{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/formatting-prompts-func","entry":"formatting_prompts_func","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":14,"n_papers_ran":12,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":14,"n_samples_ran":12,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":6,"ran_fixture":0,"ran":6,"unverified":2},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2411.04991","paper":"/paper/rethinking-bradley-terry-models-in-preference","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"holarissun/rewardmodelingbeyondbradleyterry","path":"step1_sft.py","file_url":"https://github.com/holarissun/rewardmodelingbeyondbradleyterry/blob/HEAD/step1_sft.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"825c9fb07509b2a6","mcp_get_code":{"code_sha256":"825c9fb07509b2a6"}},{"arxiv_id":"2411.01855","paper":"/paper/can-language-models-learn-to-skip-steps","title":"Can Language Models Learn to Skip Steps?","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tengxiaoliu/lm_skip","path":"src/sft.py","file_url":"https://github.com/tengxiaoliu/lm_skip/blob/HEAD/src/sft.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6971550400aee17b","mcp_get_code":{"code_sha256":"6971550400aee17b"}},{"arxiv_id":"2410.14204","paper":"/paper/meditod-an-english-dialogue-dataset-for","title":"MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dair-iitd/MediTOD","path":"src/llama/infer.py","file_url":"https://github.com/dair-iitd/MediTOD/blob/HEAD/src/llama/infer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7c2702021405a385","mcp_get_code":{"code_sha256":"7c2702021405a385"}},{"arxiv_id":"2410.13828","paper":"/paper/a-common-pitfall-of-margin-based-language","title":"A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"humainlab/understand_marginpo","path":"sft.py","file_url":"https://github.com/humainlab/understand_marginpo/blob/HEAD/sft.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4fc874bb9bf50168","mcp_get_code":{"code_sha256":"4fc874bb9bf50168"}},{"arxiv_id":"2410.05269","paper":"/paper/data-advisor-dynamic-data-curation-for-safety","title":"Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feiwang96/Data-Advisor","path":"train_target_model.py","file_url":"https://github.com/feiwang96/Data-Advisor/blob/HEAD/train_target_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"992c9f47d47101c4","mcp_get_code":{"code_sha256":"992c9f47d47101c4"}},{"arxiv_id":"2405.02466","paper":"/paper/proflingo-a-fingerprinting-based-copyright","title":"ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models","date":"2024-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hengvt/proflingo","path":"finetuning.py","file_url":"https://github.com/hengvt/proflingo/blob/HEAD/finetuning.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1493a5222e81fedc","mcp_get_code":{"code_sha256":"1493a5222e81fedc"}},{"arxiv_id":"2402.18913","paper":"/paper/adamergex-cross-lingual-transfer-with-large","title":"AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/adamergex","path":"train_lora.py","file_url":"https://github.com/damo-nlp-sg/adamergex/blob/HEAD/train_lora.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aaeaf5967a619b25","mcp_get_code":{"code_sha256":"aaeaf5967a619b25"}},{"arxiv_id":"2402.18815","paper":"/paper/how-do-large-language-models-handle","title":"How do Large Language Models Handle Multilingualism?","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/multilingual_analysis","path":"neuron_enhancement/train_neuron.py","file_url":"https://github.com/damo-nlp-sg/multilingual_analysis/blob/HEAD/neuron_enhancement/train_neuron.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ef2b510b7d7a78bb","mcp_get_code":{"code_sha256":"ef2b510b7d7a78bb"}},{"arxiv_id":"2402.16472","paper":"/paper/medit-multilingual-text-editing-via","title":"mEdIT: Multilingual Text Editing via Instruction Tuning","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vipulraheja/medit","path":"train/medit_trainer.py","file_url":"https://github.com/vipulraheja/medit/blob/HEAD/train/medit_trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"62e3bb6f4bbb82a4","mcp_get_code":{"code_sha256":"62e3bb6f4bbb82a4"}},{"arxiv_id":"2402.07844","paper":"/paper/mercury-an-efficiency-benchmark-for-llm-code","title":"Mercury: A Code Efficiency Benchmark for Code Large Language Models","date":"2024-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elfsong/mercury","path":"src/sft_train.py","file_url":"https://github.com/elfsong/mercury/blob/HEAD/src/sft_train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f0b76e881e34bb03","mcp_get_code":{"code_sha256":"f0b76e881e34bb03"}},{"arxiv_id":"2309.13734","paper":"/paper/use-of-large-language-models-for-stance","title":"Prompting and Fine-Tuning Open-Sourced Large Language Models for Stance Classification","date":"2023-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ijcruic/llm-stance-labeling","path":"fine_tune_models.py","file_url":"https://github.com/ijcruic/llm-stance-labeling/blob/HEAD/fine_tune_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"63c1e5c6dc5be2f7","mcp_get_code":{"code_sha256":"63c1e5c6dc5be2f7"}},{"arxiv_id":"2308.02151","paper":"/paper/retroformer-retrospective-large-language","title":"Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weirayao/retroformer","path":"sft_run.py","file_url":"https://github.com/weirayao/retroformer/blob/HEAD/sft_run.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b5e1f1931c2b8747","mcp_get_code":{"code_sha256":"b5e1f1931c2b8747"}},{"arxiv_id":"2305.14314","paper":"/paper/qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daniel-furman/sft-demos","path":"_peft/falcon/peft_falcon_180b_instruct.py","file_url":"https://github.com/daniel-furman/sft-demos/blob/HEAD/_peft/falcon/peft_falcon_180b_instruct.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ba51656a6aaea3b7","mcp_get_code":{"code_sha256":"ba51656a6aaea3b7"}},{"arxiv_id":"2305.13269","paper":"/paper/chain-of-knowledge-a-framework-for-grounding","title":"Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/chain-of-knowledge","path":"finetune/sft_trainer.py","file_url":"https://github.com/damo-nlp-sg/chain-of-knowledge/blob/HEAD/finetune/sft_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"568afe28168c3da5","mcp_get_code":{"code_sha256":"568afe28168c3da5"}}]}