{"total":285,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902,"area":null},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"area":null},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699,"area":null},{"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,"area":null},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256,"area":"lr"},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243,"area":null},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203,"area":null},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203,"area":null},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192,"area":null},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2101.00774","title":"Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering","created":"2021-01-04","cited_by_count":178,"area":null},{"id":"2212.07919","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","created":"2022-12-15","cited_by_count":177,"area":"lr"},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2210.09338","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","created":"2022-10-17","cited_by_count":156,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142,"area":null},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141,"area":null},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"area":"lr"},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126,"area":null},{"id":"2311.17371","title":"Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs","created":"2023-11-29","cited_by_count":114,"area":"agents"},{"id":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100,"area":null},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2103.13009","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","created":"2021-03-24","cited_by_count":98,"area":null},{"id":"2308.04592","title":"Shepherd: A Critic for Language Model Generation","created":"2023-08-08","cited_by_count":97,"area":"lr"},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2309.04766","title":"SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning","created":"2023-09-09","cited_by_count":94,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2311.10227","title":"Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities","created":"2023-11-16","cited_by_count":89,"area":"wm"},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88,"area":"lr"},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2304.10703","title":"ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness","created":"2023-04-21","cited_by_count":77,"area":"lr"},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2310.00752","title":"TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks","created":"2023-10-01","cited_by_count":70,"area":null},{"id":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","cited_by_count":70,"area":"wm"},{"id":"2403.06412","title":"CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean","created":"2024-03-11","cited_by_count":66,"area":null},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2305.17008","title":"NormBank: A Knowledge Bank of Situational Social Norms","created":"2023-05-26","cited_by_count":60,"area":null},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59,"area":null},{"id":"2104.07644","title":"ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning","created":"2021-04-15","cited_by_count":58,"area":null},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"area":null},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","cited_by_count":57,"area":null},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57,"area":null},{"id":"2111.00607","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","created":"2021-10-31","cited_by_count":56,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53,"area":"lr"},{"id":"2311.11077","title":"Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning","created":"2023-11-18","cited_by_count":53,"area":null},{"id":"2306.05783","title":"Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation","created":"2023-06-09","cited_by_count":52,"area":null},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2105.03659","title":"Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text","created":"2021-05-08","cited_by_count":46,"area":null},{"id":"2108.00648","title":"From LSAT: The Progress and Challenges of Complex Reasoning","created":"2021-08-02","cited_by_count":43,"area":null},{"id":"2407.13998","title":"RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering","created":"2024-07-19","cited_by_count":43,"area":"rag"},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2112.03254","title":"Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention","created":"2021-12-06","cited_by_count":40,"area":null},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2407.09007","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2201.12438","title":"Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey","created":"2022-01-28","cited_by_count":38,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2405.00361","title":"AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts","created":"2024-05-01","cited_by_count":34,"area":null},{"id":"2110.08455","title":"Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey","created":"2021-10-16","cited_by_count":33,"area":null},{"id":"2402.01349","title":"LLMs May Perform MCQA by Selecting the Least Incorrect Option","created":"2024-02-02","cited_by_count":33,"area":null},{"id":"2402.01742","title":"Towards Optimizing the Costs of LLM Usage","created":"2024-01-29","cited_by_count":33,"area":null},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2309.11166","title":"Are Large Language Models Really Robust to Word-Level Perturbations?","created":"2023-09-20","cited_by_count":32,"area":"alignment"},{"id":"2411.15382","title":"On the Impact of Fine-Tuning on Chain-of-Thought Reasoning","created":"2024-11-22","cited_by_count":32,"area":"lr"},{"id":"2106.00874","title":"Conversational Question Answering: A Survey","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2104.08350","title":"ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning","created":"2021-04-16","cited_by_count":30,"area":null},{"id":"2109.06427","title":"Commonsense-Focused Dialogues for Response Generation: An Empirical Study","created":"2021-09-14","cited_by_count":30,"area":null},{"id":"2109.08406","title":"Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers","created":"2021-09-17","cited_by_count":30,"area":null},{"id":"2402.11597","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","created":"2024-02-18","cited_by_count":30,"area":null},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2102.12634","title":"Automatic Story Generation: Challenges and Attempts","created":"2021-02-25","cited_by_count":28,"area":null},{"id":"2103.14349","title":"DAGN: Discourse-Aware Graph Network for Logical Reasoning","created":"2021-03-26","cited_by_count":28,"area":null},{"id":"2310.00074","title":"SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation","created":"2023-09-29","cited_by_count":27,"area":"lr"},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2203.08512","title":"ConTinTin: Continual Learning from Task Instructions","created":"2022-03-16","cited_by_count":26,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","cited_by_count":25,"area":null}],"next_cursor":"100"}