Attention Basin: Why Contextual Position Matters in Large Language Models
By: Zihao Yi , Delong Zeng , Zhenqing Ling and more
Potential Business Impact:
Makes AI smarter by putting important info first.
The performance of Large Language Models (LLMs) is significantly sensitive to the contextual position of information in the input. To investigate the mechanism behind this positional bias, our extensive experiments reveal a consistent phenomenon we term the attention basin: when presented with a sequence of structured items (e.g., retrieved documents or few-shot examples), models systematically assign higher attention to the items at the beginning and end of the sequence, while neglecting those in the middle. Crucially, our analysis further reveals that allocating higher attention to critical information is key to enhancing model performance. Based on these insights, we introduce Attention-Driven Reranking (AttnRank), a two-stage framework that (i) estimates a model's intrinsic positional attention preferences using a small calibration set, and (ii) reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions. AttnRank is a model-agnostic, training-free, and plug-and-play method with minimal computational overhead. Experiments on multi-hop QA and few-shot in-context learning tasks demonstrate that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures.
Similar Papers
Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing
Computation and Language
Helps computers remember more of long stories.
Positional Biases Shift as Inputs Approach Context Window Limits
Computation and Language
Makes computers remember information better, even when it's long.
A Preliminary Study on the Promises and Challenges of Native Top-$k$ Sparse Attention
Computation and Language
Makes AI understand long texts faster and better.