Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913456454631424 |
|---|---|
| author | Hua, Yilun Artzi, Yoav |
| author_facet | Hua, Yilun Artzi, Yoav |
| contents | Humans spontaneously use increasingly efficient language as interactions progress, by adapting and forming ad-hoc conventions. This phenomenon has been studied extensively using reference games, showing properties of human language that go beyond relaying intents. It remains unexplored whether multimodal large language models (MLLMs) similarly increase communication efficiency during interactions, and what mechanisms they may adopt for this purpose. We introduce ICCA, an automated framework to evaluate such conversational adaptation as an in-context behavior in MLLMs. We evaluate several state-of-the-art MLLMs, and observe that while they may understand the increasingly efficient language of their interlocutor, they do not spontaneously make their own language more efficient over time. This latter ability can only be elicited in some models (e.g., GPT-4) with heavy-handed prompting. This shows that this property of linguistic interaction does not arise from current training regimes, even though it is a common hallmark of human language. ICCA is available at https://github.com/lil-lab/ICCA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01417 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs Hua, Yilun Artzi, Yoav Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Humans spontaneously use increasingly efficient language as interactions progress, by adapting and forming ad-hoc conventions. This phenomenon has been studied extensively using reference games, showing properties of human language that go beyond relaying intents. It remains unexplored whether multimodal large language models (MLLMs) similarly increase communication efficiency during interactions, and what mechanisms they may adopt for this purpose. We introduce ICCA, an automated framework to evaluate such conversational adaptation as an in-context behavior in MLLMs. We evaluate several state-of-the-art MLLMs, and observe that while they may understand the increasingly efficient language of their interlocutor, they do not spontaneously make their own language more efficient over time. This latter ability can only be elicited in some models (e.g., GPT-4) with heavy-handed prompting. This shows that this property of linguistic interaction does not arise from current training regimes, even though it is a common hallmark of human language. ICCA is available at https://github.com/lil-lab/ICCA. |
| title | Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2408.01417 |