{"total":193,"rows":[{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629,"area":null},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311,"area":null},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2107.05407","title":"PonderNet: Learning to Ponder","created":"2021-07-12","cited_by_count":168,"area":null},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2304.11062","title":"Scaling Transformer to 1M tokens and beyond with RMT","created":"2023-04-19","cited_by_count":98,"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":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85,"area":null},{"id":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77,"area":null},{"id":"2104.00783","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","created":"2021-04-01","cited_by_count":75,"area":null},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73,"area":null},{"id":"2102.13249","title":"Chess as a Testbed for Language Model State Tracking","created":"2021-02-26","cited_by_count":72,"area":null},{"id":"2307.08689","title":"COLLIE: Systematic Construction of Constrained Text Generation Tasks","created":"2023-07-17","cited_by_count":70,"area":null},{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69,"area":null},{"id":"2202.07654","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","created":"2022-02-15","cited_by_count":67,"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":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47,"area":null},{"id":"2205.01128","title":"Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems","created":"2022-05-02","cited_by_count":44,"area":null},{"id":"2305.02363","title":"Entity Tracking in Language Models","created":"2023-05-03","cited_by_count":44,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2310.04444","title":"What's the Magic Word? A Control Theory of LLM Prompting","created":"2023-10-02","cited_by_count":41,"area":null},{"id":"2109.02593","title":"General-Purpose Question-Answering with Macaw","created":"2021-09-06","cited_by_count":40,"area":null},{"id":"2511.02817","title":"Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities","created":"2025-11-04","cited_by_count":40,"area":null},{"id":"2402.10790","title":"In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss","created":"2024-02-16","cited_by_count":36,"area":null},{"id":"2405.02134","title":"Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection","created":"2024-05-03","cited_by_count":33,"area":null},{"id":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33,"area":null},{"id":"2107.03992","title":"A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware","created":"2021-07-08","cited_by_count":32,"area":null},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","cited_by_count":31,"area":null},{"id":"2405.21068","title":"Code Pretraining Improves Entity Tracking Abilities of Language Models","created":"2024-05-31","cited_by_count":31,"area":null},{"id":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29,"area":null},{"id":"2305.15068","title":"ToMChallenges: A Principle-Guided Dataset and Diverse Evaluation Tasks for Exploring Theory of Mind","created":"2023-05-24","cited_by_count":28,"area":null},{"id":"2109.12393","title":"Sorting through the noise: Testing robustness of information processing in pre-trained language models","created":"2021-09-25","cited_by_count":27,"area":null},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25,"area":null},{"id":"2505.00026","title":"Theory of Mind in Large Language Models: Assessment and Enhancement","created":"2025-04-26","cited_by_count":25,"area":null},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"area":null},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2406.12158","title":"LLMs Are Prone to Fallacies in Causal Inference","created":"2024-06-18","cited_by_count":23,"area":null},{"id":"2507.02782","title":"Understanding and Improving Length Generalization in Recurrent Models","created":"2025-07-03","cited_by_count":23,"area":null},{"id":"2104.07635","title":"Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2211.02069","title":"LMentry: A Language Model Benchmark of Elementary Language Tasks","created":"2022-11-03","cited_by_count":22,"area":null},{"id":"2309.03852","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","created":"2023-09-07","cited_by_count":22,"area":null},{"id":"2102.01065","title":"Do Question Answering Modeling Improvements Hold Across Benchmarks?","created":"2021-02-01","cited_by_count":20,"area":null},{"id":"2106.01074","title":"Database Reasoning Over Text","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2602.07055","title":"Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2110.02370","title":"Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning","created":"2021-10-05","cited_by_count":18,"area":null},{"id":"2112.09054","title":"Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2305.03353","title":"MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic","created":"2023-05-05","cited_by_count":18,"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":"2401.03321","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space","created":"2024-01-06","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":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","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":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2112.03204","title":"Quantifying Adaptability in Pre-trained Language Models with 500 Tasks","created":"2021-12-06","cited_by_count":13,"area":null},{"id":"2502.06049","title":"LM2: Large Memory Models","created":"2025-02-09","cited_by_count":13,"area":null},{"id":"2101.11707","title":"Knowledge-driven Natural Language Understanding of English Text and its Applications","created":"2021-01-27","cited_by_count":12,"area":null},{"id":"2501.04070","title":"More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives","created":"2025-01-07","cited_by_count":12,"area":null},{"id":"2502.15007","title":"LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2509.24552","title":"Short window attention enables long-term memorization","created":"2025-09-29","cited_by_count":11,"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":"2208.12848","title":"Coalescing Global and Local Information for Procedural Text Understanding","created":"2022-08-26","cited_by_count":10,"area":null},{"id":"2308.08147","title":"MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluation","created":"2023-08-16","cited_by_count":10,"area":null},{"id":"2309.14735","title":"Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Models","created":"2023-09-26","cited_by_count":10,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2406.19230","title":"Spiking Convolutional Neural Networks for Text Classification","created":"2024-06-27","cited_by_count":10,"area":null},{"id":"2504.00927","title":"Multi-Token Attention","created":"2025-04-01","cited_by_count":10,"area":null},{"id":"2303.11594","title":"A Review on Machine Theory of Mind","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2603.13875","title":"GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent","created":"2026-03-14","cited_by_count":9,"area":null},{"id":"2102.10952","title":"A Relational Tsetlin Machine with Applications to Natural Language Understanding","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","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":"2405.01458","title":"UQA: Corpus for Urdu Question Answering","created":"2024-05-02","cited_by_count":8,"area":null},{"id":"2408.08291","title":"The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community","created":"2024-08-15","cited_by_count":8,"area":null},{"id":"2107.01700","title":"End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline","created":"2021-07-04","cited_by_count":7,"area":null},{"id":"2108.02846","title":"Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2112.00086","title":"Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking","created":"2021-11-30","cited_by_count":7,"area":null},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","cited_by_count":7,"area":null},{"id":"2211.03358","title":"Probing neural language models for understanding of words of estimative probability","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"2212.10754","title":"CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2106.01096","title":"Learning to Rehearse in Long Sequence Memorization","created":"2021-06-02","cited_by_count":6,"area":null},{"id":"2211.07950","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2307.05454","title":"Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2410.13098","title":"A Little Human Data Goes A Long Way","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2412.15386","title":"Systematic Evaluation of Long-Context LLMs on Financial Concepts","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2510.17196","title":"Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2101.03999","title":"A Neural Question Answering System for Basic Questions about Subroutines","created":"2021-01-11","cited_by_count":5,"area":null},{"id":"2101.04921","title":"Neural Sequence-to-grid Module for Learning Symbolic Rules","created":"2021-01-13","cited_by_count":5,"area":null},{"id":"2103.00519","title":"KANDINSKYPatterns -- An experimental exploration environment for Pattern Analysis and Machine Intelligence","created":"2021-02-28","cited_by_count":5,"area":null},{"id":"2106.05830","title":"A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems","created":"2021-06-10","cited_by_count":5,"area":null},{"id":"2201.04458","title":"Diagnosing BERT with Retrieval Heuristics","created":"2022-01-12","cited_by_count":5,"area":null},{"id":"2310.07819","title":"Faithfulness Measurable Masked Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2311.09796","title":"Interpreting User Requests in the Context of Natural Language Standing Instructions","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2402.07402","title":"BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind","created":"2024-02-12","cited_by_count":5,"area":null}],"next_cursor":"100"}