Papers › Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

26 May 2023NeurIPS 2023 11arXiv:2305.16646archive 2025-07-28

Xiaoming Shi, Siqiao Xue, Kangrui Wang, Fan Zhou, James Y. Zhang, Jun Zhou, Chenhao Tan, Hongyuan Mei

Large language models have shown astonishing performance on a wide range of reasoning tasks. In this paper, we investigate whether they could reason about real-world events and help improve the prediction performance of event sequence models. We design LAMP, a framework that integrates a large language model in event prediction. Particularly, the language model performs abductive reasoning to assist an event sequence model: the event model proposes predictions on future events given the past; instructed by a few expert-annotated demonstrations, the language model learns to suggest possible causes for each proposal; a search module finds out the previous events that match the causes; a scoring function learns to examine whether the retrieved events could actually cause the proposal. Through extensive experiments on several challenging real-world datasets, we demonstrate that our framework -- thanks to the reasoning capabilities of large language models -- could significantly outperform the state-of-the-art event sequence models.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 24 code samples harvested from 4 repositories linked to this paper: 19 ran (of which 4 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 2 repositories, 14 ran (10 with no instrument failure; 4 where Syntology's instrument failed); found in paper text by Syntology: 7 samples from 2 repositories, 5 ran (5 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ant-research/easytemporalpointprocess officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
ilampard/lamp officialmentioned in paperpytorchApache-2.0Syntology: 13 samples, 10 ran (1 instrument-failed) · 3 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

24 samples harvested: 19 ran (of which 4 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 4 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
1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
13ran
5unverified

Licence: 4 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 4 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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

