AIBearisharXiv – CS AI · Mar 46/103
🧠
Contextual Drag: How Errors in the Context Affect LLM Reasoning
Researchers have identified 'contextual drag' - a phenomenon where large language models (LLMs) generate similar errors when failed attempts are present in their context. The study found 10-20% performance drops across 11 models on 8 reasoning tasks, with iterative self-refinement potentially leading to self-deterioration.