{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688},{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"2309.03883","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","created":"2023-09-07","cited_by_count":376},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1906.04908","title":"SPoC: Search-based Pseudocode to Code","created":"2019-06-12","cited_by_count":176},{"id":"1601.01280","title":"Language to Logical Form with Neural Attention","created":"2016-01-06","cited_by_count":158},{"id":"2303.06689","title":"Self-planning Code Generation with Large Language Models","created":"2023-03-12","cited_by_count":124},{"id":"2202.12172","title":"Overcoming a Theoretical Limitation of Self-Attention","created":"2022-02-24","cited_by_count":113},{"id":"2305.04087","title":"Self-Edit: Fault-Aware Code Editor for Code Generation","created":"2023-05-06","cited_by_count":111},{"id":"1808.09588","title":"Mapping Language to Code in Programmatic Context","created":"2018-08-29","cited_by_count":104},{"id":"1902.02181","title":"Attention in Natural Language Processing","created":"2019-02-04","cited_by_count":101},{"id":"2210.15157","title":"Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language","created":"2022-10-27","cited_by_count":82},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79},{"id":"1909.11218","title":"Attention Interpretability Across NLP Tasks","created":"2019-09-24","cited_by_count":71},{"id":"2310.08992","title":"CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules","created":"2023-10-13","cited_by_count":58},{"id":"2206.07585","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","created":"2022-06-15","cited_by_count":54},{"id":"2202.06840","title":"What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code","created":"2022-02-14","cited_by_count":50},{"id":"2309.07098","title":"Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding","created":"2023-09-13","cited_by_count":42},{"id":"2110.08294","title":"Coherence boosting: When your pretrained language model is not paying enough attention","created":"2021-10-15","cited_by_count":38},{"id":"2201.01549","title":"SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations","created":"2022-01-05","cited_by_count":36},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33},{"id":"2305.01628","title":"The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers","created":"2023-05-02","cited_by_count":29},{"id":"2307.03214","title":"PREADD: Prefix-Adaptive Decoding for Controlled Text Generation","created":"2023-07-06","cited_by_count":29},{"id":"2305.07372","title":"Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations","created":"2023-05-12","cited_by_count":19},{"id":"2302.09587","title":"On the Reliability and Explainability of Language Models for Program Generation","created":"2023-02-19","cited_by_count":17},{"id":"2308.09138","title":"Semantic Consistency for Assuring Reliability of Large Language Models","created":"2023-08-17","cited_by_count":15},{"id":"2306.01220","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","created":"2023-06-02","cited_by_count":14},{"id":"2402.07304","title":"Insights into Natural Language Database Query Errors: From Attention Misalignment to User Handling Strategies","created":"2024-02-11","cited_by_count":12},{"id":"1910.02555","title":"Domain Differential Adaptation for Neural Machine Translation","created":"2019-10-07","cited_by_count":10},{"id":"2207.08466","title":"What does Transformer learn about source code?","created":"2022-07-18","cited_by_count":9},{"id":"2305.14771","title":"David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs","created":"2023-05-24","cited_by_count":6},{"id":"2405.02355","title":"CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation","created":"2024-05-03","cited_by_count":4}],"next_cursor":null}