Paper recorded by Signals 4 on 2026-10-19 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-19 on arXiv · recorded by Signals 4 on 2026-10-20
Category: cs.CL · 自然语言处理 · first seen 2026-10-20
Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but a reader can still answer correctly from an unfaithful compression, so these metrics underestimate such loss. To bridge this gap, we introduce KEEP-Bench, a diagnostic benchmark that directly assesses compression faithfulness wit