{"total":58,"rows":[{"id":"2106.15110","title":"Time-Aware Language Models as Temporal Knowledge Bases","created":"2021-06-29","cited_by_count":296,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145,"area":null},{"id":"2401.06853","title":"Large Language Models Can Learn Temporal Reasoning","created":"2024-01-12","cited_by_count":111,"area":"lr"},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2402.17834","title":"Stable LM 2 1.6B Technical Report","created":"2024-02-27","cited_by_count":90,"area":null},{"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":"2102.03315","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","created":"2021-02-05","cited_by_count":80,"area":null},{"id":"2406.11050","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners","created":"2024-06-16","cited_by_count":73,"area":"lr"},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2305.16646","title":"Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning","created":"2023-05-26","cited_by_count":45,"area":"lr"},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2202.12205","title":"Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review","created":"2022-02-24","cited_by_count":38,"area":"lr"},{"id":"2202.08772","title":"A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models","created":"2022-02-17","cited_by_count":30,"area":null},{"id":"2505.13508","title":"Time-R1: Towards Comprehensive Temporal Reasoning in LLMs","created":"2025-05-16","cited_by_count":25,"area":"lr"},{"id":"2203.11239","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","created":"2022-03-21","cited_by_count":23,"area":null},{"id":"2402.05733","title":"TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation","created":"2024-02-08","cited_by_count":23,"area":"agents"},{"id":"2107.02681","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","created":"2021-07-06","cited_by_count":22,"area":"distill"},{"id":"2203.00758","title":"There is a Time and Place for Reasoning Beyond the Image","created":"2022-03-01","cited_by_count":22,"area":null},{"id":"2305.05191","title":"COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective","created":"2023-05-09","cited_by_count":22,"area":"lr"},{"id":"2307.01972","title":"Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification","created":"2023-07-05","cited_by_count":19,"area":null},{"id":"2210.16865","title":"Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts","created":"2022-10-30","cited_by_count":18,"area":null},{"id":"2212.10467","title":"Generic Temporal Reasoning with Differential Analysis and Explanation","created":"2022-12-20","cited_by_count":18,"area":"lr"},{"id":"2404.12494","title":"BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models","created":"2024-04-18","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":"2109.10475","title":"Salience-Aware Event Chain Modeling for Narrative Understanding","created":"2021-09-22","cited_by_count":15,"area":null},{"id":"2210.04992","title":"Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction","created":"2022-10-10","cited_by_count":15,"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":"2305.14970","title":"Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning","created":"2023-05-24","cited_by_count":13,"area":"lr"},{"id":"2308.00002","title":"An Overview Of Temporal Commonsense Reasoning and Acquisition","created":"2023-07-28","cited_by_count":10,"area":"lr"},{"id":"2410.08133","title":"Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks","created":"2024-10-10","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":"2210.06254","title":"Zero-Shot On-the-Fly Event Schema Induction","created":"2022-10-12","cited_by_count":9,"area":null},{"id":"2203.05711","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2305.15268","title":"EvEval: A Comprehensive Evaluation of Event Semantics for Large Language Models","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2502.11269","title":"Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations","created":"2025-02-16","cited_by_count":6,"area":null},{"id":"2406.01863","title":"Towards Effective Time-Aware Language Representation: Exploring Enhanced Temporal Understanding in Language Models","created":"2024-06-04","cited_by_count":5,"area":"lr"},{"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":"2205.12420","title":"Learning Action Conditions from Instructional Manuals for Instruction Understanding","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2209.15501","title":"A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2305.16579","title":"NLP Reproducibility For All: Understanding Experiences of Beginners","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2404.01453","title":"Unveiling Divergent Inductive Biases of LLMs on Temporal Data","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2404.17513","title":"A Comprehensive Evaluation on Event Reasoning of Large Language Models","created":"2024-04-26","cited_by_count":4,"area":"lr"},{"id":"2202.00848","title":"Some Reflections on Drawing Causal Inference using Textual Data: Parallels Between Human Subjects and Organized Texts","created":"2022-02-02","cited_by_count":2,"area":null},{"id":"2202.00964","title":"What Has Been Enhanced in my Knowledge-Enhanced Language Model?","created":"2022-02-02","cited_by_count":2,"area":null},{"id":"2306.13986","title":"Large Language Models as Sous Chefs: Revising Recipes with GPT-3","created":"2023-06-24","cited_by_count":2,"area":null},{"id":"2309.11737","title":"Choice-75: A Dataset on Decision Branching in Script Learning","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2310.18364","title":"From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning","created":"2023-10-24","cited_by_count":2,"area":"lr"},{"id":"2401.00779","title":"Temporal Validity Change Prediction","created":"2024-01-01","cited_by_count":2,"area":null},{"id":"2506.05790","title":"Discrete Minds in a Continuous World: Do Language Models Know Time Passes?","created":"2025-06-06","cited_by_count":2,"area":"lr"},{"id":"2508.11163","title":"MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.17807","title":"Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark","created":"2025-09-22","cited_by_count":1,"area":"lr"},{"id":"2210.05780","title":"Cross-Lingual Speaker Identification Using Distant Supervision","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2303.15381","title":"Causal schema induction for knowledge discovery","created":"2023-03-27","cited_by_count":0,"area":null},{"id":"2505.24258","title":"FABLE: A Novel Data-Flow Analysis Benchmark on Procedural Text for Large Language Model Evaluation","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2604.24620","title":"Looking for the Bottleneck in Fine-grained Temporal Relation Classification","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.04243","title":"Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA","created":"2026-05-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}