Before Answering: Evidence Sufficiency under Size-Matched Memory Construction
Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory. Benchmarks for this task usually create insufficient-evidence examples by deleting supporting passages. We show that this construction leaks the label through memory size: on MuSiQue,...
Joyanta J. Mondal, Md. Shifatul Ahsan Apurba, Mridul Banik et al.
· 1 citation