{"list":"other","total":97,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"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":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"2305.09617","title":"Towards Expert-Level Medical Question Answering with Large Language Models","created":"2023-05-16","cited_by_count":384},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2301.07069","title":"Prompting Large Language Model for Machine Translation: A Case Study","created":"2023-01-17","cited_by_count":250},{"id":"2303.05398","title":"MathPrompter: Mathematical Reasoning using Large Language Models","created":"2023-03-04","cited_by_count":236},{"id":"2210.02875","title":"Binding Language Models in Symbolic Languages","created":"2022-10-06","cited_by_count":228},{"id":"2110.08387","title":"Generated Knowledge Prompting for Commonsense Reasoning","created":"2021-10-15","cited_by_count":214},{"id":"2207.08143","title":"Can large language models reason about medical questions?","created":"2022-07-17","cited_by_count":194},{"id":"2401.04398","title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding","created":"2024-01-09","cited_by_count":188},{"id":"2301.13808","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","created":"2023-01-31","cited_by_count":178},{"id":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"id":"2302.12246","title":"Active Prompting with Chain-of-Thought for Large Language Models","created":"2023-02-23","cited_by_count":154},{"id":"1808.06752","title":"Lessons from Natural Language Inference in the Clinical Domain","created":"2018-08-21","cited_by_count":151},{"id":"2109.08535","title":"Simple Entity-Centric Questions Challenge Dense Retrievers","created":"2021-09-17","cited_by_count":140},{"id":"2305.03268","title":"Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework","created":"2023-05-05","cited_by_count":139},{"id":"2305.06599","title":"Structured Chain-of-Thought Prompting for Code Generation","created":"2023-05-11","cited_by_count":138},{"id":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123},{"id":"2305.13269","title":"Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources","created":"2023-05-22","cited_by_count":122},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107},{"id":"2010.03640","title":"Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations","created":"2020-10-07","cited_by_count":98},{"id":"2109.00904","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","created":"2021-09-02","cited_by_count":90},{"id":"2311.11829","title":"System 2 Attention (is something you might need too)","created":"2023-11-20","cited_by_count":89},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88},{"id":"2305.11255","title":"Reasoning Implicit Sentiment with Chain-of-Thought Prompting","created":"2023-05-18","cited_by_count":80},{"id":"1805.01217","title":"CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service","created":"2018-05-03","cited_by_count":73},{"id":"2311.08734","title":"Thread of Thought Unraveling Chaotic Contexts","created":"2023-11-15","cited_by_count":72},{"id":"2302.00618","title":"Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models","created":"2023-02-01","cited_by_count":61},{"id":"2308.05342","title":"Metacognitive Prompting Improves Understanding in Large Language Models","created":"2023-08-10","cited_by_count":58},{"id":"2311.09277","title":"Contrastive Chain-of-Thought Prompting","created":"2023-11-15","cited_by_count":52},{"id":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40},{"id":"2005.06376","title":"BIOMRC: A Dataset for Biomedical Machine Reading Comprehension","created":"2020-05-13","cited_by_count":35},{"id":"2309.13339","title":"Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic","created":"2023-09-23","cited_by_count":35},{"id":"1803.09720","title":"CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension","created":"2018-03-26","cited_by_count":34},{"id":"2210.16952","title":"Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning","created":"2022-10-30","cited_by_count":34},{"id":"2010.08961","title":"Rethinking Document-level Neural Machine Translation","created":"2020-10-18","cited_by_count":32},{"id":"2308.07935","title":"Transforming Sentiment Analysis in the Financial Domain with ChatGPT","created":"2023-08-13","cited_by_count":25},{"id":"2404.06001","title":"Privacy Preserving Prompt Engineering: A Survey","created":"2024-04-09","cited_by_count":25},{"id":"2304.03087","title":"Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media","created":"2023-04-06","cited_by_count":23},{"id":"2304.13911","title":"Federated Prompting and Chain-of-Thought Reasoning for Improving LLMs Answering","created":"2023-04-27","cited_by_count":14},{"id":"2110.08542","title":"Hey AI, Can You Solve Complex Tasks by Talking to Agents?","created":"2021-10-16","cited_by_count":13},{"id":"2402.18419","title":"Can GPT Improve the State of Prior Authorization via Guideline Based Automated Question Answering?","created":"2024-02-28","cited_by_count":7}],"next_cursor":null}