{"total":123,"rows":[{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699,"area":null},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553,"area":"mechinterp"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2106.15110","title":"Time-Aware Language Models as Temporal Knowledge Bases","created":"2021-06-29","cited_by_count":296,"area":null},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176,"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":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2212.10535","title":"A Survey of Deep Learning for Mathematical Reasoning","created":"2022-12-20","cited_by_count":124,"area":"lr"},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115,"area":"mechinterp"},{"id":"2401.06853","title":"Large Language Models Can Learn Temporal Reasoning","created":"2024-01-12","cited_by_count":111,"area":"lr"},{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92,"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":"2305.13040","title":"SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents","created":"2023-05-22","cited_by_count":71,"area":"agents"},{"id":"2404.15522","title":"LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models","created":"2024-04-23","cited_by_count":68,"area":"lr"},{"id":"2303.16421","title":"ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models","created":"2023-03-29","cited_by_count":63,"area":null},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59,"area":null},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"area":null},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57,"area":null},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57,"area":"lr"},{"id":"2106.04571","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","created":"2021-06-08","cited_by_count":55,"area":null},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"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":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"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":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2310.00835","title":"TRAM: Benchmarking Temporal Reasoning for Large Language Models","created":"2023-10-02","cited_by_count":40,"area":"lr"},{"id":"2201.12438","title":"Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey","created":"2022-01-28","cited_by_count":38,"area":null},{"id":"2104.08161","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2104.08350","title":"ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning","created":"2021-04-16","cited_by_count":30,"area":null},{"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":"2103.14349","title":"DAGN: Discourse-Aware Graph Network for Logical Reasoning","created":"2021-03-26","cited_by_count":28,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2311.08398","title":"Are Large Language Models Temporally Grounded?","created":"2023-11-14","cited_by_count":27,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2101.12175","title":"LOME: Large Ontology Multilingual Extraction","created":"2021-01-28","cited_by_count":23,"area":null},{"id":"2402.11100","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","created":"2024-02-16","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":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","cited_by_count":21,"area":"alignment"},{"id":"2109.04947","title":"Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding","created":"2021-09-10","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":"2407.03525","title":"UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization","created":"2024-07-03","cited_by_count":17,"area":null},{"id":"2110.01113","title":"Probing Language Models for Understanding of Temporal Expressions","created":"2021-10-03","cited_by_count":16,"area":null},{"id":"2205.01898","title":"Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts","created":"2022-05-04","cited_by_count":15,"area":null},{"id":"2210.07471","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","created":"2022-10-14","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":"2305.11790","title":"Prompting with Pseudo-Code Instructions","created":"2023-05-19","cited_by_count":14,"area":null},{"id":"2201.00136","title":"Zero-shot Commonsense Question Answering with Cloze Translation and Consistency Optimization","created":"2022-01-01","cited_by_count":13,"area":null},{"id":"2210.17517","title":"Lila: A Unified Benchmark for Mathematical Reasoning","created":"2022-10-31","cited_by_count":13,"area":"lr"},{"id":"2310.15415","title":"Mind the Gap Between Conversations for Improved Long-Term Dialogue Generation","created":"2023-10-24","cited_by_count":13,"area":null},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","cited_by_count":11,"area":null},{"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":"2506.04041","title":"LexTime: A Benchmark for Temporal Ordering of Legal Events","created":"2025-06-04","cited_by_count":10,"area":null},{"id":"2104.10193","title":"Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks","created":"2021-04-20","cited_by_count":9,"area":null},{"id":"2503.17755","title":"Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes","created":"2025-03-22","cited_by_count":9,"area":null},{"id":"2205.07455","title":"Reasoning about Procedures with Natural Language Processing: A Tutorial","created":"2022-05-16","cited_by_count":8,"area":null},{"id":"2310.15239","title":"CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks","created":"2023-10-23","cited_by_count":8,"area":"lr"},{"id":"2407.11638","title":"A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting","created":"2024-07-16","cited_by_count":8,"area":"lr"},{"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":"2506.03984","title":"Around the World in 24 Hours: Probing LLM Knowledge of Time and Place","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2305.05936","title":"Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering","created":"2023-05-10","cited_by_count":6,"area":null},{"id":"2305.06087","title":"A Glimpse in ChatGPT Capabilities and its impact for AI research","created":"2023-05-10","cited_by_count":6,"area":null},{"id":"2505.15323","title":"Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2103.10387","title":"Decomposing and Recomposing Event Structure","created":"2021-03-18","cited_by_count":5,"area":null},{"id":"2109.04922","title":"Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers","created":"2021-09-10","cited_by_count":5,"area":null},{"id":"2208.08241","title":"ILLUME: Rationalizing Vision-Language Models through Human Interactions","created":"2022-08-17","cited_by_count":5,"area":"mllm"},{"id":"2208.09012","title":"A Kind Introduction to Lexical and Grammatical Aspect, with a Survey of Computational Approaches","created":"2022-08-18","cited_by_count":5,"area":null},{"id":"2301.04643","title":"tieval: An Evaluation Framework for Temporal Information Extraction Systems","created":"2023-01-11","cited_by_count":5,"area":null},{"id":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","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":"2505.17572","title":"USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2601.13206","title":"Real-Time Deadlines Reveal Fragile Temporal Adaptation in LLM Strategic Dialogues","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2108.04674","title":"Natural Language Processing with Commonsense Knowledge: A Survey","created":"2021-08-10","cited_by_count":4,"area":null},{"id":"2309.04635","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","created":"2023-09-08","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":"2408.04388","title":"MM-Forecast: A Multimodal Approach to Temporal Event Forecasting with Large Language Models","created":"2024-08-08","cited_by_count":4,"area":null},{"id":"2212.03747","title":"Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2305.11826","title":"ReTAG: Reasoning Aware Table to Analytic Text Generation","created":"2023-05-19","cited_by_count":3,"area":null},{"id":"2305.17491","title":"FERMAT: An Alternative to Accuracy for Numerical Reasoning","created":"2023-05-27","cited_by_count":3,"area":"lr"},{"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":"2312.12853","title":"CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models","created":"2023-12-20","cited_by_count":3,"area":"lr"},{"id":"2508.19988","title":"AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2305.14569","title":"Few-shot Unified Question Answering: Tuning Models or Prompts?","created":"2023-05-23","cited_by_count":2,"area":"lr"},{"id":"2310.10981","title":"Instructive Dialogue Summarization with Query Aggregations","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2312.10253","title":"Catwalk: A Unified Language Model Evaluation Framework for Many Datasets","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2401.00779","title":"Temporal Validity Change Prediction","created":"2024-01-01","cited_by_count":2,"area":null},{"id":"2403.00990","title":"Formulation Comparison for Timeline Construction using LLMs","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2404.11978","title":"EVIT: Event-Oriented Instruction Tuning for Event Reasoning","created":"2024-04-18","cited_by_count":2,"area":"lr"},{"id":"2410.13662","title":"ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about Actions","created":"2024-10-17","cited_by_count":2,"area":null}],"next_cursor":"100"}