{"total":31,"rows":[{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2305.06453","title":"Autonomous GIS: the next-generation AI-powered GIS","created":"2023-05-10","cited_by_count":53,"area":null},{"id":"2211.12835","title":"Automatic Generation of Socratic Subquestions for Teaching Math Word Problems","created":"2022-11-23","cited_by_count":43,"area":null},{"id":"2411.03766","title":"Number Cookbook: Number Understanding of Language Models and How to Improve It","created":"2024-11-06","cited_by_count":42,"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":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29,"area":null},{"id":"2212.10678","title":"Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2404.04963","title":"SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials","created":"2024-04-07","cited_by_count":20,"area":null},{"id":"2305.13954","title":"Robust Prompt Optimization for Large Language Models Against Distribution Shifts","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2401.18070","title":"Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?","created":"2024-01-31","cited_by_count":19,"area":null},{"id":"2305.03598","title":"NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports","created":"2023-05-05","cited_by_count":18,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2507.12379","title":"Probing for Arithmetic Errors in Language Models","created":"2025-07-16","cited_by_count":18,"area":null},{"id":"2404.18585","title":"FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering","created":"2024-04-29","cited_by_count":16,"area":null},{"id":"2410.13502","title":"MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2306.04347","title":"World Models for Math Story Problems","created":"2023-06-07","cited_by_count":11,"area":null},{"id":"2408.05102","title":"How Well Do LLMs Identify Cultural Unity in Diversity?","created":"2024-08-09","cited_by_count":8,"area":null},{"id":"2504.01509","title":"PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation","created":"2025-04-02","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2409.17313","title":"Navigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation","created":"2024-09-25","cited_by_count":7,"area":null},{"id":"2309.08922","title":"Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models","created":"2023-09-16","cited_by_count":6,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2305.08524","title":"Measuring Consistency in Text-based Financial Forecasting Models","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2305.08572","title":"Estimating the Causal Effects of Natural Logic Features in Neural NLI Models","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2411.19456","title":"Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability","created":"2024-11-29","cited_by_count":3,"area":null},{"id":"2502.05150","title":"CodeSCM: Causal Analysis for Multi-Modal Code Generation","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2408.14380","title":"Probing Causality Manipulation of Large Language Models","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2409.17005","title":"Models Can and Should Embrace the Communicative Nature of Human-Generated Math","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2602.17826","title":"Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2404.02622","title":"Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2405.04170","title":"D-NLP at SemEval-2024 Task 2: Evaluating Clinical Inference Capabilities of Large Language Models","created":"2024-05-07","cited_by_count":0,"area":null}],"next_cursor":null}