Papers › Large Language Models Can Learn Temporal Reasoning

Large Language Models Can Learn Temporal Reasoning

12 Jan 2024arXiv:2401.06853archive 2025-07-28

Siheng Xiong, Ali Payani, Ramana Kompella, Faramarz Fekri

While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they are not without their flaws and inaccuracies. Recent studies have introduced various methods to mitigate these limitations. Temporal reasoning (TR), in particular, presents a significant challenge for LLMs due to its reliance on diverse temporal concepts and intricate temporal logic. In this paper, we propose TG-LLM, a novel framework towards language-based TR. Instead of reasoning over the original context, we adopt a latent representation, temporal graph (TG) that enhances the learning of TR. A synthetic dataset (TGQA), which is fully controllable and requires minimal supervision, is constructed for fine-tuning LLMs on this text-to-TG translation task. We confirmed in experiments that the capability of TG translation learned on our dataset can be transferred to other TR tasks and benchmarks. On top of that, we teach LLM to perform deliberate reasoning over the TGs via Chain-of-Thought (CoT) bootstrapping and graph data augmentation. We observed that those strategies, which maintain a balance between usefulness and diversity, bring more reliable CoTs and final results than the vanilla CoT distillation.

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 27 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 27 samples from 1 repository, 12 ran (6 with no instrument failure; 6 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

xiongsiheng/tg-llm officialmentioned in papermentioned on GitHubpytorchMITSyntology: 27 samples, 12 ran (6 instrument-failed) · 15 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

27 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 15 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 · violated contract
6ran · our draft was wrong
5ran
15unverified

Licence: 0 of the 27 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 xiongsiheng/tg-llm. “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.

xiongsiheng/tg-llm official repository 27 samples, 12 ran (6 instrument-failed) · 15 unverified
TG_formating_change src/utlis.py ran MIT (permissive) · 2c503ce417d1dcb7 · report fixture: signature TG:list/1/str, dataset_name:str/0/str, targ_dataset:str/0/str · returned list · level recorded 2026-09-24
add_brackets src/utlis.py ran · our draft was wrong MIT (permissive) · e60f57957786c21d · report fixture: signature ls:list/1/str · returned list · level recorded 2026-09-24
calculate_EM src/Evaluation.py ran · violated contract fingerprinted MIT (permissive) · aafcf7f19d17018f · report fixture: signature a_gold:str/0/str, a_pred:str/0/str · returned bool · level recorded 2026-09-24
configure_experiment src/Inference_in_context_learning_ppl.py ran · our draft was wrong MIT (permissive) · 7bf3b153ae77bf4e · report fixture: signature args:Namespace/0/? · returned dict · level recorded 2026-09-24
initialize_model in 15 papers src/Inference_in_context_learning_ppl.py ran MIT (permissive) · 04baeed1a6087e14 · report fixture: signature config:dict/0/? · returned tuple · level recorded 2026-09-24
my_generate_prompt_CoT_bs src/prompt_generation.py ran MIT (permissive) · 59cd476e2da672b1 · report fixture: signature TG:list/1/str, EK:list/1/str, Q:str/0/str, prompt_format:str/0/str · returned str · level recorded 2026-09-24
my_generate_prompt_TG_Reasoning src/prompt_generation.py ran MIT (permissive) · 728cf1bc1de4ee15 · report fixture: signature dataset_name:str/0/str, split_name:str/0/str, story:str/0/str, TG:list/1/str, EK:list/1/str, Q:str/0/str, CoT:list/1/str, A:list/1/str, f_ICL:bool/0/bool, Q_type:str/0/str, mode:str/0/str, eos_token:str/0/str, f_no_TG:bool/0/bool, prompt_format:str/0/str · returned str · level recorded 2026-09-24
my_gpt_completion src/Models.py ran MIT (permissive) · 0f869ecd0da8b94a · report fixture: signature openai_model:str/0/str, messages:list/1/dict, timeout:int/0/int, max_new_tokens:int/0/int, wait_time:int/0/int · returned str · level recorded 2026-09-24
parse_generation src/Evaluation.py ran · our draft was wrong fingerprinted MIT (permissive) · b06bb22f061273b7 · report fixture: signature pred:str/0/str · returned str · level recorded 2026-09-24
prepare_prompts in 11 papers src/Example_accelerate_inference.py ran · our draft was wrong MIT (permissive) · 67e14cf8263186c1 · report fixture: signature prompts:list/1/str, tokenizer:callable/0/?, batch_size:int/0/int · returned list · level recorded 2026-09-24
process_CoT src/utlis.py ran · our draft was wrong fingerprinted MIT (permissive) · 8aaaded627e91fec · report fixture: signature ans_pred:str/0/str · returned str · level recorded 2026-09-24
setup_model in 8 papers src/CoT_bootstrap.py ran · our draft was wrong MIT (permissive) · 5e981e8216935d05 · report fixture: signature model_name:str/0/str · returned tuple · level recorded 2026-09-24
calculate_F1 src/Evaluation.py unverified MIT (permissive) · cb4f976df70802fa · report
initialize_model_and_tokenizer src/Inference_in_context_learning.py unverified MIT (permissive) · 03fb82e648b4f4cb · report
load_and_prepare_data in 7 papers src/CoT_bootstrap.py unverified MIT (permissive) · d9e464347efd6ebe · report
load_and_prepare_dataset src/SFT_text_to_TG_Trans.py unverified MIT (permissive) · f5f3d5df55849409 · report
load_data in 700 papers src/Inference_in_context_learning_ppl.py unverified MIT (permissive) · c7264563bb030e10 · report
load_data in 700 papers src/SFT_TG_Reasoning.py unverified MIT (permissive) · 53c786894bf78ed0 · report
load_model_and_tokenizer in 61 papers src/SFT_TG_Reasoning_ppl.py unverified MIT (permissive) · e9cff349000673db · report
load_test_data in 21 papers src/Inference_in_context_learning.py unverified MIT (permissive) · cce7996e68e164e1 · report
my_generate_prompt_ICL src/prompt_generation.py unverified MIT (permissive) · ea5ab833166b0ed2 · report
obtain_loss_in_batch src/Models.py unverified MIT (permissive) · 57830d7473a5dbd2 · report
prepare_TG_pred src/SFT_TG_Reasoning.py unverified MIT (permissive) · 485538ab9c196ec3 · report
prepare_data in 87 papers src/SFT_TG_Reasoning_ppl.py unverified MIT (permissive) · 5c967fee8b9215c7 · report
read_data in 132 papers src/SFT_TG_Reasoning.py unverified MIT (permissive) · 37999e53da63da2e · report
run_inference in 23 papers src/Example_accelerate_inference.py unverified MIT (permissive) · b0e211cdbd2080be · report
setup_directories src/SFT_TG_Reasoning_ppl.py unverified MIT (permissive) · c676e0c7b2233e53 · report

Tasks

Data AugmentationDiversityText GenerationTranslation

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