On the Emergence of Position Bias in Transformers

• URL: http://arxiv.org/abs/2502.01951v1
• Date: Tue, 04 Feb 2025 02:53:07 GMT
• Title: On the Emergence of Position Bias in Transformers
• Authors: Xinyi Wu, Yifei Wang, Stefanie Jegelka, Ali Jadbabaie,
• Abstract summary: This paper introduces a novel graph-theoretic framework to analyze position bias in multi-layer attention. We quantify how tokens interact with contextual information based on their sequential positions. Our framework offers a principled foundation for understanding positional biases in transformers.
• Score: 59.87743433861665
• License:
• Abstract: Recent studies have revealed various manifestations of position bias in transformer architectures, from the "lost-in-the-middle" phenomenon to attention sinks, yet a comprehensive theoretical understanding of how attention masks and positional encodings shape these biases remains elusive. This paper introduces a novel graph-theoretic framework to analyze position bias in multi-layer attention. Modeling attention masks as directed graphs, we quantify how tokens interact with contextual information based on their sequential positions. We uncover two key insights: First, causal masking inherently biases attention toward earlier positions, as tokens in deeper layers attend to increasingly more contextualized representations of earlier tokens. Second, we characterize the competing effects of the causal mask and relative positional encodings, such as the decay mask and rotary positional encoding (RoPE): while both mechanisms introduce distance-based decay within individual attention maps, their aggregate effect across multiple attention layers -- coupled with the causal mask -- leads to a trade-off between the long-term decay effects and the cumulative importance of early sequence positions. Through controlled numerical experiments, we not only validate our theoretical findings but also reproduce position biases observed in real-world LLMs. Our framework offers a principled foundation for understanding positional biases in transformers, shedding light on the complex interplay of attention mechanism components and guiding more informed architectural design.

Related papers

• Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs [77.66717051042032]
  Practitioners have consistently observed three puzzling phenomena in transformer-based large language models. These phenomena are characterized by certain so-called "sink tokens" receiving disproportionately high attention weights. We elucidate the mechanisms behind extreme-token phenomena.
  arXiv  Detail & Related papers  (2024-10-17T17:54:06Z)
• Benign Overfitting in Token Selection of Attention Mechanism [34.316270145027616]
  We study the training dynamics and generalization ability of the attention mechanism under classification problems with label noise. We show that, with the characterization of signal-to-noise ratio (SNR), the token selection of attention mechanism achieves benign overfitting. Our work also demonstrates an interesting delayed acquisition of generalization after an initial phase of overfitting.
  arXiv  Detail & Related papers  (2024-09-26T08:20:05Z)
• Unveiling and Controlling Anomalous Attention Distribution in Transformers [8.456319173083315]
  Waiver phenomenon allows elements to absorb excess attention without affecting their contribution to information. In specific models, due to differences in positional encoding and attention patterns, we have found that the selection of waiver elements by the model can be categorized into two methods.
  arXiv  Detail & Related papers  (2024-06-26T11:53:35Z)
• What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding [67.59552859593985]
  Graph Transformers, which incorporate self-attention and positional encoding, have emerged as a powerful architecture for various graph learning tasks. This paper introduces first theoretical investigation of a shallow Graph Transformer for semi-supervised classification.
  arXiv  Detail & Related papers  (2024-06-04T05:30:16Z)
• Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation [64.85974098314344]
  Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images. We propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism.
  arXiv  Detail & Related papers  (2023-09-23T02:40:28Z)
• Revisiting Over-smoothing in BERT from the Perspective of Graph [111.24636158179908]
  Recently over-smoothing phenomenon of Transformer-based models is observed in both vision and language fields. We find that layer normalization plays a key role in the over-smoothing issue of Transformer-based models. We consider hierarchical fusion strategies, which combine the representations from different layers adaptively to make the output more diverse.
  arXiv  Detail & Related papers  (2022-02-17T12:20:52Z)
• Ripple Attention for Visual Perception with Sub-quadratic Complexity [7.425337104538644]
  Transformer architectures are now central to modeling in natural language processing tasks. We propose ripple attention, a sub-quadratic attention mechanism for visual perception. In ripple attention, contributions of different tokens to a query are weighted with respect to their relative spatial distances in the 2D space.
  arXiv  Detail & Related papers  (2021-10-06T02:00:38Z)
• Multi-Head Attention: Collaborate Instead of Concatenate [85.71058762269374]
  We propose a collaborative multi-head attention layer that enables heads to learn shared projections. Experiments confirm that sharing key/query dimensions can be exploited in language understanding, machine translation and vision.
  arXiv  Detail & Related papers  (2020-06-29T20:28:52Z)
• Telling BERT's full story: from Local Attention to Global Aggregation [14.92157586545743]
  We take a deep look into the behavior of self-attention heads in the transformer architecture. We show that attention distributions can nevertheless provide insights into the local behavior of attention heads.
  arXiv  Detail & Related papers  (2020-04-10T01:36:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.