2 papers
cs.CL2026
Lost in Compaction: Evaluating Side-Constraint Loss under Context Compaction
Zhiqi Wang, Yichi Zhang, Dongwon Lee +1
When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We identify a class of user-issued instructions, Session Constraints (SCs),…
cs.CR2026
HijackKV: New Threat in Position-Independent KV Cache Reuse
Yichi Zhang, Zhiqi Wang, Huan Zhang +1
Key-Value (KV) cache reduces inference latency in large language models (LLMs). Traditional prefix-based reuse has low cache hit rates across inference requests because it requires…