Papers › Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?

Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?

28 Sep 2023arXiv:2309.16595archive 2025-07-28

Jin Huang, Xingjian Zhang, Qiaozhu Mei, Jiaqi Ma

Large language models (LLMs) are gaining increasing attention for their capability to process graphs with rich text attributes, especially in a zero-shot fashion. Recent studies demonstrate that LLMs obtain decent text classification performance on common text-rich graph benchmarks, and the performance can be improved by appending encoded structural information as natural languages into prompts. We aim to understand why the incorporation of structural information inherent in graph data can improve the prediction performance of LLMs. First, we rule out the concern of data leakage by curating a novel leakage-free dataset and conducting a comparative analysis alongside a previously widely-used dataset. Second, as past work usually encodes the ego-graph by describing the graph structure in natural language, we ask the question: do LLMs understand the graph structure in accordance with the intent of the prompt designers? Third, we investigate why LLMs can improve their performance after incorporating structural information. Our exploration of these questions reveals that (i) there is no substantial evidence that the performance of LLMs is significantly attributed to data leakage; (ii) instead of understanding prompts as graph structures as intended by the prompt designers, LLMs tend to process prompts more as contextual paragraphs and (iii) the most efficient elements of the local neighborhood included in the prompt are phrases that are pertinent to the node label, rather than the graph structure.

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 15 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 13 samples from 1 repository, 8 ran (6 with no instrument failure; 2 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.

trais-lab/llm-structured-data officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
CurryTang/Graph-LLM mentioned on GitHubpytorchMITSyntology: 13 samples, 8 ran (2 instrument-failed) · 5 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

15 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 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.

1ran · honoured contract
3ran · our draft was wrong
6ran
5unverified

Licence: 8 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

trais-lab/llm-structured-data official repository 2 samples, 2 ran (1 instrument-failed) · 0 unverified
get_subgraph utils/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 68261186ab933f2d · report fixture: signature node_idx:int/0/int, edge_index:Tensor/2/int, hop:int/0/int · returned list · level recorded 2026-09-22
sample_test_nodes utils/utils.py ran · honoured contract no licence file found · pointer only · 2a78218aa16ad624 · report fixture: signature data:MockGraphData/0/?, text:dict/0/?, sample_size:int/0/int, dataset:str/0/str · returned list · level recorded 2026-09-22
CurryTang/Graph-LLM community (archive-listed) 13 samples, 8 ran (2 instrument-failed) · 5 unverified
api_endpoint_from_url in 10 papers async_api.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 0a0bc4ba8c9af478 · report fixture: signature request_url:str/0/str · returned str · level recorded 2026-09-22
get_model_name_mapping lmfinetune.py ran MIT (permissive) · e1e7a14ef324d0a0 · report fixture: signature model_name:str/0/str · returned str · level recorded 2026-09-24
hyper_search hyper.py ran MIT (permissive) · f3c0523f8aa04241 · report fixture: signature trial:MockTrial/0/?, embedding_type:str/0/str, gnn_model:callable/0/?, dataset:MockDataset/0/? · returned dict · level recorded 2026-09-24
persist_cache_to_disk api.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · f4cc3f30e8c88187 · report fixture: signature filename:str/0/str · returned function · level recorded 2026-09-24
pkl_and_write data.py ran MIT (permissive) · e9743a63e8c74735 · report fixture: signature obj:dict/0/?, path:str/0/str · returned str · level recorded 2026-09-24
prompt_zero_shot ego_graph.py ran MIT (permissive) here; the stored copy is pointer only · 98699449238cacb8 · report fixture: signature data_obj:MockDataObj/0/?, sampled_test_node_idxs:list/1/int, train_node_idxs:list/1/int, topk:bool/0/bool, need_class:bool/0/bool, instruction_format:str/0/str, mapping:dict/0/?, all_possible:bool/0/bool, cot:bool/0/bool, memory_limit:int/0/int · returned tuple · level recorded 2026-09-24
ptr2index data.py ran MIT (permissive) · 82ab704565cc2a39 · report fixture: signature ptr:Tensor/1/int · returned Tensor · level recorded 2026-09-24
replace_args_with_dict_values args.py ran MIT (permissive) here; the stored copy is pointer only · ca3bd8e13278c0f7 · report fixture: signature args:SimpleArgs/0/?, dictionary:dict/0/? · returned SimpleArgs · level recorded 2026-09-24
get_embedding in 28 papers api.py unverified MIT (permissive) here; the stored copy is pointer only · ccb546755da4914b · report
get_model in 368 papers models.py unverified MIT (permissive) · 6e6759bd8de7af1e · report
load_yaml_file in 9 papers api.py unverified MIT (permissive) · 14306190576e01d0 · report
num_tokens_consumed_from_request in 10 papers async_api.py unverified MIT (permissive) here; the stored copy is pointer only · 27007d0ec4adb00b · report
to_edge_index data.py unverified MIT (permissive) · 9fcf6a81ca26b3d1 · report

Tasks

Graph LearningNode ClassificationText ClassificationText-To-SQLtext-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) GPT-4 (Baseline) Execution Accuracy % (Dev) 46.35 #31 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) GPT-4 (Baseline) Execution Accuracy % (Test) 54.89 #31 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) Claude-2 (Baseline) Execution Accuracy % (Dev) 42.70 #32 of 41 Archive leaderboard report
Text-To-SQL BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) Claude-2 (Baseline) Execution Accuracy % (Test) 49.02 #32 of 41 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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