{"id":"show-or-tell","title":"Show or Tell? Modeling the evolution of request-making in Human-LLM conversations","authors":[{"given":"Shengqi","family":"Zhu"},{"given":"Jeffrey M.","family":"Rzeszotarski"},{"given":"David","family":"Mimno"}],"first_public":"2025-08-02","date_note":"First arXiv version.","date_source":"https://arxiv.org/abs/2508.01213","year":2026,"venue":"Findings of EACL 2026","paper_url":"https://aclanthology.org/2026.findings-eacl.265/","arxiv":"2508.01213","category":"behavior","relationship":"uses","dataset_version":"211,414 English request-making first turns from 18,964 inferred users, drawn from WildChat conversations collected between April 2023 and May 2024.","summary":"Introduces ReCCRE, which separates request content, context, assigned roles, and general expressions in user prompts. The study tracks how users phrase requests as they gain experience and over calendar time.","finding":"Users include more context in their requests over time, and individual users’ expression patterns tend to stabilize with experience.","evidence_url":"https://arxiv.org/html/2508.01213v2","evidence_note":"Sections 3–5: segmentation, filtering, and longitudinal analyses.","bibtex_key":"showortell2025","record_url":"https://yuntiandeng.com/wildchat/papers/show-or-tell/","relationship_label":"Uses WildChat","citation_title":"Show or Tell? Modeling the evolution of request-making in Human-LLM conversations","citation_type":"paper-conference","bibtex_type":"inproceedings","citation_url":"https://aclanthology.org/2026.findings-eacl.265/","citation_year":2026,"citation_note":"Findings of EACL 2026 proceedings paper.","doi":"10.18653/v1/2026.findings-eacl.265","container_title":"Findings of the Association for Computational Linguistics: EACL 2026","pages":"5023–5034","publisher":"Association for Computational Linguistics"}