{"total":112,"rows":[{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128,"area":null},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2311.18760","title":"TaskBench: Benchmarking Large Language Models for Task Automation","created":"2023-11-30","cited_by_count":144,"area":null},{"id":"2309.17428","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","created":"2023-09-29","cited_by_count":129,"area":null},{"id":"2503.01875","title":"Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement","created":"2025-02-26","cited_by_count":82,"area":null},{"id":"2406.12036","title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","created":"2024-06-17","cited_by_count":70,"area":null},{"id":"2407.20183","title":"MindSearch: Mimicking Human Minds Elicits Deep AI Searcher","created":"2024-07-29","cited_by_count":66,"area":null},{"id":"2406.02888","title":"HYDRA: Model Factorization Framework for Black-Box LLM Personalization","created":"2024-06-05","cited_by_count":60,"area":null},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54,"area":null},{"id":"2408.01875","title":"Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval","created":"2024-08-03","cited_by_count":52,"area":null},{"id":"2407.00379","title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","created":"2024-06-29","cited_by_count":49,"area":null},{"id":"2311.10775","title":"ToolTalk: Evaluating Tool-Usage in a Conversational Setting","created":"2023-11-15","cited_by_count":45,"area":null},{"id":"2406.03712","title":"A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions","created":"2024-06-06","cited_by_count":34,"area":null},{"id":"2601.21123","title":"CUA-Skill: Develop Skills for Computer Using Agent","created":"2026-01-28","cited_by_count":33,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2404.15500","title":"GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2309.08872","title":"PDFTriage: Question Answering over Long, Structured Documents","created":"2023-09-16","cited_by_count":29,"area":null},{"id":"2406.07815","title":"Are Large Language Models Good Statisticians?","created":"2024-06-12","cited_by_count":27,"area":null},{"id":"2406.20015","title":"ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models","created":"2024-06-28","cited_by_count":25,"area":null},{"id":"2404.18211","title":"A survey of dynamic graph neural networks","created":"2024-04-28","cited_by_count":24,"area":null},{"id":"2410.19743","title":"AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction","created":"2024-10-10","cited_by_count":24,"area":null},{"id":"2410.16708","title":"Atomic Fact Decomposition Helps Attributed Question Answering","created":"2024-10-22","cited_by_count":21,"area":null},{"id":"2411.10478","title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","created":"2024-11-11","cited_by_count":19,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2406.00380","title":"HonestLLM: Toward an Honest and Helpful Large Language Model","created":"2024-06-01","cited_by_count":18,"area":null},{"id":"2404.14809","title":"A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications","created":"2024-04-23","cited_by_count":17,"area":null},{"id":"2410.11710","title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","created":"2024-10-15","cited_by_count":17,"area":null},{"id":"2502.06710","title":"Learning Musical Representations for Music Performance Question Answering","created":"2025-02-10","cited_by_count":17,"area":null},{"id":"2507.03253","title":"RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs","created":"2025-07-04","cited_by_count":17,"area":null},{"id":"2403.12415","title":"VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation","created":"2024-03-19","cited_by_count":14,"area":null},{"id":"2410.13153","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2411.16313","title":"CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning","created":"2024-11-25","cited_by_count":14,"area":null},{"id":"2311.07715","title":"PolyIE: A Dataset of Information Extraction from Polymer Material Scientific Literature","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2508.03284","title":"ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools","created":"2025-08-05","cited_by_count":13,"area":null},{"id":"2406.10459","title":"CancerLLM: A Large Language Model in Cancer Domain","created":"2024-06-15","cited_by_count":12,"area":null},{"id":"2509.19406","title":"TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding","created":"2025-09-23","cited_by_count":12,"area":null},{"id":"2310.10760","title":"Towards reducing hallucination in extracting information from financial reports using Large Language Models","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2504.04319","title":"Geo-OLM: Enabling Sustainable Earth Observation Studies with Cost-Efficient Open Language Models & State-Driven Workflows","created":"2025-04-06","cited_by_count":11,"area":null},{"id":"2505.20903","title":"Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?","created":"2025-05-27","cited_by_count":11,"area":null},{"id":"2605.06978","title":"Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries","created":"2026-05-07","cited_by_count":11,"area":null},{"id":"2312.10321","title":"LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2504.15546","title":"A Framework for Testing and Adapting REST APIs as LLM Tools","created":"2025-04-22","cited_by_count":10,"area":null},{"id":"2509.04292","title":"Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?","created":"2025-09-04","cited_by_count":10,"area":null},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2403.12316","title":"OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2410.20749","title":"Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs","created":"2024-10-28","cited_by_count":9,"area":null},{"id":"2506.00264","title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2404.05182","title":"DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2405.01738","title":"Question