{"list":"other","total":66,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2009.12756","title":"Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval","created":"2020-09-27","cited_by_count":162},{"id":"2010.04898","title":"Open-Domain Question Answering Goes Conversational via Question Rewriting","created":"2020-10-10","cited_by_count":148},{"id":"1911.10470","title":"Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering","created":"2019-11-24","cited_by_count":147},{"id":"2204.07931","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?","created":"2022-04-17","cited_by_count":138},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132},{"id":"2203.05115","title":"Internet-augmented language models through few-shot prompting for open-domain question answering","created":"2022-03-10","cited_by_count":131},{"id":"1710.10723","title":"Simple and Effective Multi-Paragraph Reading Comprehension","created":"2017-10-29","cited_by_count":120},{"id":"2305.06984","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","created":"2023-05-11","cited_by_count":111},{"id":"2305.18201","title":"A Critical Evaluation of Evaluations for Long-form Question Answering","created":"2023-05-29","cited_by_count":111},{"id":"2204.10757","title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","created":"2022-04-22","cited_by_count":109},{"id":"2104.08455","title":"Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding","created":"2021-04-17","cited_by_count":106},{"id":"1908.08167","title":"Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering","created":"2019-08-22","cited_by_count":96},{"id":"2110.00768","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","created":"2021-10-02","cited_by_count":96},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77},{"id":"2101.00408","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","created":"2021-01-02","cited_by_count":75},{"id":"2107.06963","title":"Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features","created":"2021-07-14","cited_by_count":74},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73},{"id":"2202.07654","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","created":"2022-02-15","cited_by_count":67},{"id":"2101.00133","title":"NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned","created":"2021-01-01","cited_by_count":52},{"id":"2010.12527","title":"Answering Open-Domain Questions of Varying Reasoning Steps from Text","created":"2020-10-23","cited_by_count":43},{"id":"2110.07752","title":"Hindsight: Posterior-guided training of retrievers for improved open-ended generation","created":"2021-10-14","cited_by_count":38},{"id":"2305.16519","title":"The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering","created":"2023-05-25","cited_by_count":26},{"id":"2106.08433","title":"Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering","created":"2021-06-15","cited_by_count":2}],"next_cursor":null}