{"total":71,"rows":[{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2305.10037","title":"Can Language Models Solve Graph Problems in Natural Language?","created":"2023-05-17","cited_by_count":252,"area":"lr"},{"id":"2210.07128","title":"Language Models of Code are Few-Shot Commonsense Learners","created":"2022-10-13","cited_by_count":160,"area":"lr"},{"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":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2103.14349","title":"DAGN: Discourse-Aware Graph Network for Logical Reasoning","created":"2021-03-26","cited_by_count":28,"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":"2210.16433","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","created":"2022-10-28","cited_by_count":24,"area":"moe"},{"id":"2301.10896","title":"Causal Reasoning of Entities and Events in Procedural Texts","created":"2023-01-26","cited_by_count":23,"area":"lr"},{"id":"2203.07264","title":"Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data","created":"2022-03-14","cited_by_count":22,"area":null},{"id":"2210.02969","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","created":"2022-10-06","cited_by_count":22,"area":null},{"id":"2110.12349","title":"Think about it! Improving defeasible reasoning by first modeling the question scenario","created":"2021-10-24","cited_by_count":20,"area":null},{"id":"2105.07571","title":"Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes","created":"2021-05-17","cited_by_count":18,"area":null},{"id":"2210.09175","title":"Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization","created":"2022-10-17","cited_by_count":15,"area":null},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2210.06277","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","created":"2022-10-12","cited_by_count":14,"area":null},{"id":"2210.08590","title":"Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective","created":"2022-10-16","cited_by_count":14,"area":"lr"},{"id":"2508.12495","title":"Mitigating Hallucinations in Large Language Models via Causal Reasoning","created":"2025-08-17","cited_by_count":13,"area":"lr"},{"id":"2104.08840","title":"On the Influence of Masking Policies in Intermediate Pre-training","created":"2021-04-18","cited_by_count":12,"area":null},{"id":"2108.12370","title":"DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning","created":"2021-08-27","cited_by_count":12,"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":"2410.10083","title":"Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?","created":"2024-10-14","cited_by_count":11,"area":null},{"id":"2105.05418","title":"Could you give me a hint? Generating inference graphs for defeasible reasoning","created":"2021-05-12","cited_by_count":10,"area":null},{"id":"2207.07568","title":"Reasoning about Actions over Visual and Linguistic Modalities: A Survey","created":"2022-07-15","cited_by_count":10,"area":null},{"id":"2510.01539","title":"Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2104.08712","title":"PaCo: Preconditions Attributed to Commonsense Knowledge","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2302.10914","title":"GLUECons: A Generic Benchmark for Learning Under Constraints","created":"2023-02-16","cited_by_count":9,"area":null},{"id":"2502.11607","title":"GraphThought: Graph Combinatorial Optimization with Thought Generation","created":"2025-02-17","cited_by_count":9,"area":"lr"},{"id":"2204.04813","title":"Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning","created":"2022-04-11","cited_by_count":8,"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":"2210.00185","title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","created":"2022-10-01","cited_by_count":8,"area":null},{"id":"2305.14603","title":"OpenPI2.0: An Improved Dataset for Entity Tracking in Texts","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2410.05565","title":"Chain and Causal Attention for Efficient Entity Tracking","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2305.13179","title":"Teaching Probabilistic Logical Reasoning to Transformers","created":"2023-05-22","cited_by_count":7,"area":"lr"},{"id":"2311.17438","title":"CLOMO: Counterfactual Logical Modification with Large Language Models","created":"2023-11-29","cited_by_count":7,"area":"lr"},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2510.21131","title":"Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2104.08765","title":"Improving Neural Model Performance through Natural Language Feedback on Their Explanations","created":"2021-04-18","cited_by_count":5,"area":"alignment"},{"id":"2208.00329","title":"PASTA: A Dataset for Modeling Participant States in Narratives","created":"2022-07-31","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":"2105.13449","title":"Relational Gating for \"What If\" Reasoning","created":"2021-05-27","cited_by_count":4,"area":null},{"id":"2205.12420","title":"Learning Action Conditions from Instructional Manuals for Instruction Understanding","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2302.06829","title":"The Role of Semantic Parsing in Understanding Procedural Text","created":"2023-02-14","cited_by_count":4,"area":null},{"id":"2503.10941","title":"Graph-Grounded LLMs: Leveraging Graphical Function Calling to Minimize LLM Hallucinations","created":"2025-03-13","cited_by_count":4,"area":"agents"},{"id":"2506.05188","title":"Counterfactual reasoning: an analysis of in-context emergence","created":"2025-06-05","cited_by_count":4,"area":"lr"},{"id":"2104.00814","title":"CURIE: An Iterative Querying Approach for Reasoning About Situations","created":"2021-04-01","cited_by_count":3,"area":null},{"id":"2106.03973","title":"Generating Hypothetical Events for Abductive Inference","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2209.07760","title":"Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios","created":"2022-09-16","cited_by_count":3,"area":"lr"},{"id":"2403.03167","title":"PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2407.20513","title":"Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2203.11187","title":"Relevant CommonSense Subgraphs for \"What if...\" Procedural Reasoning","created":"2022-03-21","cited_by_count":2,"area":"lr"},{"id":"2204.07835","title":"What If: Generating Code to Answer Simulation Questions","created":"2022-04-16","cited_by_count":2,"area":null},{"id":"2207.01450","title":"Discourse-Aware Graph Networks for Textual Logical Reasoning","created":"2022-07-04","cited_by_count":2,"area":"lr"},{"id":"2210.03029","title":"Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2212.03866","title":"Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2310.13290","title":"Interpreting Indirect Answers to Yes-No Questions in Multiple Languages","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2503.10695","title":"Introducing Verification Task of Set Consistency with Set-Consistency Energy Networks","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2206.10265","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2306.00652","title":"Explanation Graph Generation via Generative Pre-training over Synthetic Graphs","created":"2023-06-01","cited_by_count":1,"area":"lr"},{"id":"2405.20318","title":"Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2409.14880","title":"End-to-End Graph Flattening Method for Large Language Models","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2601.00743","title":"An Agentic Framework for Neuro-Symbolic Programming","created":"2026-01-02","cited_by_count":1,"area":"agents"},{"id":"2203.09424","title":"elBERto: Self-supervised Commonsense Learning for Question Answering","created":"2022-03-17","cited_by_count":0,"area":null},{"id":"2411.01807","title":"Can Language Models Enable In-Context Database?","created":"2024-11-04","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":"2606.27187","title":"HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal Models","created":"2026-06-25","cited_by_count":0,"area":"mllm"}],"next_cursor":null}