Home › Code › apply_chat_template

apply_chat_template

Syntologyentry name in harvested coderead from the graph 2026-09-24

apply_chat_template appears in the code Syntology harvested for 44 papers, as 35 distinct code bodies found in 45 places (a place is one code body under one paper). At least one of them ran in 26 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named apply_chat_template do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 20 of the 35 distinct code bodies named apply_chat_template; 15 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
0ran · violated contract
4ran · our draft was wrong
0ran · fixture could not drive it
15ran
15unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 18 of the 45 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

44 papers shown of 44, newest first; 45 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 11 papers added by Syntology; 1 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents added by Syntology 2026-08 (from id) EIT-NLP/ReCache/capsule/src/chat.py 561fab9ba99c10a9 unverified no licence file found · pointer only
REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning added by Syntology 2026-07 (from id) yunjie-sysu/REGEN/regen_train.py fa5ffe76078469b4 ran no licence file found · pointer only
Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training added by Syntology 2026-06 (from id) jinymusim/ART/src/reasoning_with_art/models/chat_template.py 8c6d5abeff384032 unverified BSD-3-Clause (permissive)
A Regret Minimization Framework on Preference Learning in Large Language Models added by Syntology 2026-06 (from id) YSLIU627/Regularized-Preference-Optimization/alignment-handbook/src/alignment/data.py 5a84f9e5640fe497 ran Apache-2.0 (permissive)
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation added by Syntology 2026-06 (from id) YuYingLi0/FiRe-OPD/math_eval/eval_math.py 6eceb1b9ba215e62 ran no licence file found · pointer only
Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization added by Syntology 2026-05 (from id) Hyalinesky/DGAO/trl/data_utils.py c70072e46530e6e1 ran Apache-2.0 (permissive)
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation added by Syntology 2026-05 (from id) caiyuchen-ustc/EffOPD/EffOPD/math_eval/eval_math.py 6eceb1b9ba215e62 ran no licence file found · pointer only
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text added by Syntology 2026-04 (from id) HCY123902/POP/training/data_utils.py f8fe363ab9ecb4d6 unverified no licence file found · pointer only
Biases in the Blind Spot: Detecting What LLMs Fail to Mention added by Syntology 2026-02 (from id) FlyingPumba/biases-in-the-blind-spot/biases_in_the_blind_spot/prompting.py 8d2a192c16537e25 unverified no licence file found · pointer only
EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing added by Syntology 2025-12 (from id) VectorSpaceLab/OmniGen2/OmniGen2-RL/reward_server/reward_server.py a6ba03fb70bfe8c6 unverified Apache-2.0 (permissive)
Iterative Prompt Refinement for Safer Text-to-Image Generation added by Syntology 2025-09 (from id) ku-dmlab/IPR/trl/data_utils.py 53017c7a8e570221 unverified Apache-2.0 (permissive)
OmniGen2: Exploration to Advanced Multimodal Generation 23 Jun 2025 vectorspacelab/omnigen2/OmniGen2-RL/reward_server/reward_server.py a6ba03fb70bfe8c6 unverified Apache-2.0 (permissive)
Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving 10 Jun 2025 thumlp/multicogeval/scripts/evaluate_high_level.py 435da15dd90581b2 ran · our draft was wrong no licence file found · pointer only
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen! 21 May 2025 thu-coai/backdoor-data-extraction/train/trl/data_utils.py 53017c7a8e570221 unverified MIT (permissive)
Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning 20 May 2025 jiwonsong-dev/reasoningpathcompression/utils/apply_chat_template.py 2d966163bc3a3005 unverified MIT (permissive)
DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models 14 May 2025 xiwenc1/dra-grpo/src/open_r1/trl/data_utils.py 53017c7a8e570221 unverified MIT (permissive)
DeepCritic: Deliberate Critique with Large Language Models 1 May 2025 rucbm/deepcritic/Critique_Generation/correct_slutions_rollout.py 488c133e028a1ca6 unverified MIT (permissive)
DeepCritic: Deliberate Critique with Large Language Models 1 May 2025 rucbm/deepcritic/Critique_Generation/gen_step_solutions.py 2e16de463ce3df94 unverified MIT (permissive)
Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models 28 Apr 2025 minnesotanlp/mpo/trl/data_utils.py 0b7223ebdefef219 unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
