Home › Code › format_prompt

format_prompt

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

format_prompt appears in the code Syntology harvested for 45 papers, as 53 distinct code bodies found in 56 places (a place is one code body under one paper). At least one of them ran in 28 of the papers; 6 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 format_prompt 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 34 of the 53 distinct code bodies named format_prompt; 19 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
10ran · our draft was wrong
1ran · fixture could not drive it
23ran
19unverified
6fingerprinted

Licence is a property of each copy, so it is counted per place: 23 of the 56 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

45 papers shown of 45, newest first; 56 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 10 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
Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling added by Syntology 2026-08 (from id) aMa2210/beyond-the-hivemind/src/pipeline/step2_generate_responses.py 16b8fc2643349221 ran · our draft was wrong licence not identified · pointer only
Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning added by Syntology 2026-05 (from id) safety-research/faithful-cot/eval/evaluate_hacking_ratio.py 980d1a07fda8a0db ran no licence file found · pointer only
Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs added by Syntology 2026-05 (from id) proviso-bench/Presupposition-and-Reasoning-in-Conditionals/inference/closedsource/inference_closedsource.py 248a640efdc7464c ran no licence file found · pointer only
PeerPrism: Peer Evaluation Expertise vs Review-writing AI added by Syntology 2026-04 (from id) Reviewerly-Inc/PeerPrism/02_review_transformation/transformations/hybrid_reviews.py 68efb2a62e8a8147 ran · our draft was wrong fingerprinted no licence file found · pointer only
LAMUS: A Large-Scale Corpus for Legal Argument Mining from U.S. Caselaw using LLMs added by Syntology 2026-03 (from id) LavanyaPobbathi/LAMUS/code/experiment/C_finetuning_ablation_v2.py 9ccf27d30fdb741b unverified no licence file found · pointer only
Protecting Language Models Against Unauthorized Distillation through Trace Rewriting added by Syntology 2026-02 (from id) xhOwenMa/trace-rewriting/optimize/propose_candidates.py fb2d68d136e3fdb1 unverified no licence file found · pointer only
GOPO: Policy Optimization using Ranked Rewards added by Syntology 2026-02 (from id) friendshipkim/gopo/generate/generate_completions.py 7720ea43a933acbd unverified Apache-2.0 (permissive)
Beyond Translation: Cross-Cultural Meme Transcreation with Vision-Language Models added by Syntology 2026-02 (from id) AIM-SCU/MemeXGen/judges/_common/prompt.py 3b648343d9b97d8e unverified MIT (permissive)
Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation added by Syntology 2026-01 (from id) Yale-BIDS-Chen-Lab/FL_LLM_Med/src/command/medical_re_csv_parse.py 1c1226b88bdf7048 unverified no licence file found · pointer only
Stochastic Self-Organization in Multi-Agent Systems added by Syntology 2025-10 (from id) tnurbek/selforg/evaluations/evaluate_xverify.py ca9fc2b740a5a87e unverified no licence file found · pointer only
SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation 27 May 2025 ClaudiaCuttano/SANSA/util/demo_sansa.py 9f2171cc1758c725 ran · fixture could not drive it MIT (permissive)
Out of Style: RAG's Fragility to Linguistic Variation 11 Apr 2025 springcty/rag-fragility-to-linguistic-variation/LLM_generation/utils/vllm_inference.py afab3aee4c1d97a0 unverified MIT (permissive)
Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning 8 Apr 2025 Sanchit-404/Reasoing-Towards-Fairness/scripts/finetune_on_traces.py 6b9e5582f91b19d7 ran · our draft was wrong no licence file found · pointer only
RARE: Retrieval-Augmented Reasoning Modeling 30 Mar 2025 open-dataflow/rare/inference/vllm_infer_mm.py 43b4dce1bb401779 unverified Apache-2.0 (permissive)
RARE: Retrieval-Augmented Reasoning Modeling 30 Mar 2025 open-dataflow/rare/inference/vllm_infer_text.py 0fb897a1530a0ca3 unverified Apache-2.0 (permissive)
arXiv:2503.05188 2025-03 (from id) BugMakerzzz/CRISP/crisp_reason.py 4b6f78016356fabe ran · our draft was wrong no licence file found · pointer only
DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning 28 Feb 2025 pat-jj/deepretrieval/query_rewrite.py f4549a2164452ce1 unverified MIT (permissive)
DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning 28 Feb 2025 pat-jj/deepretrieval/code/src/query_rewrite.py dbf81b46206bc092 unverified MIT (permissive)
Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning 24 Feb 2025 gauss5930/mclm/src/prm.py b960d1f9e15f6bd3 ran · our draft was wrong no licence file found · pointer only
Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases 20 Feb 2025 RenaGao/LLMPirorknowledge/lib/annotation.py 6340c353203620a9 unverified MIT (permissive)
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment 16 Jan 2025 tatsu-lab/alpaca_farm/src/alpaca_farm/data_preprocessor.py a71a4bdc37586fe2 ran Apache-2.0 (permissive)
MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models 2024-12 (from id) shansongliu/MuMu-LLaMA/MuMu-LLaMA/llama/utils.py fa5a132156cdaf6d unverified MIT (permissive)
One Diffusion to Generate Them All 25 Nov 2024 lehduong/onediffusion/gradio_demo.py 362b432acdaa105e ran · our draft was wrong licence not identified · pointer only
