{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"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":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"2410.05080","title":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","created":"2024-10-07","cited_by_count":235},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171},{"id":"1909.07940","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","created":"2019-09-17","cited_by_count":159},{"id":"2004.04487","title":"Injecting Numerical Reasoning Skills into Language Models","created":"2020-04-09","cited_by_count":133},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125},{"id":"2210.10634","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","created":"2022-10-12","cited_by_count":115},{"id":"2401.13835","title":"What Large Language Models Know and What People Think They Know","created":"2024-01-24","cited_by_count":110},{"id":"2308.07286","title":"The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation","created":"2023-08-14","cited_by_count":95},{"id":"2505.13259","title":"From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery","created":"2025-05-19","cited_by_count":93},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76},{"id":"2404.07544","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","created":"2024-04-11","cited_by_count":57},{"id":"2405.12856","title":"LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language","created":"2024-05-21","cited_by_count":55},{"id":"2505.13898","title":"Do Language Models Use Their Depth Efficiently?","created":"2025-05-20","cited_by_count":50},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37},{"id":"2409.14381","title":"Investigating Layer Importance in Large Language Models","created":"2024-09-22","cited_by_count":36},{"id":"2402.14547","title":"OmniPred: Language Models as Universal Regressors","created":"2024-02-22","cited_by_count":34},{"id":"2105.03311","title":"Translation Quality Assessment: A Brief Survey on Manual and Automatic Methods","created":"2021-05-05","cited_by_count":23},{"id":"2410.04691","title":"Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning","created":"2024-10-07","cited_by_count":21},{"id":"2411.14708","title":"Understanding LLM Embeddings for Regression","created":"2024-11-22","cited_by_count":19},{"id":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18},{"id":"2503.04381","title":"TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge","created":"2025-03-06","cited_by_count":17},{"id":"2311.10367","title":"Exploring the Relationship between In-Context Learning and Instruction Tuning","created":"2023-11-17","cited_by_count":14},{"id":"2403.04182","title":"Regression-aware Inference with LLMs","created":"2024-03-07","cited_by_count":14},{"id":"2506.21718","title":"Performance Prediction for Large Systems via Text-to-Text Regression","created":"2025-06-26","cited_by_count":14},{"id":"2406.02756","title":"Aligning Large Language Models via Fine-grained Supervision","created":"2024-06-04","cited_by_count":13},{"id":"2505.20538","title":"AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy","created":"2025-05-26","cited_by_count":13},{"id":"2501.19383","title":"Decoding-based Regression","created":"2025-01-31","cited_by_count":12},{"id":"2509.26476","title":"Regression Language Models for Code","created":"2025-09-30","cited_by_count":11},{"id":"2506.06657","title":"Quantile Regression with Large Language Models for Price Prediction","created":"2025-06-07","cited_by_count":10},{"id":"2412.16270","title":"MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design","created":"2024-12-20","cited_by_count":8},{"id":"2502.07193","title":"Provably Efficient Online RLHF with One-Pass Reward Modeling","created":"2025-02-11","cited_by_count":8},{"id":"2502.17657","title":"StatLLM: A Dataset for Evaluating the Performance of Large Language Models in Statistical Analysis","created":"2025-02-24","cited_by_count":8},{"id":"2602.07812","title":"LLMs Know More About Numbers than They Can Say","created":"2026-02-08","cited_by_count":7},{"id":"2603.06616","title":"RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models","created":"2026-02-20","cited_by_count":7},{"id":"2506.12713","title":"Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?","created":"2025-06-15","cited_by_count":6},{"id":"2603.02913","title":"Eliciting Numerical Predictive Distributions of LLMs Without Autoregression","created":"2026-03-03","cited_by_count":6},{"id":"2406.05326","title":"Advancing Semantic Textual Similarity Modeling: A Regression Framework with Translated ReLU and Smooth K2 Loss","created":"2024-06-08","cited_by_count":5},{"id":"2601.12152","title":"Who Owns Creativity and Who Does the Work? Trade-offs in LLM-Supported Research Ideation","created":"2026-01-17","cited_by_count":3},{"id":"2507.00439","title":"Improving the Distributional Alignment of LLMs using Supervision","created":"2025-07-01","cited_by_count":2},{"id":"2509.07309","title":"PIE: Performance Interval Estimation for Free-Form Generation Tasks","created":"2025-09-09","cited_by_count":1}],"next_cursor":null}