{"list":"other","total":74,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"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":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"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":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"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":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2311.16452","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","created":"2023-11-28","cited_by_count":329},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240},{"id":"2311.04850","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","created":"2023-11-08","cited_by_count":195},{"id":"2405.00332","title":"A Careful Examination of Large Language Model Performance on Grade School Arithmetic","created":"2024-05-01","cited_by_count":191},{"id":"2308.13387","title":"Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs","created":"2023-08-25","cited_by_count":184},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2408.08926","title":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models","created":"2024-08-15","cited_by_count":164},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160},{"id":"2203.14960","title":"Domino: Discovering Systematic Errors with Cross-Modal Embeddings","created":"2022-03-24","cited_by_count":156},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"2406.04520","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","created":"2024-06-06","cited_by_count":128},{"id":"2406.14852","title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models","created":"2024-06-21","cited_by_count":113},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105},{"id":"2203.04291","title":"Learning from Few Examples: A Summary of Approaches to Few-Shot Learning","created":"2022-03-07","cited_by_count":86},{"id":"2309.16349","title":"Human Feedback is not Gold Standard","created":"2023-09-28","cited_by_count":83},{"id":"2309.15129","title":"Evaluating Cognitive Maps and Planning in Large Language Models with CogEval","created":"2023-09-25","cited_by_count":77},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75},{"id":"2307.03025","title":"Style Over Substance: Evaluation Biases for Large Language Models","created":"2023-07-06","cited_by_count":70},{"id":"2308.00755","title":"The Bias Amplification Paradox in Text-to-Image Generation","created":"2023-08-01","cited_by_count":70},{"id":"2312.06722","title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","created":"2023-12-11","cited_by_count":69},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57},{"id":"2402.10946","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","created":"2024-02-09","cited_by_count":50},{"id":"2311.06233","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","created":"2023-11-10","cited_by_count":47},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44},{"id":"2407.08351","title":"AutoBencher: Towards Declarative Benchmark Construction","created":"2024-07-11","cited_by_count":44},{"id":"2404.06209","title":"Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models","created":"2024-04-09","cited_by_count":36},{"id":"2311.09682","title":"MacGyver: Are Large Language Models Creative Problem Solvers?","created":"2023-11-16","cited_by_count":34},{"id":"2405.14191","title":"S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models","created":"2024-05-23","cited_by_count":33},{"id":"2405.16281","title":"ConStat: Performance-Based Contamination Detection in Large Language Models","created":"2024-05-25","cited_by_count":33},{"id":"2404.02319","title":"Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization","created":"2024-04-02","cited_by_count":30},{"id":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28},{"id":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","cited_by_count":28},{"id":"2406.14449","title":"APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking","created":"2024-06-20","cited_by_count":28},{"id":"2407.13696","title":"Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench","created":"2024-07-18","cited_by_count":27},{"id":"2407.09435","title":"MUSCLE: A Model Update Strategy for Compatible LLM Evolution","created":"2024-07-12","cited_by_count":15},{"id":"2107.01057","title":"Backward-Compatible Prediction Updates: A Probabilistic Approach","created":"2021-07-02","cited_by_count":14},{"id":"2310.15511","title":"KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval","created":"2023-10-24","cited_by_count":11},{"id":"2402.02103","title":"D\\'ej\\`a Vu Memorization in Vision-Language Models","created":"2024-02-03","cited_by_count":9},{"id":"2408.11748","title":"Understanding Depth and Height Perception in Large Visual-Language Models","created":"2024-08-21","cited_by_count":8},{"id":"2407.14333","title":"Prompt Adaptation as a Dynamic Complement in Generative AI Systems","created":"2024-07-19","cited_by_count":7},{"id":"2112.10290","title":"Distributionally Robust Group Backwards Compatibility","created":"2021-12-20","cited_by_count":2},{"id":"2409.10525","title":"\"Is This It?\": Towards Ecologically Valid Benchmarks for Situated Collaboration","created":"2024-08-30","cited_by_count":2}],"next_cursor":null}