{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"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":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"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":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2009.03393","title":"Generative Language Modeling for Automated Theorem Proving","created":"2020-09-07","cited_by_count":388},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"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":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"2004.05483","title":"Unsupervised Commonsense Question Answering with Self-Talk","created":"2020-04-11","cited_by_count":161},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"1810.08575","title":"Supervising strong learners by amplifying weak experts","created":"2018-10-19","cited_by_count":145},{"id":"2002.09758","title":"Unsupervised Question Decomposition for Question Answering","created":"2020-02-22","cited_by_count":118},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"1511.06279","title":"Neural Programmer-Interpreters","created":"2015-11-19","cited_by_count":101},{"id":"1705.08417","title":"Reinforcement Learning with a Corrupted Reward Channel","created":"2017-05-23","cited_by_count":70},{"id":"1901.03559","title":"An investigation of model-free planning","created":"2019-01-11","cited_by_count":66},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49},{"id":"2009.14786","title":"Measuring Systematic Generalization in Neural Proof Generation with Transformers","created":"2020-09-30","cited_by_count":43},{"id":"1704.06611","title":"Making Neural Programming Architectures Generalize via Recursion","created":"2017-04-21","cited_by_count":35},{"id":"1711.05240","title":"Weakly-supervised Semantic Parsing with Abstract Examples","created":"2017-11-14","cited_by_count":13},{"id":"2011.08827","title":"Avoiding Tampering Incentives in Deep RL via Decoupled Approval","created":"2020-11-17","cited_by_count":12},{"id":"2011.08820","title":"REALab: An Embedded Perspective on Tampering","created":"2020-11-17","cited_by_count":8}],"next_cursor":null}