Metraipolis › archive › dc_2ebe9fc01349
MIS-Bench: Benchmarking Multimodal LLMs for Psychotherapeutic Interpersonal Skills Assessment — arXiv:2609.22778
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22778
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:37.878Z
- SHA-256 of the archived text
9817bfdf9aa3e6337a8749e8f88791f88310c1f2cbb7341d945361cb1ee1711b- Stable URL of this page
https://metraipolis.com/documento/dc_2ebe9fc01349
How to cite
MIS-Bench: Benchmarking Multimodal LLMs for Psychotherapeutic Interpersonal Skills Assessment — arXiv:2609.22778 — arXiv (en), https://arxiv.org/abs/2609.22778 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ebe9fc01349 (Metraipolis archive dc_2ebe9fc01349, sha256 9817bfdf9aa3e6337a8749e8f88791f88310c1f2cbb7341d945361cb1ee1711b)
BibTeX
@misc{dc2ebe9fc01349,
title = {MIS-Bench: Benchmarking Multimodal LLMs for Psychotherapeutic Interpersonal Skills Assessment — arXiv:2609.22778},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22778},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ebe9fc01349; sha256 9817bfdf9aa3e6337a8749e8f88791f88310c1f2cbb7341d945361cb1ee1711b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22778. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal large language models (MLLMs) are increasingly used as evaluators, yet their reliability in professional assessment tasks that require expert judgment remains unclear. We investigate this challenge in the context of assessing psychotherapeutic interpersonal skills and introduce MIS-Bench, a Multimodal Interpersonal Skills (MIS) benchmark comprising 996 psychotherapy response videos annotated across 8 dimensions of Facilitative Interpersonal Skills. Across 9 MLLMs with multiple modality and prompting settings, we find that current models show only modest agreement with human experts, inconsistent gains from multimodal input, and limited benefits from reasoning-based prompting. To mitigate this gap, we propose MIS-RAFT, a regression-aware fine-tuning method inspired by RAFT and tailored to fine-grained interpersonal skill scoring at one-decimal precision. MIS-RAFT addresses the mismatch between autoregressive token prediction and scalar-valued expert assessment, significantly improving agreement with human ratings. Overall, MIS-Bench reveals a clear gap between general multimodal capability and expert-level interpersonal judgment, while MIS-RAFT offers a promising path toward more reliable model-based assessment. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.22778 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:48:44.956Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).