Papers › Analysing The Impact of Sequence Composition on Language Model Pre-Training
Analysing The Impact of Sequence Composition on Language Model Pre-Training
Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Miłoś, Yuxiang Wu, Pasquale Minervini
Most language model pre-training frameworks concatenate multiple documents into fixed-length sequences and use causal masking to compute the likelihood of each token given its context; this strategy is widely adopted due to its simplicity and efficiency. However, to this day, the influence of the pre-training sequence composition strategy on the generalisation properties of the model remains under-explored. In this work, we find that applying causal masking can lead to the inclusion of distracting information from previous documents during pre-training, which negatively impacts the performance of the models on language modelling and downstream tasks. In intra-document causal masking, the likelihood of each token is only conditioned on the previous tokens in the same document, eliminating potential distracting information from previous documents and significantly improving performance. Furthermore, we find that concatenating related documents can reduce some potential distractions during pre-training, and our proposed efficient retrieval-based sequence construction method, BM25Chunk, can improve in-context learning (+11.6%), knowledge memorisation (+9.8%), and context utilisation (+7.2%) abilities of language models without sacrificing efficiency.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2402.13991")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2402.13991", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2402.13991")
Code
Syntology 21 code samples harvested from 1 repository linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 1 violated, 3 with no contract checked; 13 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 21 samples from 1 repository, 21 ran (8 with no instrument failure; 13 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 21 samples that ran have no recorded date.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
21 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 1 violated, 3 with no contract checked; 13 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 1 of the 21 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from yuzhaouoe/pretraining-data-packing. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 llama_modeling.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) ·
30d7eec482ebf6b1 · report
fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded, date not recorded census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket llama_modeling.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) ·
f725bc2d76076485 · report
fixture: signature q:Tensor/3/float, k:Tensor/3/float, cos:Tensor/4/float, sin:Tensor/4/float, position_ids:Tensor/2/int · returned tuple · level recorded, date not recorded 874a9519ebeb3c53 · report
fixture: signature examples:list/1/dict, max_num_fragments_in_chunk:int/0/int · returned dict · level recorded 2026-09-24 eb90b0d7f1e2c692 · report
fixture: signature cur_all_split_dirs:list/1/str · returned int · level recorded 2026-09-24 d9243c078ceacce8 · report
fixture: signature refs:list/1/dict, preds:list/1/str · returned float · level recorded 2026-09-24 efa3643614e9c5f5 · report
fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned bool · level recorded 2026-09-24 bb142953e9e84a14 · report
fixture: signature data_dir:str/0/str, batch_idx:int/0/int · returned tuple · level recorded 2026-09-24 1bc433883369de22 · report
fixture: signature chunk:list/1/int · returned tuple · level recorded 2026-09-24 da105da73281cce5 · report
fixture: signature jsonl_path:str/0/str · returned str · level recorded 2026-09-24 2a6a0d112f2ef000 · report
fixture: signature indices:ndarray/1/int, worker_info:WorkerInfo/0/? · returned tuple · level recorded 2026-09-24 813da56adc0dd787 · report
fixture: signature path:str/0/str · returned dict · level recorded 2026-09-22 ad0a5228eb3d81f4 · report
fixture: signature path:str/0/str, max_line:int/0/int · returned ndarray · level recorded 2026-09-24 11cde6e6bca04ca4 · report
fixture: signature jsonl_path:str/0/str · returned list · level recorded 2026-09-24 b678e0cd3681e4cd · report
fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24 6829ceb72569fa12 · report
fixture: signature metric_fn:callable/0/?, prediction:Tensor/1/float, ground_truths:list/1/Tensor · returned float · level recorded 2026-09-22 9afac6122e0fd74e · report
fixture: signature pred:str/0/str · returned str · level recorded 2026-09-24 137756758ba95a6a · report
fixture: signature attn:list/1/list · returned list · level recorded 2026-09-24 census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 llama_modeling.py ran · our draft was wrong fingerprinted MIT (permissive) ·
b99eea6376d1e212 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded efbd9b87adf49321 · report
fixture: signature examples:list/1/dict · returned list · level recorded 2026-09-24 b494dc24033bda53 · report
fixture: signature tokenizer:SimpleTokenizer/0/?, item:dict/0/? · returned list · level recorded 2026-09-24 92ed24e518eb48dc · report
fixture: signature data:ndarray/1/int · returned float64 · level recorded 2026-09-24 Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections