Video-LLMs can be trained, via SFT or DPO on a new synthetic dataset UVQA, to refuse questions that cannot be answered from the video content, with modest cost to answerable QA performance.
Figure 14:Prompt used for Evaluation:(a) Evaluation prompt for answerable dataset, and (b) Evaluation prompt for our unanswerable dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
Video-LLMs can be trained, via SFT or DPO on a new synthetic dataset UVQA, to refuse questions that cannot be answered from the video content, with modest cost to answerable QA performance.