Expired75% confidenceFactExact time
A 2023 study by Stanford University's Nelson Liu and colleagues found that when key information is placed in the middle of a long context, model performance can drop by more than 20%.
5
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Planning with Files: Solving AI Coding's "Amnesia" Problem with Three Files
bilibiliCharaplay6/7/2026
Related Claims
VerifiedStanford University's 2023 "Lost in the Middle" study (Liu et al.) showed that when key information is located in the middle section of the context, the model's retrieval accuracy drops approximately 20–30 percentage points compared to the head and tail, and this is especially significant when the context exceeds 32K tokens.84% similarUnverifiedA 2023 Stanford University study found that even the most advanced models at the time experienced a 30% to 50% drop in information-retrieval accuracy for middle segments when processing contexts exceeding 32K tokens.78% similarVerifiedA 2023 Stanford University research experiment demonstrated that when key information was placed in the middle of an input document, GPT-4's correct recall rate dropped approximately 20–30% compared to when the information was placed at the beginning or end.70% similarUnverifiedResearch indicates that when the context exceeds a certain length, the model's recall accuracy for content in the middle portion may drop below 50%.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/46529API
curl https://kongchang.com/api/v1/knowledge/claims/46529MCP
get_claim(id=46529)