Do LLMs "know" internally when they follow instructions? 18 Oct 2024 apple/ml-internal-llms-instruction-following/run/save_LLMs_activations.py ced84377f1394101 unverified licence not identified · pointer only
Reward-Augmented Data Enhances Direct Preference Alignment of LLMs 10 Oct 2024 shenao-zhang/reward-augmented-preference/scripts/preprocess.py 1290bdbfd3cfa6e5 ran · our draft was wrong Apache-2.0 (permissive)
Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino 20 Sep 2024 aisingapore/kalahi/kalahi/utilities.py b89a6d986d96e4fa ran fingerprinted CC-BY-4.0 · pointer only
Archon: An Architecture Search Framework for Inference-Time Techniques 23 Sep 2024 scalingintelligence/archon/src/archon/completions/utils.py a3621beb3eb4d82a ran Apache-2.0 (permissive)
RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code 23 Sep 2024 qing-yuan233/RMCBench/script/run_open_llm.py e0e266948769ee25 ran fingerprinted licence not identified · pointer only
Aligning Large Language Models with Diverse Political Viewpoints 20 Jun 2024 dominiksinsaarland/aligning-LLMs-with-political-views/src/inference.py 223868879693b620 ran · our draft was wrong no licence file found · pointer only
InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales 19 Jun 2024 weizhepei/instructrag/src/data_utils.py 106a37e7db749702 unverified MIT (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/language-modeling/hellaswag.py 28110ec97c757855 ran Apache-2.0 (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/language-modeling/story_cloze.py 11065df7f8515818 ran Apache-2.0 (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/language-modeling/winograd.py 522de10ce348cb0c ran Apache-2.0 (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/glue/glue.py 8131636afc6ecc7d ran Apache-2.0 (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/glue/multirc.py 1edc73f4d0b284d9 ran Apache-2.0 (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/needle-in-a-haystack/haystack.py 67264be51677507e ran Apache-2.0 (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/question-answering/arc.py f423eb95fad23611 ran Apache-2.0 (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/question-answering/natural_questions.py 4f852be96a94479f ran Apache-2.0 (permissive)
BERTs are Generative In-Context Learners 7 Jun 2024 ltgoslo/bert-in-context/question-answering/openbookqa.py 41aac6a681c0af69 ran Apache-2.0 (permissive)
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models 27 May 2024 ShengYun-Peng/llm-landscape/src/llm/util.py c50b059fdffe4c7c unverified MIT (permissive)
From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models 24 Apr 2024 meowpass/followcomplexinstruction/get_data/do_inference.py ee0fb943a653c769 unverified no licence file found · pointer only
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes 28 Mar 2024 jxbbb/tod3cap/tod3cap_camera/llama/utils.py 7006a7479b6f348f ran fingerprinted no licence file found · pointer only
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That? 11 Mar 2024 egozverev/Shold-It-Be-Executed-Or-Processed/model_eval/get_model_outputs.py ed71b768b354fced ran MIT (permissive)
Personalized Language Modeling from Personalized Human Feedback 6 Feb 2024 humainlab/personalized_rlhf/evaluate/alpaca_farm/data_preprocessor.py a71a4bdc37586fe2 ran MIT (permissive)
Corrective Retrieval Augmented Generation 29 Jan 2024 huskyinsalt/crag/scripts/CRAG_Inference.py 3881f4fd643eb25c ran · our draft was wrong fingerprinted no licence file found · pointer only
ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization 13 Jan 2024 ac-rad/organa/exp_task_manager.py 53def563fe69199b ran no licence file found · pointer only
ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization 13 Jan 2024 ac-rad/organa/nlp_service.py de90ed129c9b8178 ran no licence file found · pointer only
CLadder: Assessing Causal Reasoning in Language Models 7 Dec 2023 causalNLP/cladder/causalbenchmark/eval/generate_data_llama.py a5a90249b782a1b6 ran MIT (permissive)
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models 27 Nov 2023 epfllm/meditron/evaluation/inference.py 1ababc7e1e681f41 ran Apache-2.0 (permissive)
GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs 8 Nov 2023 umass-foundation-model/genome/engine/prompt.py 8a2d342cd5ddce4c unverified Apache-2.0 (permissive)
Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging 17 Oct 2023 joeljang/rlphf/gpt4_evaluate/alpaca_farm/data_preprocessor.py a71a4bdc37586fe2 ran no licence file found · pointer only
Misusing Tools in Large Language Models With Visual Adversarial Examples 4 Oct 2023 ZihanWangKi/VLMToolMisuse/llama_adapter/utils.py 7006a7479b6f348f ran fingerprinted no licence file found · pointer only
Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF 16 Sep 2023 simengsun/alpaca_farm_lora/alpaca_farm/src/alpaca_farm/data_preprocessor.py 5ef0d2db8e674cd5 ran Apache-2.0 (permissive)
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following 1 Sep 2023 ziyuguo99/point-bind_point-llm/Point-LLM/llama/utils.py b58b8fd28d0ff117 ran fingerprinted MIT (permissive)
MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks 28 Apr 2023 microsoft/CoML/coml/configagent/suggest.py 8a9ff381ef3920b0 unverified MIT (permissive)
Improving Code Generation by Training with Natural Language Feedback 28 Mar 2023 nyu-mll/ILF-for-code-generation/create_finetuning_data_from_refinements.py d661e4c718b84a32 ran · our draft was wrong MIT (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