SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916053549842432 |
|---|---|
| author | Jung-Mok, Lee Sung-Bin, Kim Chang, Joohyun Hyun, Lee Oh, Tae-Hyun |
| author_facet | Jung-Mok, Lee Sung-Bin, Kim Chang, Joohyun Hyun, Lee Oh, Tae-Hyun |
| contents | Laughter is a complex social signal that conveys communicative intent beyond amusement. While prior work has focused on isolated laughter analysis tasks, a comprehensive understanding of laughter in real-world scenarios remains underexplored. Therefore, we introduce SMILE-Next, a dataset for real-world laughter understanding with multimodal textual representations and question-answer annotations across three tasks: laughter detection, laughter type classification, and laughter reasoning. Building upon SMILE-Next, we aim to develop a laughter-specialized large language model capable of nuanced understanding of laughter in real-world contexts. To this end, we propose two key components: laughter-specific Self-Instruct and the Mixture-of-Laugh-Experts (MoLE) framework. Laughter-specific Self-Instruct enhances generalization across tasks and domains by automatically synthesizing diverse laughter-centric instructions. MoLE introduces a task-adaptive expert routing mechanism that dynamically selects specialized experts tailored to each laughter-related task, improving task-specific performance and efficiency. Experimental results show that the combination of our proposed components substantially outperforms multimodal LLM baselines, advancing robust real-world laughter understanding. Project page is at: https://mok0102.github.io/smile-next/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28084 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter Jung-Mok, Lee Sung-Bin, Kim Chang, Joohyun Hyun, Lee Oh, Tae-Hyun Computation and Language Artificial Intelligence Laughter is a complex social signal that conveys communicative intent beyond amusement. While prior work has focused on isolated laughter analysis tasks, a comprehensive understanding of laughter in real-world scenarios remains underexplored. Therefore, we introduce SMILE-Next, a dataset for real-world laughter understanding with multimodal textual representations and question-answer annotations across three tasks: laughter detection, laughter type classification, and laughter reasoning. Building upon SMILE-Next, we aim to develop a laughter-specialized large language model capable of nuanced understanding of laughter in real-world contexts. To this end, we propose two key components: laughter-specific Self-Instruct and the Mixture-of-Laugh-Experts (MoLE) framework. Laughter-specific Self-Instruct enhances generalization across tasks and domains by automatically synthesizing diverse laughter-centric instructions. MoLE introduces a task-adaptive expert routing mechanism that dynamically selects specialized experts tailored to each laughter-related task, improving task-specific performance and efficiency. Experimental results show that the combination of our proposed components substantially outperforms multimodal LLM baselines, advancing robust real-world laughter understanding. Project page is at: https://mok0102.github.io/smile-next/. |
| title | SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.28084 |