{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unpacking-positional-encoding-in-transformers","title":"Unpacking Positional Encoding in Transformers: A Spectral Analysis of Content-Position Coupling","arxiv_id":"2505.13027","date":"2025-05-19","proceeding":null,"authors":["Zihan Gu","Han Zhang","Ruoyu Chen","Yue Hu","Hua Zhang"],"abstract":"Positional encoding (PE) is essential for enabling Transformers to model sequential structure. However, the mechanisms by which different PE schemes couple token content and positional information-and how these mechanisms influence model dynamics-remain theoretically underexplored. In this work, we present a unified framework that analyzes PE through the spectral properties of Toeplitz and related matrices derived from attention logits. We show that multiplicative content-position coupling-exemplified by Rotary Positional Encoding (RoPE) via a Hadamard product with a Toeplitz matrix-induces spectral contraction, which theoretically improves optimization stability and efficiency. Guided by this theory, we construct synthetic tasks that contrast content-position dependent and content-position independent settings, and evaluate a range of PE methods. Our experiments reveal strong alignment with theory: RoPE consistently outperforms other methods on position-sensitive tasks and induces \"single-head deposit\" patterns in early layers, indicating localized positional processing. Further analyses show that modifying the method and timing of PE coupling, such as MLA in Deepseek-V3, can effectively mitigate this concentration. These results establish explicit content-relative mixing with relative-position Toeplitz signals as a key principle for effective PE design and provide new insight into how positional structure is integrated in Transformer architectures.","url_abs":"https://arxiv.org/abs/2505.13027v1","url_pdf":"https://arxiv.org/pdf/2505.13027v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":null,"task_name":"Position"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.13027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13027"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Qihuai27/Deposit-Pattern-Research","reach":null}],"summary":{"ran_draft_wrong":5,"ran_honours":1},"by_repo_kind":{"found_in_text":{"samples":6,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2e688674c9dc7c67","entry":"generate_data","repo":"Qihuai27/Deposit-Pattern-Research","repo_kind":"found_in_text","path":"dis_gen/1_data_preparation/data-gen.py","file_url":"https://github.com/Qihuai27/Deposit-Pattern-Research/blob/HEAD/dis_gen/1_data_preparation/data-gen.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e688674c9dc7c67"}},{"code_sha256_prefix":"37c63ae82b3f2143","entry":"generate_trigger_pair","repo":"Qihuai27/Deposit-Pattern-Research","repo_kind":"found_in_text","path":"dis_gen/1_data_preparation/data-gen.py","file_url":"https://github.com/Qihuai27/Deposit-Pattern-Research/blob/HEAD/dis_gen/1_data_preparation/data-gen.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37c63ae82b3f2143"}},{"code_sha256_prefix":"a4db0bd7edafd91d","entry":"get_cosine_schedule_with_warmup","repo":"Qihuai27/Deposit-Pattern-Research","repo_kind":"found_in_text","path":"count_gen/2_models/mla.py","file_url":"https://github.com/Qihuai27/Deposit-Pattern-Research/blob/HEAD/count_gen/2_models/mla.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4db0bd7edafd91d"}},{"code_sha256_prefix":"046a90108a58984c","entry":"load_dataset","repo":"Qihuai27/Deposit-Pattern-Research","repo_kind":"found_in_text","path":"count_gen/2_models/mla.py","file_url":"https://github.com/Qihuai27/Deposit-Pattern-Research/blob/HEAD/count_gen/2_models/mla.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"046a90108a58984c"}},{"code_sha256_prefix":"4f79bf4713e7fbec","entry":"load_vocab","repo":"Qihuai27/Deposit-Pattern-Research","repo_kind":"found_in_text","path":"dis_gen/1_data_preparation/data-gen.py","file_url":"https://github.com/Qihuai27/Deposit-Pattern-Research/blob/HEAD/dis_gen/1_data_preparation/data-gen.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f79bf4713e7fbec"}},{"code_sha256_prefix":"f7002b57212e6f6f","entry":"train","repo":"Qihuai27/Deposit-Pattern-Research","repo_kind":"found_in_text","path":"count_gen/2_models/mla.py","file_url":"https://github.com/Qihuai27/Deposit-Pattern-Research/blob/HEAD/count_gen/2_models/mla.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7002b57212e6f6f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}