Xiaoxing Hu, Wenxi Yao, Chaoyuan Shi, Ziqi Ye, Xiaorong Guo, Peixuan Li, Zhuoran Sun, Ziyang Gong · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28444 · open-access PDF
Omni LLM dapat secara alami menemukan bukti audio dan visual kunci dan mengintegrasikan informasi di seluruh modalitas untuk pertimbangan audiovisual. Referensi pertimbangan audiovisual yang ada yang sebagian besar bergantung pada pertanyaan multi-pilih biasanya mencetak model hanya berdasarkan koreksi jawaban, membuatnya sulit untuk menilai apakah sebuah model benar-benar membentuk rantai pertimbangan dari bukti ke jawaban yang benar. Selain itu, pendekatan teks atau unimodal dapat memungkinkan model untuk menjawab dengan benar tanpa menganalisis bukti audiovisual yang diperlukan, melemahkan lebih lanjut keandalan referensi evaluasi.
Machine translation (Meta M2M100); the English original follows.
Omni LLMs can naturally locate key audio and visual evidence and integrate information across modalities for audiovisual reasoning. Existing audio-visual reasoning benchmarks that mainly rely on multiple-choice questions usually score models solely based on answer correctness, making it difficult to assess whether a model truly forms a reasoning chain from evidence to the correct answer. In addition, textual or unimodal shortcuts may allow models to answer correctly without analyzing the necessary audio-visual evidence, further weakening the reliability of evaluation benchmarks. To address the
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28444, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange