{"total":18,"rows":[{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2403.09606","title":"Large Language Models and Causal Inference in Collaboration: A Survey","created":"2024-03-14","cited_by_count":26,"area":null},{"id":"2410.15319","title":"Causality for Large Language Models","created":"2024-10-20","cited_by_count":25,"area":null},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","cited_by_count":18,"area":null},{"id":"2305.11790","title":"Prompting with Pseudo-Code Instructions","created":"2023-05-19","cited_by_count":14,"area":null},{"id":"2406.15823","title":"CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans","created":"2024-06-22","cited_by_count":11,"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":"2304.13250","title":"Exploring the Curious Case of Code Prompts","created":"2023-04-26","cited_by_count":6,"area":null},{"id":"2508.01300","title":"How Far Are LLMs from Symbolic Planners? An NLP-Based Perspective","created":"2025-08-02","cited_by_count":6,"area":null},{"id":"2311.09601","title":"Code Models are Zero-shot Precondition Reasoners","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2406.18449","title":"Cascading Large Language Models for Salient Event Graph Generation","created":"2024-06-26","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":"2306.13986","title":"Large Language Models as Sous Chefs: Revising Recipes with GPT-3","created":"2023-06-24","cited_by_count":2,"area":null},{"id":"2309.11737","title":"Choice-75: A Dataset on Decision Branching in Script Learning","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2403.00990","title":"Formulation Comparison for Timeline Construction using LLMs","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2311.15964","title":"Efficient Pre-training for Localized Instruction Generation of Videos","created":"2023-11-27","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}],"next_cursor":null}