{"total":541,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626,"area":null},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853,"area":null},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819,"area":null},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799,"area":null},{"id":"2410.10813","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","created":"2024-10-14","cited_by_count":707,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"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":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486,"area":null},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461,"area":null},{"id":"2108.09293","title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","created":"2021-08-20","cited_by_count":431,"area":null},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383,"area":null},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323,"area":null},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316,"area":null},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"area":null},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234,"area":null},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201,"area":null},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194,"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":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175,"area":null},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172,"area":null},{"id":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159,"area":null},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151,"area":null},{"id":"2307.01379","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","created":"2023-07-03","cited_by_count":150,"area":null},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141,"area":null},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136,"area":null},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2311.07383","title":"LM-Polygraph: Uncertainty Estimation for Language Models","created":"2023-11-13","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":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2305.13626","title":"Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration","created":"2023-05-23","cited_by_count":116,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2504.05506","title":"ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering","created":"2025-04-07","cited_by_count":108,"area":null},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"area":null},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105,"area":null},{"id":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100,"area":null},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2110.00768","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","created":"2021-10-02","cited_by_count":96,"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":"2303.11315","title":"Context-faithful Prompting for Large Language Models","created":"2023-03-20","cited_by_count":80,"area":null},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"area":null},{"id":"2312.02913","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","created":"2023-12-05","cited_by_count":70,"area":null},{"id":"2112.08558","title":"CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning","created":"2021-12-16","cited_by_count":68,"area":null},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65,"area":null},{"id":"2407.00499","title":"ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees","created":"2024-06-29","cited_by_count":65,"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":"2503.13423","title":"SuperBPE: Space Travel for Language Models","created":"2025-03-17","cited_by_count":63,"area":null},{"id":"2205.09073","title":"Dialog Inpainting: Turning Documents into Dialogs","created":"2022-05-18","cited_by_count":56,"area":null},{"id":"2403.02509","title":"SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models","created":"2024-03-04","cited_by_count":56,"area":null},{"id":"2604.12946","title":"Parcae: Scaling Laws For Stable Looped Language Models","created":"2026-04-14","cited_by_count":55,"area":null},{"id":"2404.10960","title":"Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations","created":"2024-04-16","cited_by_count":54,"area":null},{"id":"2109.12595","title":"MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents","created":"2021-09-26","cited_by_count":53,"area":null},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2406.03476","title":"Does your data spark joy? Performance gains from domain upsampling at the end of training","created":"2024-06-05","cited_by_count":52,"area":null},{"id":"2206.11309","title":"GODEL: Large-Scale Pre-Training for Goal-Directed Dialog","created":"2022-06-22","cited_by_count":51,"area":null},{"id":"2310.11689","title":"Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs","created":"2023-10-18","cited_by_count":50,"area":null},{"id":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47,"area":null},{"id":"2210.08817","title":"PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance","created":"2022-10-17","cited_by_count":45,"area":null},{"id":"2402.18048","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","created":"2024-02-28","cited_by_count":45,"area":null},{"id":"2404.07947","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","created":"2024-03-15","cited_by_count":45,"area":null},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"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":"2211.12835","title":"Automatic Generation of Socratic Subquestions for Teaching Math Word Problems","created":"2022-11-23","cited_by_count":43,"area":null},{"id":"2502.17598","title":"Hallucination Detection in LLMs Using Spectral Features of Attention Maps","created":"2025-02-24","cited_by_count":43,"area":null},{"id":"2201.05176","title":"Neural Approaches to Conversational Information Retrieval","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2205.11081","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","created":"2022-05-23","cited_by_count":42,"area":null},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2204.14272","title":"End-to-end Spoken Conversational Question Answering: Task, Dataset and Model","created":"2022-04-29","cited_by_count":37,"area":null},{"id":"2212.10525","title":"SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks","created":"2022-12-20","cited_by_count":35,"area":null},{"id":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35,"area":null},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35,"area":null},{"id":"2111.11894","title":"TWEETSUMM -- A Dialog Summarization Dataset for Customer Service","created":"2021-11-23","cited_by_count":34,"area":null},{"id":"2209.06664","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","created":"2022-09-14","cited_by_count":34,"area":null},{"id":"2402.16288","title":"PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering","created":"2024-02-26","cited_by_count":34,"area":null},{"id":"2407.07064","title":"Prompting Techniques for Secure Code Generation: A Systematic Investigation","created":"2024-07-09","cited_by_count":34,"area":null},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2111.05204","title":"Reason first, then respond: Modular Generation for Knowledge-infused Dialogue","created":"2021-11-09","cited_by_count":32,"area":null},{"id":"2106.00874","title":"Conversational Question Answering: A Survey","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"area":null},{"id":"2311.01677","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","created":"2023-11-03","cited_by_count":31,"area":null},{"id":"2402.11161","title":"PEDANTS: Cheap but Effective and Interpretable Answer Equivalence","created":"2024-02-17","cited_by_count":31,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null}],"next_cursor":"100"}