{"total":154,"rows":[{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318,"area":null},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274,"area":"agents"},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244,"area":null},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172,"area":null},{"id":"2310.06117","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","created":"2023-10-09","cited_by_count":159,"area":"lr"},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145,"area":null},{"id":"2205.11388","title":"StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models","created":"2022-05-23","cited_by_count":126,"area":null},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119,"area":null},{"id":"2401.06853","title":"Large Language Models Can Learn Temporal Reasoning","created":"2024-01-12","cited_by_count":111,"area":"lr"},{"id":"2406.09170","title":"Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning","created":"2024-06-13","cited_by_count":88,"area":"lr"},{"id":"2506.01062","title":"SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models","created":"2025-06-01","cited_by_count":75,"area":"lr"},{"id":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63,"area":null},{"id":"2404.03602","title":"Evaluating LLMs at Detecting Errors in LLM Responses","created":"2024-04-04","cited_by_count":50,"area":null},{"id":"2310.00835","title":"TRAM: Benchmarking Temporal Reasoning for Large Language Models","created":"2023-10-02","cited_by_count":40,"area":"lr"},{"id":"2306.08952","title":"Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models","created":"2023-06-15","cited_by_count":37,"area":"lr"},{"id":"2110.06884","title":"ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers","created":"2021-10-13","cited_by_count":29,"area":null},{"id":"2311.08002","title":"TempTabQA: Temporal Question Answering for Semi-Structured Tables","created":"2023-11-14","cited_by_count":27,"area":null},{"id":"2112.05785","title":"TempoQR: Temporal Question Reasoning over Knowledge Graphs","created":"2021-12-10","cited_by_count":26,"area":null},{"id":"2305.14010","title":"IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2405.08460","title":"Is Your LLM Outdated? A Deep Look at Temporal Generalization","created":"2024-05-14","cited_by_count":26,"area":null},{"id":"2402.16797","title":"Set the Clock: Temporal Alignment of Pretrained Language Models","created":"2024-02-26","cited_by_count":25,"area":null},{"id":"2404.08700","title":"DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs","created":"2024-04-10","cited_by_count":24,"area":null},{"id":"2602.13530","title":"REMem: Reasoning with Episodic Memory in Language Agent","created":"2026-02-13","cited_by_count":23,"area":null},{"id":"2402.19248","title":"Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark","created":"2024-02-29","cited_by_count":22,"area":null},{"id":"2405.18027","title":"TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2402.16568","title":"Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models","created":"2024-02-26","cited_by_count":18,"area":null},{"id":"2501.03040","title":"ChronoSense: Exploring Temporal Understanding in Large Language Models with Time Intervals of Events","created":"2025-01-06","cited_by_count":18,"area":null},{"id":"2407.03525","title":"UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization","created":"2024-07-03","cited_by_count":17,"area":null},{"id":"2412.15540","title":"MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering","created":"2024-12-20","cited_by_count":17,"area":null},{"id":"2203.04706","title":"Data Representativity for Machine Learning and AI Systems","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2310.05157","title":"MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models","created":"2023-10-08","cited_by_count":15,"area":"lr"},{"id":"2402.11034","title":"PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering","created":"2024-02-16","cited_by_count":15,"area":null},{"id":"2502.14258","title":"Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information","created":"2025-02-20","cited_by_count":15,"area":null},{"id":"2502.21024","title":"TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions","created":"2025-02-28","cited_by_count":15,"area":null},{"id":"2303.12860","title":"Salient Span Masking for Temporal Understanding","created":"2023-03-22","cited_by_count":14,"area":null},{"id":"2305.14221","title":"Question Answering as Programming for Solving Time-Sensitive Questions","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2501.13121","title":"Episodic Memories Generation and Evaluation Benchmark for Large Language Models","created":"2025-01-21","cited_by_count":14,"area":null},{"id":"2505.20243","title":"It's High Time: A Survey of Temporal Question Answering","created":"2025-05-26","cited_by_count":14,"area":null},{"id":"2402.15400","title":"Faithful Temporal Question Answering over Heterogeneous Sources","created":"2024-02-23","cited_by_count":13,"area":null},{"id":"2412.13582","title":"EvoWiki: Evaluating LLMs on Evolving Knowledge","created":"2024-12-18","cited_by_count":13,"area":null},{"id":"2503.04800","title":"HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation","created":"2025-03-03","cited_by_count":13,"area":"rag"},{"id":"2510.13590","title":"RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge","created":"2025-10-15","cited_by_count":13,"area":"rag"},{"id":"2407.14192","title":"LeKUBE: A Legal Knowledge Update BEnchmark","created":"2024-07-19","cited_by_count":12,"area":null},{"id":"2310.14709","title":"Once Upon a $\\textit{Time}$ in $\\textit{Graph}$: Relative-Time Pretraining for Complex Temporal Reasoning","created":"2023-10-23","cited_by_count":11,"area":"lr"},{"id":"2503.17073","title":"A Study into Investigating Temporal Robustness of LLMs","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2308.00002","title":"An Overview Of Temporal Commonsense Reasoning and Acquisition","created":"2023-07-28","cited_by_count":10,"area":"lr"},{"id":"2501.12774","title":"LLMs as Repositories of Factual Knowledge: Limitations and Solutions","created":"2025-01-22","cited_by_count":10,"area":null},{"id":"2506.04041","title":"LexTime: A Benchmark for Temporal Ordering of Legal