SOURCE-LINKED INTELLIGENCE

The Sirens' Song: When Proximal Background Context Overshadows Distant Evidence

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Long-context LLMs focus on retrieving distant evidence from extensive context, yet existing work has largely focused on overcoming distance alone. In this work, we identify the Proximity Trap, insufficient attention to distant evidence often arises less from distance itself than from cumulative competition with abundant, task-irrelevant proximal background. To address the Proximity Trap, we introduce LYRA (Long-context heavY-tailed Relevance Alignment), a t-distributed directional matching mechanism that reshapes the context retrieval distribution, directing more attention mass toward task-rel

Read original source ↗ Open in workspace

recordType

paper

region

Global