Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
0
VLMs that reliably refuse entirely invalid prompts systematically fall apart when unanswerable, infeasible, or unsafe sub-claims are embedded inside otherwise benign compound queries.
Seemingly benign user requests frequently clash with unstated personal constraints, yet current LLM assistants consistently fail to retrieve the implicit knowledge-base evidence required to trigger appropriate refusals.
VLMs often blunder when faced with ambiguous visual questions, but a new dataset and fine-tuning approach can teach them to strategically seek clarification or list possibilities instead of confidently guessing wrong.
