{"list":"other","total":61,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"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":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"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":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"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":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"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":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2003.02320","title":"Knowledge Graphs","created":"2020-03-04","cited_by_count":621},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2301.07597","title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection","created":"2023-01-18","cited_by_count":481},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329},{"id":"2010.01057","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","created":"2020-10-02","cited_by_count":326},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208},{"id":"1506.08909","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","created":"2015-06-30","cited_by_count":172},{"id":"1803.08035","title":"Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs","created":"2018-03-21","cited_by_count":155},{"id":"1611.05088","title":"Learning a Deep Embedding Model for Zero-Shot Learning","created":"2016-11-15","cited_by_count":153},{"id":"2004.04494","title":"MuTual: A Dataset for Multi-Turn Dialogue Reasoning","created":"2020-04-09","cited_by_count":115},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111},{"id":"2207.00747","title":"Rationale-Augmented Ensembles in Language Models","created":"2022-07-02","cited_by_count":111},{"id":"2110.07298","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","created":"2021-10-14","cited_by_count":104},{"id":"1612.01627","title":"Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots","created":"2016-12-06","cited_by_count":103},{"id":"2010.05006","title":"Automated Concatenation of Embeddings for Structured Prediction","created":"2020-10-10","cited_by_count":86},{"id":"2009.06504","title":"Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue","created":"2020-09-14","cited_by_count":26},{"id":"2210.06277","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","created":"2022-10-12","cited_by_count":14},{"id":"2204.08152","title":"Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling","created":"2022-04-18","cited_by_count":7}],"next_cursor":null}