RESEARCHInvestigateNEXT 12 MONTHS
Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs
arXiv cs.LG — Machine Learning
Factual evidence
What the source reports
New research shows bitsandbytes post-training quantization (INT8/INT4) worsens memory retrieval degradation in LLMs over long conversations.
Open source