{"total":88,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"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":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"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":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66,"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":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","cited_by_count":57,"area":null},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"id":"2105.03659","title":"Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text","created":"2021-05-08","cited_by_count":46,"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":"2301.11333","title":"Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systems","created":"2023-01-25","cited_by_count":41,"area":null},{"id":"2304.08979","title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","created":"2023-04-18","cited_by_count":37,"area":null},{"id":"2109.06427","title":"Commonsense-Focused Dialogues for Response Generation: An Empirical Study","created":"2021-09-14","cited_by_count":30,"area":null},{"id":"2301.12307","title":"MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization","created":"2023-01-28","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":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","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":"2509.24803","title":"TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models","created":"2025-09-29","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":"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":"2409.03563","title":"100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances","created":"2024-09-05","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":"2209.11830","title":"Multiple-Choice Question Generation: Towards an Automated Assessment Framework","created":"2022-09-23","cited_by_count":23,"area":null},{"id":"2312.04333","title":"Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers","created":"2023-12-07","cited_by_count":20,"area":null},{"id":"2406.13094","title":"Exploring and Benchmarking the Planning Capabilities of Large Language Models","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2509.17995","title":"Variation in Verification: Understanding Verification Dynamics in Large Language Models","created":"2025-09-22","cited_by_count":19,"area":null},{"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":"2311.05419","title":"Mirror: A Universal Framework for Various Information Extraction Tasks","created":"2023-11-09","cited_by_count":12,"area":null},{"id":"2210.06104","title":"EduQG: A Multi-format Multiple Choice Dataset for the Educational Domain","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2301.05948","title":"tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation","created":"2023-01-14","cited_by_count":11,"area":null},{"id":"2306.08997","title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models","created":"2023-06-15","cited_by_count":10,"area":null},{"id":"2403.10351","title":"TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2502.09642","title":"Krutrim LLM: Multilingual Foundational Model for over a Billion People","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2205.00274","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","created":"2022-04-30","cited_by_count":9,"area":null},{"id":"2211.16220","title":"Which Shortcut Solution Do Question Answering Models Prefer to Learn?","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2502.15823","title":"InductionBench: LLMs Fail in the Simplest Complexity Class","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2305.06557","title":"Long-Tailed Question Answering in an Open World","created":"2023-05-11","cited_by_count":7,"area":null},{"id":"2306.13047","title":"Analysis of the Cambridge Multiple-Choice Questions Reading Dataset with a Focus on Candidate Response Distribution","created":"2023-06-22","cited_by_count":7,"area":null},{"id":"2510.05164","title":"SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2105.04201","title":"REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training","created":"2021-05-10","cited_by_count":6,"area":null},{"id":"2211.07040","title":"World Knowledge in Multiple Choice Reading Comprehension","created":"2022-11-13","cited_by_count":6,"area":null},{"id":"2410.21195","title":"Belief in the Machine: Investigating Epistemological Blind Spots of Language Models","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2409.01495","title":"The Compressor-Retriever Architecture for Language Model OS","created":"2024-09-02","cited_by_count":5,"area":null},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2105.10334","title":"Fact-driven Logical Reasoning for Machine Reading Comprehension","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2307.01076","title":"Analyzing Multiple-Choice Reading and Listening Comprehension Tests","created":"2023-07-03","cited_by_count":4,"area":null},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2406.12641","title":"DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2610.02076","title":"LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them","created":"2026-10-01","cited_by_count":4,"area":null},{"id":"2311.04554","title":"Assessing Distractors in Multiple-Choice Tests","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2403.18327","title":"$\\forall$uto$\\exists$val: Autonomous Assessment of LLMs in Formal Synthesis and Interpretation Tasks","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2410.09675","title":"COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2506.00773","title":"Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2509.08960","title":"BRoverbs -- Measuring how much LLMs understand Portuguese proverbs","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2605.12446","title":"ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2205.00047","title":"Logically Consistent Adversarial Attacks for Soft Theorem Provers","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2307.05113","title":"Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2308.00946","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions","created":"2023-08-02","cited_by_count":2,"area":null},{"id":"2312.11507","title":"Explain To Decide: A Human-Centric Review on the Role of Explainable Artificial Intelligence in AI-assisted Decision Making","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2410.13259","title":"From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2606.16151","title":"GRACE: Step-Level Benchmark for Faithful Reasoning over Context","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2402.00978","title":"An Information-Theoretic Approach to Analyze NLP Classification Tasks","created":"2024-02-01","cited_by_count":1,"area":null},{"id":"2405.04872","title":"Logical Negation Augmenting and Debiasing for Prompt-based Methods","created":"2024-05-08","cited_by_count":1,"area":null},{"id":"2502.19973","title":"Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2608.02966","title":"Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple-Choice Benchmarks","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2102.04632","title":"Statistically Profiling Biases in Natural Language Reasoning Datasets and Models","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2203.09424","title":"elBERto: Self-supervised Commonsense Learning for Question Answering","created":"2022-03-17","cited_by_count":0,"area":null},{"id":"2408.02114","title":"Recent Advances in Multi-Choice Machine Reading Comprehension: A Survey on Methods and Datasets","created":"2024-08-04","cited_by_count":0,"area":null},{"id":"2411.16985","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions (Full Thesis)","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2502.08904","title":"MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic Training","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2503.07144","title":"MRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension Benchmark","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2510.09709","title":"The Idola Tribus of AI: Large Language Models tend to perceive order where none exists","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.25908","title":"SciTrust 2.0: A Comprehensive Framework for Evaluating Trustworthiness of Large Language Models in Scientific Applications","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2602.01132","title":"Don't Judge a Book by its Cover: Testing LLMs' Robustness Under Logical Obfuscation","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.09961","title":"ViMultiChoice: Toward a Method That Gives Explanation for Multiple-Choice Reading Comprehension in Vietnamese","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.06262","title":"From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.09034","title":"The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2609.27517","title":"Not What You Meant: Can LLMs Follow a Specified Negation Semantics?","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.35793","title":"Learning from the Gap Between Pass@K and Pass@1","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.38274","title":"Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.15897","title":"Review Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}