{"list":"other","total":56,"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225},{"id":"1606.05386","title":"Model-Agnostic Interpretability of Machine Learning","created":"2016-06-16","cited_by_count":219},{"id":"2010.09926","title":"Explainable Automated Fact-Checking for Public Health Claims","created":"2020-10-19","cited_by_count":211},{"id":"2005.04611","title":"How Context Affects Language Models' Factual Predictions","created":"2020-05-10","cited_by_count":181},{"id":"2106.05707","title":"FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information","created":"2021-06-10","cited_by_count":167},{"id":"2305.12744","title":"Fact-Checking Complex Claims with Program-Guided Reasoning","created":"2023-05-22","cited_by_count":146},{"id":"1908.05267","title":"Towards Debiasing Fact Verification Models","created":"2019-08-14","cited_by_count":143},{"id":"2305.16504","title":"On the Tool Manipulation Capability of Open-source Large Language Models","created":"2023-05-25","cited_by_count":122},{"id":"2010.06189","title":"X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models","created":"2020-10-13","cited_by_count":117},{"id":"2008.09036","title":"Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries","created":"2020-08-20","cited_by_count":107},{"id":"2106.09231","title":"Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases","created":"2021-06-17","cited_by_count":107},{"id":"2210.13777","title":"SciFact-Open: Towards open-domain scientific claim verification","created":"2022-10-25","cited_by_count":94},{"id":"2210.03329","title":"Calibrating Factual Knowledge in Pretrained Language Models","created":"2022-10-07","cited_by_count":92},{"id":"2106.09248","title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","created":"2021-06-17","cited_by_count":91},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66},{"id":"2004.14992","title":"How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking","created":"2020-04-30","cited_by_count":63},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50},{"id":"2206.11863","title":"CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking","created":"2022-06-06","cited_by_count":37},{"id":"2304.08979","title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","created":"2023-04-18","cited_by_count":37}],"next_cursor":null}