{"total":252,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919,"area":"lr"},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434,"area":"lr"},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744,"area":null},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743,"area":null},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699,"area":null},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688,"area":null},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327,"area":"lr"},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"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":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221,"area":null},{"id":"2110.08387","title":"Generated Knowledge Prompting for Commonsense Reasoning","created":"2021-10-15","cited_by_count":214,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176,"area":null},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169,"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":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133,"area":null},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117,"area":"lr"},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110,"area":"lr"},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108,"area":"lr"},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105,"area":"lr"},{"id":"2404.17140","title":"Small Language Models Need Strong Verifiers to Self-Correct Reasoning","created":"2024-04-26","cited_by_count":86,"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":"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":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2208.07852","title":"Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models","created":"2022-08-16","cited_by_count":70,"area":null},{"id":"2403.20046","title":"Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning","created":"2024-03-29","cited_by_count":69,"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":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2309.15028","title":"Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding","created":"2023-09-26","cited_by_count":60,"area":"lr"},{"id":"2104.07644","title":"ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning","created":"2021-04-15","cited_by_count":58,"area":null},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","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":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56,"area":"lr"},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2402.07688","title":"CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge","created":"2024-02-12","cited_by_count":55,"area":"rag"},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"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":"2305.03695","title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements","created":"2023-05-05","cited_by_count":44,"area":null},{"id":"2210.03078","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","created":"2022-10-06","cited_by_count":43,"area":null},{"id":"2304.04748","title":"Exploring Effective Factors for Improving Visual In-Context Learning","created":"2023-04-10","cited_by_count":43,"area":null},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2401.06081","title":"Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint","created":"2024-01-11","cited_by_count":39,"area":null},{"id":"2205.12538","title":"Is a Question Decomposition Unit All We Need?","created":"2022-05-25","cited_by_count":37,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2405.01379","title":"Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving","created":"2024-05-02","cited_by_count":35,"area":null},{"id":"2405.16282","title":"Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models","created":"2024-05-25","cited_by_count":34,"area":null},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2212.09146","title":"Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model","created":"2022-12-18","cited_by_count":32,"area":"lr"},{"id":"2106.11988","title":"On the Diversity and Limits of Human Explanations","created":"2021-06-22","cited_by_count":30,"area":null},{"id":"2305.10235","title":"Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility","created":"2023-05-15","cited_by_count":30,"area":null},{"id":"2305.10263","title":"M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models","created":"2023-05-17","cited_by_count":30,"area":null},{"id":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"area":null},{"id":"2203.08480","title":"E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning","created":"2022-03-16","cited_by_count":28,"area":"lr"},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26,"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":"2304.04280","title":"FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain","created":"2023-04-09","cited_by_count":25,"area":null},{"id":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","cited_by_count":25,"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":"2305.14502","title":"RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2501.04961","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","created":"2025-01-09","cited_by_count":24,"area":null},{"id":"2112.10006","title":"Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey","created":"2021-12-18","cited_by_count":23,"area":null},{"id":"2301.10896","title":"Causal Reasoning of Entities and Events in Procedural Texts","created":"2023-01-26","cited_by_count":23,"area":"lr"},{"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":"2110.03192","title":"GNN is a Counter? Revisiting GNN for Question Answering","created":"2021-10-07","cited_by_count":21,"area":null},{"id":"2210.12261","title":"Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination","created":"2022-10-21","cited_by_count":18,"area":null},{"id":"2105.11776","title":"Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering","created":"2021-05-25","cited_by_count":17,"area":null},{"id":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2107.11879","title":"Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration","created":"2021-07-25","cited_by_count":17,"area":null},{"id":"2205.02593","title":"METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation","created":"2022-05-05","cited_by_count":17,"area":"lr"},{"id":"2211.01482","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2203.09161","title":"How Many Data Samples is an Additional Instruction Worth?","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2209.07662","title":"NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning","created":"2022-09-16","cited_by_count":16,"area":"lr"},{"id":"2504.02620","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2106.01354","title":"multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning","created":"2021-06-02","cited_by_count":15,"area":null},{"id":"2109.02905","title":"Exploiting Reasoning Chains for Multi-hop Science Question Answering","created":"2021-09-07","cited_by_count":15,"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":"2305.13016","title":"Iterative Forward Tuning Boosts In-Context Learning in Language Models","created":"2023-05-22","cited_by_count":15,"area":null},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"area":"lr"},{"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":"2210.12887","title":"Retrieval Augmentation for Commonsense Reasoning: A Unified Approach","created":"2022-10-23","cited_by_count":14,"area":"lr"},{"id":"2305.11790","title":"Prompting with Pseudo-Code Instructions","created":"2023-05-19","cited_by_count":14,"area":null},{"id":"2509.06733","title":"Reinforcement Learning Foundations for Deep Research Systems: A Survey","created":"2025-09-08","cited_by_count":14,"area":"lr"},{"id":"2110.08542","title":"Hey AI, Can You Solve Complex Tasks by Talking to Agents?","created":"2021-10-16","cited_by_count":13,"area":null}],"next_cursor":"100"}