Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.19252 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912663863296000 |
|---|---|
| author | Shi, Yingtian Yang, Jinda Wang, Yuhan Yin, Yiwen Li, Haoyu Gao, Kunyu Yu, Chun |
| author_facet | Shi, Yingtian Yang, Jinda Wang, Yuhan Yin, Yiwen Li, Haoyu Gao, Kunyu Yu, Chun |
| contents | The growing diversity of large language models (LLMs) means users often need to compare and combine outputs from different models to obtain higher-quality or more comprehensive responses. However, switching between separate interfaces and manually integrating outputs is inherently inefficient, leading to a high cognitive burden and fragmented workflows. To address this, we present LLMartini, a novel interactive system that supports seamless comparison, selection, and intuitive cross-model composition tools. The system decomposes responses into semantically aligned segments based on task-specific criteria, automatically merges consensus content, and highlights model differences through color coding while preserving unique contributions. In a user study (N=18), LLMartini significantly outperformed conventional manual methods across all measured metrics, including task completion time, cognitive load, and user satisfaction. Our work highlights the importance of human-centered design in enhancing the efficiency and creativity of multi-LLM interactions and offers practical implications for leveraging the complementary strengths of various language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19252 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLMartini: Seamless and Interactive Leveraging of Multiple LLMs through Comparison and Composition Shi, Yingtian Yang, Jinda Wang, Yuhan Yin, Yiwen Li, Haoyu Gao, Kunyu Yu, Chun Human-Computer Interaction The growing diversity of large language models (LLMs) means users often need to compare and combine outputs from different models to obtain higher-quality or more comprehensive responses. However, switching between separate interfaces and manually integrating outputs is inherently inefficient, leading to a high cognitive burden and fragmented workflows. To address this, we present LLMartini, a novel interactive system that supports seamless comparison, selection, and intuitive cross-model composition tools. The system decomposes responses into semantically aligned segments based on task-specific criteria, automatically merges consensus content, and highlights model differences through color coding while preserving unique contributions. In a user study (N=18), LLMartini significantly outperformed conventional manual methods across all measured metrics, including task completion time, cognitive load, and user satisfaction. Our work highlights the importance of human-centered design in enhancing the efficiency and creativity of multi-LLM interactions and offers practical implications for leveraging the complementary strengths of various language models. |
| title | LLMartini: Seamless and Interactive Leveraging of Multiple LLMs through Comparison and Composition |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2510.19252 |