31},{"id":"2105.03953","title":"Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation","created":"2021-05-09","cited_by_count":29},{"id":"2307.08114","title":"Tangent Model Composition for Ensembling and Continual Fine-tuning","created":"2023-07-16","cited_by_count":25},{"id":"2209.15206","title":"What Makes Pre-trained Language Models Better Zero-shot Learners?","created":"2022-09-30","cited_by_count":23},{"id":"2305.05968","title":"Investigating Forgetting in Pre-Trained Representations Through Continual Learning","created":"2023-05-10","cited_by_count":21},{"id":"2310.12342","title":"Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking","created":"2023-10-18","cited_by_count":19},{"id":"2203.12926","title":"Multitasking Framework for Unsupervised Simple Definition Generation","created":"2022-03-24","cited_by_count":18},{"id":"2310.13231","title":"Multi-level Contrastive Learning for Script-based Character Understanding","created":"2023-10-20","cited_by_count":15},{"id":"2009.09364","title":"Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference","created":"2020-09-20","cited_by_count":13},{"id":"2306.06058","title":"Assisting Language Learners: Automated Trans-Lingual Definition Generation via Contrastive Prompt Learning","created":"2023-06-09","cited_by_count":13},{"id":"2210.00543","title":"Fine-grained Contrastive Learning for Definition Generation","created":"2022-10-02","cited_by_count":10},{"id":"2211.14838","title":"PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets","created":"2022-11-27","cited_by_count":10},{"id":"2109.08805","title":"BERT-Beta: A Proactive Probabilistic Approach to Text Moderation","created":"2021-09-18","cited_by_count":6},{"id":"2403.07322","title":"A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing Models","created":"2024-03-12","cited_by_count":5},{"id":"2404.08964","title":"Understanding Multimodal Deep Neural Networks: A Concept Selection View","created":"2024-04-13","cited_by_count":4},{"id":"2204.07701","title":"BLCU-ICALL at SemEval-2022 Task 1: Cross-Attention Multitasking Framework for Definition Modeling","created":"2022-04-16","cited_by_count":3},{"id":"2403.06725","title":"Improving Low-Resource Knowledge Tracing Tasks by Supervised Pre-training and Importance Mechanism Fine-tuning","created":"2024-03-11","cited_by_count":3}],"next_cursor":null}