EXAONE Deep: Reasoning Enhanced Language Models 16 Mar 2025 tengxiao1/simper/alignment/data.py 9be97bcdb51fd634 ran MIT (permissive)
Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support 25 Feb 2025 jdh-algo/Citrus/model_train/alignment/data.py 9be97bcdb51fd634 ran MIT (permissive)
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention 16 Feb 2025 microsoft/seerattention/distillation_decode.py 202aa55ac60ff1f6 unverified MIT (permissive)
LLM Safety Alignment is Divergence Estimation in Disguise 2 Feb 2025 rhaldarpurdue/kldo/metrics.py a3e5e980b0266d7e unverified Apache-2.0 (permissive)
Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment 19 Dec 2024 tengxiao1/cal-dpo/scripts/run_dpo.py e9f3be83e4d643bb ran · our draft was wrong no licence file found · pointer only
ProcessBench: Identifying Process Errors in Mathematical Reasoning 9 Dec 2024 qwenlm/processbench/code/run_eval.py ff5ecf497e982ea2 ran · honoured contract no licence file found · pointer only
TODO: Enhancing LLM Alignment with Ternary Preferences 2 Nov 2024 XXares/TODO/utils/utils.py 6744441ca5bd1ea7 unverified MIT (permissive)
$α$-DPO: Adaptive Reward Margin is What Direct Preference Optimization Needs 14 Oct 2024 junkangwu/alpha-dpo/alignment/data.py 9be97bcdb51fd634 ran MIT (permissive)
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective 14 Oct 2024 tengxiao1/GSIL/gsil/alignment/data.py 23781da963dd98a5 ran no licence file found · pointer only
Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback 4 Oct 2024 kykim0/margin-matching-pref-opt/src/alignment/data.py 9be06c85912c5236 ran Apache-2.0 (permissive)
MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery 9 Sep 2024 qhjqhj00/memorag/train/src/chat.py 561fab9ba99c10a9 unverified Apache-2.0 (permissive)
Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities 5 Sep 2024 lamm-mit/llm-finetuning/alignment-handbook/src/alignment/data.py 9a40c8da283bcd4a ran no licence file found · pointer only
Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models 27 Aug 2024 wx-zhang/bfpo/src/alignment/data.py ecf650a71ce5efc6 ran no licence file found · pointer only
CompAct: Compressing Retrieved Documents Actively for Question Answering 12 Jul 2024 dmis-lab/CompAct/alignment-handbook/src/alignment/data.py 9be97bcdb51fd634 ran no licence file found · pointer only
Panacea: A foundation model for clinical trial search, summarization, design, and recruitment 25 Jun 2024 linjc16/panacea/alignment/data.py b90a3acb4197f936 ran no licence file found · pointer only
Suri: Multi-constraint Instruction Following for Long-form Text Generation 27 Jun 2024 chtmp223/suri/ft/lib/alignment_mod/data.py ed74b164b2fe6a65 ran no licence file found · pointer only
ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation 16 Jun 2024 Rain9876/ShareLoRA/sharelora/few_shot.py 758b57f056efcfff ran · our draft was wrong no licence file found · pointer only
Discovering Preference Optimization Algorithms with and for Large Language Models 12 Jun 2024 luchris429/DiscoPOP/src/alignment/data.py 9be97bcdb51fd634 ran MIT (permissive)
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment 29 May 2024 shenao-zhang/selm/src/alignment/data.py 6ccb3e2cc15898e6 ran no licence file found · pointer only
Triple Preference Optimization: Achieving Better Alignment with Less Data in a Single Step Optimization 26 May 2024 sahsaeedi/triple-preference-optimization/utils/data.py a9cb92f38a00fa54 ran MIT (permissive)
SimPO: Simple Preference Optimization with a Reference-Free Reward 23 May 2024 princeton-nlp/SimPO/alignment/data.py 9be97bcdb51fd634 ran MIT (permissive)
MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning 13 May 2024 project-numina/aimo-progress-prize/training/aimo/utils/utils.py 9e3cb3146217643b unverified Apache-2.0 (permissive)
Self-Play Preference Optimization for Language Model Alignment 1 May 2024 uclaml/sppo/sppo/alignment/data.py b8b8e4dae1d1318b ran Apache-2.0 (permissive)
Noise Contrastive Alignment of Language Models with Explicit Rewards 8 Feb 2024 thu-ml/Noise-Contrastive-Alignment/data_utils.py 3c1fa452c713aa74 ran MIT (permissive)
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models 2 Jan 2024 uclaml/SPIN/spin/run_spin.py 3cac05ec501439e8 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2025.naacl-long.550 hexuan21/Weak-to-Strong/run_inference.py bdcadd7ed60f8a7c unverified Apache-2.0 (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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