Events","created":"2025-06-04","cited_by_count":10,"area":null},{"id":"2406.11830","title":"Language Modeling with Editable External Knowledge","created":"2024-06-17","cited_by_count":9,"area":"rag"},{"id":"2409.16909","title":"Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering","created":"2024-09-25","cited_by_count":9,"area":"lr"},{"id":"2406.12534","title":"Unified Active Retrieval for Retrieval Augmented Generation","created":"2024-06-18","cited_by_count":8,"area":"rag"},{"id":"2407.16030","title":"Enhancing Temporal Understanding in LLMs for Semi-structured Tables","created":"2024-07-22","cited_by_count":8,"area":"lr"},{"id":"2410.09870","title":"ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2505.19927","title":"TCP: a Benchmark for Temporal Constraint-Based Planning","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2507.13396","title":"DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning","created":"2025-07-16","cited_by_count":8,"area":"lr"},{"id":"2509.18868","title":"Memory in Large Language Models: Mechanisms, Evaluation and Evolution","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2510.01025","title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2305.15014","title":"Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic","created":"2023-05-24","cited_by_count":7,"area":"lr"},{"id":"2310.12585","title":"Time-Aware Representation Learning for Time-Sensitive Question Answering","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2401.12078","title":"Temporal Blind Spots in Large Language Models","created":"2024-01-22","cited_by_count":7,"area":null},{"id":"2510.19457","title":"MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models","created":"2025-10-22","cited_by_count":7,"area":"mllm"},{"id":"2602.04755","title":"When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2401.02212","title":"Joint Multi-Facts Reasoning Network For Complex Temporal Question Answering Over Knowledge Graph","created":"2024-01-04","cited_by_count":6,"area":null},{"id":"2406.04866","title":"ComplexTempQA:A 100m Dataset for Complex Temporal Question Answering","created":"2024-06-07","cited_by_count":6,"area":null},{"id":"2505.16088","title":"Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"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":"2510.22521","title":"Open Multimodal Retrieval-Augmented Factual Image Generation","created":"2025-10-26","cited_by_count":6,"area":"mllm"},{"id":"2601.09523","title":"TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"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":"2501.04343","title":"TimelineKGQA: A Comprehensive Question-Answer Pair Generator for Temporal Knowledge Graphs","created":"2025-01-08","cited_by_count":5,"area":null},{"id":"2502.11425","title":"Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models","created":"2025-02-17","cited_by_count":5,"area":"lr"},{"id":"2505.21115","title":"Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2507.06782","title":"Temporal Information Retrieval via Time-Specifier Model Merging","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2510.00332","title":"When Hallucination Costs Millions: Benchmarking AI Agents in High-Stakes Adversarial Financial Markets","created":"2025-09-30","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":"2503.18085","title":"Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer Approach","created":"2025-03-23","cited_by_count":4,"area":null},{"id":"2506.16444","title":"REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2507.22917","title":"Reading Between the Timelines: RAG for Answering Diachronic Questions","created":"2025-07-21","cited_by_count":4,"area":"rag"},{"id":"2205.12898","title":"Reasoning over Logically Interacted Conditions for Question Answering","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2306.12552","title":"SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning","created":"2023-06-21","cited_by_count":3,"area":"lr"},{"id":"2310.19292","title":"Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering","created":"2023-10-30","cited_by_count":3,"area":"lr"},{"id":"2406.03592","title":"Measuring Retrieval Complexity in Question Answering Systems","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2406.10885","title":"On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2407.12470","title":"Continual Learning for Temporal-Sensitive Question Answering","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2412.08985","title":"KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?","created":"2024-12-12","cited_by_count":3,"area":"rag"},{"id":"2505.01325","title":"TRAVELER: A Benchmark for Evaluating Temporal Reasoning across Vague, Implicit and Explicit References","created":"2025-05-02","cited_by_count":3,"area":"lr"},{"id":"2505.05515","title":"Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience","created":"2025-05-07","cited_by_count":3,"area":"agents"},{"id":"2505.17162","title":"DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes","created":"2025-05-22","cited_by_count":3,"area":"rag"},{"id":"2511.18931","title":"Look It Up: Analysing Internal Web Search Capabilities of Modern LLMs","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2311.09615","title":"On Retrieval Augmentation and the Limitations of Language Model Training","created":"2023-11-16","cited_by_count":2,"area":null},{"id":"2409.14065","title":"Temporally Consistent Factuality Probing for Large Language Models","created":"2024-09-21","cited_by_count":2,"area":null},{"id":"2410.10741","title":"SensorBench: Benchmarking LLMs in Coding-Based Sensor Processing","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2504.02559","title":"Leveraging LLM For Synchronizing Information Across Multilingual Tables","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2504.19472","title":"Conflicts in Texts: Data, Implications and Challenges","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2504.20610","title":"Information Retrieval in the Age of Generative AI: The RGB Model","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2505.14905","title":"Concept Incongruence: An Exploration of Time and Death in Role Playing","created":"2025-05-20","cited_by_count":2,"area":null}],"next_cursor":"100"}