Lost in the Middle at Birth: An Exact Theory of Transformer Position Bias

TL;DR

This paper reveals that the U-shaped performance bias in transformer models exists inherently at initialization due to geometric properties of the architecture, independent of training or positional encoding methods.

Contribution

It provides an exact theoretical model explaining the origin of the middle-context retrieval bias as an inherent architectural property of causal decoders with residual connections.

Findings

U-shape bias appears at initialization, before training.

The bias persists regardless of positional encoding methods like RoPE.

Empirical validation on untrained models confirms the theoretical predictions.

Abstract

The ``Lost in the Middle'' phenomenon -- a U-shaped performance curve where LLMs retrieve well from the beginning and end of a context but fail in the middle -- is widely attributed to learned Softmax artifacts or the distance-decay of positional encodings like RoPE. This paper makes a single, precise claim: \emph{the U-shape is already present at initialization, before any training or positional encoding takes effect.} It is an inherent geometric property of the causal decoder with residual connections. We model multi-layer causal attention as iterated powers of the Ces\`{a}ro matrix and derive the exact closed-form influence density in the continuous limit. Causal masking forces a logarithmic divergence of gradient influence at the start of the prompt (the Primacy Tail), while residual connections create an isolated $\mathcal{O}(1)$ anchor at the final token (the Recency Delta). Between these extremes lies a factorial dead zone of order $\mathcal{O}(1/(H{-}1)!)$, where $H$ is the network depth, making middle-context retrieval and training structurally hostile. We validate empirically that untrained Qwen2 and GPT-2 architectures exhibit this U-shape at Step~0, and that it is identical with or without RoPE. Comparing initialized and pretrained networks, we show that standard training does not overcome the topological valley, confirming that the U-shape persists as an architectural baseline under standard pretraining objectives. We do not claim that this bias is insurmountable, nor that interventions such as RoPE modifications are useless. We establish what the baseline is and where it comes from, so that future efforts to overcome it can be precisely targeted.