Papers › CiteBART: Learning to Generate Citations for Local Citation Recommendation

CiteBART: Learning to Generate Citations for Local Citation Recommendation

23 Dec 2024arXiv:2412.17534archive 2025-07-28

Ege Yiğit Çelik, Selma Tekir

Local citation recommendation (LCR) suggests a set of papers for a citation placeholder within a given context. The task has evolved as generative approaches have become more promising than the traditional pre-fetch and re-rank-based state-of-the-art approaches. This paper introduces citation-specific pre-training within an encoder-decoder architecture, where author-date citation tokens are masked to learn to reconstruct them to fulfill LCR. There are two variants for this pre-training. In the local context-only base scheme (CiteBART-Base), the citation token in a local context is masked to learn to predict the citation. The global version (CiteBART-Global) extends the local context with the citing paper's title and abstract to enrich the learning signal. CiteBART-Global achieves state-of-the-art performance on LCR benchmarks except for the FullTextPeerRead dataset, which is quite small to see the advantage of generative pre-training. The effect is significant in the larger benchmarks, e.g., Refseer and ArXiv., with the Refseer benchmark-trained model emerging as the best-performing model. We perform comprehensive experiments, including an ablation study, a qualitative analysis, and a taxonomy of hallucinations with detailed statistics. Our analyses confirm that CiteBART-Global has a cross-dataset generalization capability; the macro hallucination rate (MaHR) at the top-3 predictions is 4%, and when the ground-truth is in the top-k prediction list, the hallucination tendency in the other predictions drops significantly.

PaperPDFCodeCode Syntology ran

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):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 12 ran (12 with no instrument failure; 0 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

eyclk/citationrecommendation officialmentioned in paperpytorchMITSyntology: 16 samples, 12 ran (0 instrument-failed) · 4 unverified report

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

16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

12ran
4unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from eyclk/citationrecommendation. “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.

eyclk/citationrecommendation official repository 16 samples, 12 ran (0 instrument-failed) · 4 unverified
add_spaces_after_commas train/train_base_cit_pred_BART.py ran fingerprinted MIT (permissive) · ed93e4ca62fbffb6 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
assign_appropriate_year_for_null_years preprocessing/base_datasets/data_preprocess_for_arxiv_base.py ran fingerprinted MIT (permissive) · 7b67f2595aec1eb4 · report fixture: signature ref_id:str/0/str, author_names:list/1/str · returned str · level recorded 2026-09-25
assign_appropriate_year_for_null_years preprocessing/base_datasets/data_preprocess_for_refseer_base.py ran fingerprinted MIT (permissive) · 8ea3a7ab27e61dc5 · report fixture: signature ref_id:str/0/str, author_names:list/1/str · returned str · level recorded 2026-09-24
calculate_average_and_median_of_cit_per_ref utils/data_statistic_utils.py ran MIT (permissive) · 38ebfde953f7ced5 · report fixture: signature appearance_counts_list:list/1/int · returned tuple · level recorded 2026-09-24
check_if_raw_text_has_special_tags preprocessing/base_datasets/data_preprocess_for_refseer_base.py ran MIT (permissive) · 88ebca421726370f · report fixture: signature raw_text:str/0/str · returned bool · level recorded 2026-09-25
check_if_string_contains_year preprocessing/base_datasets/data_preprocess_for_acl200_base.py ran MIT (permissive) · 4f99c48215b33468 · report fixture: signature marker:str/0/str · returned bool · level recorded 2026-09-25
create_appearance_count_frequency_dict utils/data_statistic_utils.py ran fingerprinted MIT (permissive) · 5700d07b9aac33af · report fixture: signature appearance_counts_list:list/1/int · returned dict · level recorded 2026-09-25
create_target_token_for_ref_paper_id preprocessing/base_datasets/data_preprocess_for_acl200_base.py ran fingerprinted MIT (permissive) · a4cbaa0a0a646c3b · report fixture: signature marker_from_contexts_file:str/0/str · returned str · level recorded 2026-09-25
create_target_token_for_ref_paper_id preprocessing/base_datasets/data_preprocess_for_arxiv_base.py ran MIT (permissive) · 9b3d0dd4083197b1 · report fixture: signature ref_id:int/0/int, papers_df:dict/0/? · returned str · level recorded 2026-09-24
create_target_token_for_ref_paper_id preprocessing/base_datasets/data_preprocess_for_peerread_base.py ran MIT (permissive) · 523150d2455c7d31 · report fixture: signature ref_id:str/0/str, papers_df:dict/0/? · returned str · level recorded 2026-09-24
create_target_token_for_ref_paper_id preprocessing/base_datasets/data_preprocess_for_refseer_base.py ran MIT (permissive) · 10449f995043c586 · report fixture: signature ref_id:int/0/int, papers_df:PapersDataFrame/0/? · returned str · level recorded 2026-09-25
find_all_appearance_counts utils/data_statistic_utils.py ran MIT (permissive) · ebd620899935776d · report fixture: signature appearance_count_dict:dict/0/? · returned list · level recorded 2026-09-25
fill_mask train/train_base_cit_pred_BART.py unverified MIT (permissive) · 85c6162dc111a623 · report
place_mask_and_target_cit_on_ground_truth_context preprocessing/base_datasets/data_preprocess_for_acl200_base.py unverified MIT (permissive) · 27f10f8117094aa8 · report
preprocess_function in 29 papers train/train_base_cit_pred_BART.py unverified MIT (permissive) · 4f57ec01008c6bae · report
preprocess_function in 29 papers train/train_global_cit_pred_BART.py unverified MIT (permissive) · 0e7c221cf16af4e4 · report

Tasks

Citation PredictionCitation RecommendationCitation worthinessHallucination

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionBARTBASEBPEDense ConnectionsDropoutLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSETSoftmax

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