Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models
arXiv:2609.22101v1 Announce Type: new Abstract: Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusable context is added. We formulate this phenomenon, which we call context poisoning, as extreme-valu…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-22 04:00 · arXiv cs.CL
Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models