{"list":"other","total":90,"rows":[{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"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":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401},{"id":"2003.06713","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","created":"2020-03-14","cited_by_count":376},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364},{"id":"2304.09542","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","created":"2023-04-19","cited_by_count":360},{"id":"2305.09645","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","created":"2023-05-16","cited_by_count":343},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2306.17563","title":"Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting","created":"2023-06-30","cited_by_count":307},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285},{"id":"2310.08319","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","created":"2023-10-12","cited_by_count":272},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"2010.11784","title":"Self-Alignment Pretraining for Biomedical Entity Representations","created":"2020-10-22","cited_by_count":237},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"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":"1910.14424","title":"Multi-Stage Document Ranking with BERT","created":"2019-10-31","cited_by_count":201},{"id":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148},{"id":"2307.11019","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","created":"2023-07-20","cited_by_count":147},{"id":"2303.08559","title":"Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!","created":"2023-03-15","cited_by_count":119},{"id":"2210.10634","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","created":"2022-10-12","cited_by_count":115},{"id":"2308.07074","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","created":"2023-08-14","cited_by_count":109},{"id":"2401.02415","title":"LLaMA Pro: Progressive LLaMA with Block Expansion","created":"2024-01-04","cited_by_count":101},{"id":"1511.06114","title":"Multi-task Sequence to Sequence Learning","created":"2015-11-19","cited_by_count":94},{"id":"2305.02156","title":"Zero-Shot Listwise Document Reranking with a Large Language Model","created":"2023-05-03","cited_by_count":82},{"id":"2101.05667","title":"The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models","created":"2021-01-14","cited_by_count":81},{"id":"2403.05313","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","created":"2024-03-08","cited_by_count":75},{"id":"2301.01820","title":"InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval","created":"2023-01-04","cited_by_count":73},{"id":"2406.13542","title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","created":"2024-06-19","cited_by_count":73},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69},{"id":"2202.05144","title":"InPars: Data Augmentation for Information Retrieval using Large Language Models","created":"2022-02-10","cited_by_count":62},{"id":"2012.14610","title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","created":"2020-12-29","cited_by_count":61},{"id":"2101.00133","title":"NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned","created":"2021-01-01","cited_by_count":52},{"id":"2310.08975","title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","created":"2023-10-13","cited_by_count":44},{"id":"2310.13243","title":"Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking","created":"2023-10-20","cited_by_count":44},{"id":"2303.00807","title":"UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers","created":"2023-03-01","cited_by_count":37},{"id":"2210.13693","title":"XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing","created":"2022-10-25","cited_by_count":33},{"id":"2311.06503","title":"Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering","created":"2023-11-11","cited_by_count":29},{"id":"2406.00770","title":"Automatic Instruction Evolving for Large Language Models","created":"2024-06-02","cited_by_count":26},{"id":"2310.06504","title":"Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task","created":"2023-10-10","cited_by_count":23},{"id":"2301.11259","title":"Domain-Agnostic Molecular Generation with Chemical Feedback","created":"2023-01-26","cited_by_count":22},{"id":"2308.14436","title":"Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA","created":"2023-08-28","cited_by_count":17},{"id":"2104.14133","title":"Text-to-Text Multi-view Learning for Passage Re-ranking","created":"2021-04-29","cited_by_count":14},{"id":"2310.12426","title":"MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models","created":"2023-10-19","cited_by_count":13},{"id":"2203.12267","title":"PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation","created":"2022-03-23","cited_by_count":12},{"id":"2305.18144","title":"GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking","created":"2023-05-29","cited_by_count":11},{"id":"2402.09136","title":"DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning","created":"2024-02-14","cited_by_count":11},{"id":"2208.11508","title":"PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling","created":"2022-08-24","cited_by_count":9},{"id":"2308.14533","title":"A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER","created":"2023-08-28","cited_by_count":9},{"id":"2306.13588","title":"System-Level Natural Language Feedback","created":"2023-06-23","cited_by_count":4}],"next_cursor":null}