Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell Article Swipe

MAKE IMPACT

Taiming Lu , Muhan Gao , Kuai Yu , Adam Byerly , Daniel Khashabi · YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2406.14673

Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while LLMs encode the position of target information, they often fail to leverage this in generating accurate responses. This reveals a disconnect between information retrieval and utilization, a "know but don't tell" phenomenon. We further analyze the relationship between extraction time and final accuracy, offering insights into the underlying mechanics of transformer models.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2406.14673

PDF

https://arxiv.org/pdf/2406.14673

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4399986568

Raw OpenAlex JSON