ant-research/easytemporalpointprocess official repository 4 samples, 4 ran (3 instrument-failed) · 0 unverified
activation_layer in 34 papers easy_tpp/model/baselayer.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · d49d5a4ade4321b5 · report fixture: signature act_name:str/0/str · returned ReLU · level recorded 2026-09-25
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
easy_tpp/model/baselayer.py ran · our draft was wrong Apache-2.0 (permissive) · 8abbfdabbdf5e708 · report fixture: signature query:Tensor/4/float, key:Tensor/4/float, value:Tensor/4/float, mask:Tensor/4/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-22
clamp_preserve_gradients in 7 papers easy_tpp/model/intensity_free.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 3105c1d665ab0317 · report fixture: signature x:Tensor/2/float, min_val:float/0/float, max_val:float/0/float · returned Tensor · level recorded 2026-09-25
flatten_parameters in 5 papers easy_tpp/model/ode_tpp.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · 615bdcf3b3a4cfbe · report fixture: signature model:callable/0/? · returned Tensor · level recorded 2026-09-25
ilampard/lamp official repository 13 samples, 10 ran (1 instrument-failed) · 3 unverified
ANHPMultiHeadAttention models/ke_anhp/_model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 4f8d5fca7de08dd4 · report fixture: returned ANHPMultiHeadAttention · level recorded 2026-09-22
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/ke_anhp/_model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 71cbec2f001bc55b · report fixture: returned Attention · level recorded 2026-09-22
Dense in 22 papers models/ke_anhp/_model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 9a448be7eb920dac · report fixture: returned Dense · level recorded 2026-09-22
TimeEmbeddingLayer models/ke_anhp/_model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · b45ab9b5072bb2f6 · report fixture: returned TimeEmbeddingLayer · level recorded 2026-09-22
bce_loss in 22 papers models/ebm_runner.py ran Apache-2.0 (permissive) · 51227b0b43c5ed30 · report fixture: signature real_energy_unnorm:Tensor/1/float, fake_energys_unnorm:Tensor/2/float · returned Tensor · level recorded 2026-09-26
bce_score models/ebm_runner.py ran Apache-2.0 (permissive) · 804306367162b14c · report fixture: signature real_energy_unnorm:Tensor/1/float, fake_energys_unnorm:Tensor/2/float · returned tuple · level recorded 2026-09-26
exp_scaled_dot_score_method models/ke_anhp/_model.py ran · violated contract fingerprinted Apache-2.0 (permissive) · be04fa53df26c966 · report fixture: signature queries:Tensor/3/float, keys:Tensor/3/float · returned Tensor · level recorded 2026-09-22
get_embedding in 28 papers models/ke_anhp/_model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 3bab5ed3d30b876d · report fixture: signature idx:Tensor/1/int, embeddings:Tensor/2/float · returned Tensor · level recorded 2026-09-22
mnce_loss models/ebm_runner.py ran Apache-2.0 (permissive) · 2d8c90020f8f93fd · report fixture: signature real_energy_unnorm:Tensor/2/float, fake_energys_unnorm:Tensor/3/float · returned Tensor · level recorded 2026-09-26
search_pred_data eval_tpp.py ran Apache-2.0 (permissive) · 2bbd803d60718f65 · report fixture: signature pred_data:list/1/list, seq_idx:int/0/int, original_idx:int/0/int · returned dict · level recorded 2026-09-26
KnowEvolveANHP models/ke_anhp/_model.py unverified Apache-2.0 (permissive) · 32549da5b1d6f6df · report
RNNEntityEmbeddingLayer models/ke_anhp/_model.py unverified Apache-2.0 (permissive) · 271a64fd27570f0a · report
RelationScoreLayer models/ke_anhp/_model.py unverified Apache-2.0 (permissive) · 99f53b75f1c900fe · report
uoguelph-mlrg/LDG found in paper text by Syntology 1 sample, 0 ran · 1 unverified
DyRep dyrep.py unverified licence not identified · pointer only · 0feed5743989fe45 · report
statisticianinstilettos/recmetrics found in paper text by Syntology 6 samples, 5 ran (0 instrument-failed) · 1 unverified
catalog_coverage recmetrics/metrics.py ran MIT (permissive) · 170636830f7e013d · report fixture: signature predicted:list/1/list, catalog:list/1/str, k:int/0/int · returned float · level recorded 2026-09-26
is_listy recmetrics/plots.py ran fingerprinted MIT (permissive) · 275d9ff6710f5610 · report fixture: signature x:list/1/int · returned bool · level recorded 2026-09-26
make_listy recmetrics/plots.py ran fingerprinted MIT (permissive) · 4dbc840d3335cc9c · report fixture: signature p:str/0/str · returned list · level recorded 2026-09-26
novelty recmetrics/metrics.py ran MIT (permissive) · ea5a39a1fa474615 · report fixture: signature predicted:list/1/list, pop:dict/0/?, u:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-26
prediction_coverage recmetrics/metrics.py ran MIT (permissive) · c8eb82add723ab39 · report fixture: signature predicted:list/1/list, catalog:list/1/str, unseen_warning:bool/0/bool · returned float · level recorded 2026-09-26
roc_plot recmetrics/plots.py unverified MIT (permissive) · f851ed6bcf9fc446 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for LAMP (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for LAMP (graph method: LAMP). 9 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. KnowEvolveANHP entry · level 0 · unverified · 32549da5b1d6f6df
  2. RNNEntityEmbeddingLayer model · level 0 · unverified · 271a64fd27570f0a
  3. RelationScoreLayer model · level 0 · unverified · 99f53b75f1c900fe
  4. get_embedding helper · level 1 · ran; the contract check could not run (RAISES) · 3bab5ed3d30b876d
  5. ANHPMultiHeadAttention helper · level 1 · ran · 4f8d5fca7de08dd4
  6. TimeEmbeddingLayer model · level 1 · ran · b45ab9b5072bb2f6
  7. Attention helper · level 1 · ran · 71cbec2f001bc55b
  8. Dense helper · level 1 · ran · 9a448be7eb920dac
  9. exp_scaled_dot_score_method helper · level 1 · ran · violated contract · be04fa53df26c966

harvested Assembly for LAMP (graph method: LAMP). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. DyRep entry · level 0 · unverified · 0feed5743989fe45

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2305.16646") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingLarge Language Model

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