{"list":"other","total":58,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"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":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"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":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"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":"2309.03882","title":"Large Language Models Are Not Robust Multiple Choice Selectors","created":"2023-09-07","cited_by_count":486},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233},{"id":"2210.13312","title":"Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs","created":"2022-10-24","cited_by_count":220},{"id":"2010.12884","title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints","created":"2020-10-24","cited_by_count":149},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83},{"id":"2506.21506","title":"Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge","created":"2025-06-26","cited_by_count":76},{"id":"2402.13904","title":"Calibrating Large Language Models with Sample Consistency","created":"2024-02-21","cited_by_count":73},{"id":"2409.19817","title":"Calibrating Language Models with Adaptive Temperature Scaling","created":"2024-09-29","cited_by_count":58},{"id":"2305.19555","title":"Large Language Models Are Not Strong Abstract Reasoners","created":"2023-05-31","cited_by_count":53},{"id":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38},{"id":"2407.01437","title":"Needle in the Haystack for Memory Based Large Language Models","created":"2024-07-01","cited_by_count":34},{"id":"2410.15393","title":"CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges","created":"2024-10-20","cited_by_count":34},{"id":"2310.01651","title":"Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations","created":"2023-10-02","cited_by_count":25},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25},{"id":"2406.03009","title":"Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models","created":"2024-06-05","cited_by_count":20},{"id":"2405.03205","title":"Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions","created":"2024-05-06","cited_by_count":15},{"id":"2404.08382","title":"Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think","created":"2024-04-12","cited_by_count":14},{"id":"2409.18857","title":"Mitigating Selection Bias with Node Pruning and Auxiliary Options","created":"2024-09-27","cited_by_count":12},{"id":"2502.18389","title":"Monte Carlo Temperature: a robust sampling strategy for LLM's uncertainty quantification methods","created":"2025-02-25","cited_by_count":12},{"id":"2502.03358","title":"Minerva: A Programmable Memory Test Benchmark for Language Models","created":"2025-02-05","cited_by_count":9},{"id":"2403.13590","title":"Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models","created":"2024-03-20","cited_by_count":8},{"id":"2504.10045","title":"CHARM: Calibrating Reward Models With Chatbot Arena Scores","created":"2025-04-14","cited_by_count":7},{"id":"2408.04681","title":"Conversational AI Powered by Large Language Models Amplifies False Memories in Witness Interviews","created":"2024-08-08","cited_by_count":5},{"id":"2408.09150","title":"CogLM: Tracking Cognitive Development of Large Language Models","created":"2024-08-17","cited_by_count":4},{"id":"2311.04954","title":"Prompt Sketching for Large Language Models","created":"2023-11-08","cited_by_count":3}],"next_cursor":null}