Suggestion for Conversational Shopping Assistants Using Product Metadata","created":"2024-05-02","cited_by_count":8,"area":null},{"id":"2410.11772","title":"Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2411.08243","title":"Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset","created":"2024-11-12","cited_by_count":8,"area":null},{"id":"2505.18541","title":"RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrieval","created":"2025-05-24","cited_by_count":7,"area":null},{"id":"2506.08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2402.17097","title":"Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses","created":"2024-02-27","cited_by_count":6,"area":null},{"id":"2411.07264","title":"Multi-Document Financial Question Answering using LLMs","created":"2024-11-08","cited_by_count":6,"area":null},{"id":"2503.01033","title":"Variance reduction in output from generative AI","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2505.19533","title":"ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2507.13859","title":"SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection","created":"2025-07-18","cited_by_count":6,"area":null},{"id":"2404.00943","title":"Evalverse: Unified and Accessible Library for Large Language Model Evaluation","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2410.10872","title":"ToolBridge: An Open-Source Dataset to Equip LLMs with External Tool Capabilities","created":"2024-10-08","cited_by_count":5,"area":null},{"id":"2601.07506","title":"Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2409.09844","title":"A Benchmark Dataset with Larger Context for Non-Factoid Question Answering over Islamic Text","created":"2024-09-15","cited_by_count":4,"area":null},{"id":"2412.02897","title":"MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2503.05770","title":"Generative Artificial Intelligence: Evolving Technology, Growing Societal Impact, and Opportunities for Information Systems Research","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2505.13531","title":"AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2606.10388","title":"Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2608.05080","title":"Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning","created":"2026-08-05","cited_by_count":4,"area":null},{"id":"2311.09635","title":"Evaluating In-Context Learning of Libraries for Code Generation","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2311.13053","title":"Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2402.16696","title":"Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models","created":"2024-02-26","cited_by_count":3,"area":null},{"id":"2409.02370","title":"Do Large Language Models Possess Sensitive to Sentiment?","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2410.06943","title":"AutoFeedback: An LLM-based Framework for Efficient and Accurate API Request Generation","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2411.09613","title":"Task-Aligned Tool Recommendation for Large Language Models","created":"2024-11-14","cited_by_count":3,"area":null},{"id":"2505.11754","title":"Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2511.19957","title":"AppSelectBench: Application-Level Tool Selection Benchmark","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2404.11276","title":"Towards Data-Centric Automatic R&D","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2407.13343","title":"Learning-From-Mistakes Prompting for Indigenous Language Translation","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2408.05456","title":"Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation","created":"2024-08-10","cited_by_count":2,"area":null},{"id":"2409.15523","title":"SEAL: Suite for Evaluating API-use of LLMs","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2502.08905","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2506.17285","title":"A Framework for Generating Conversational Recommendation Datasets from Behavioral Interactions","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2312.05209","title":"HALO: An Ontology for Representing and Categorizing Hallucinations in Large Language Models","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2401.15724","title":"RE-GAINS & EnChAnT: Intelligent Tool Manipulation Systems For Enhanced Query Responses","created":"2024-01-28","cited_by_count":1,"area":null},{"id":"2402.14002","title":"Hallucinations or Attention Misdirection? The Path to Strategic Value Extraction in Business Using Large Language Models","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2412.02263","title":"Connecting Large Language Models with Blockchain: Advancing the Evolution of Smart Contracts from Automation to Intelligence","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2503.01131","title":"Beyond QA Pairs: Assessing Parameter-Efficient Fine-Tuning for Fact Embedding in LLMs","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2503.19584","title":"Multi-agent Application System in Office Collaboration Scenarios","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2503.21813","title":"OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2505.12058","title":"Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2505.12507","title":"Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.18425","title":"Advertising in AI systems: Society must be vigilant","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.02449","title":"IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2508.07321","title":"ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2512.02966","title":"Lumos: Let there be Language Model System Certification","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2606.12203","title":"Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2607.11079","title":"Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists","created":"2026-07-13","cited_by_count":1,"area":null}],"next_cursor":"100"}