{"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/jload","entry":"jload","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":59,"n_papers_ran":52,"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":12,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":60,"n_places_pointer_only":23,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":4,"unverified":5},"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":"2609.01090","paper":"/paper/arxiv-2609-01090","title":"Modelpedia: A Catalog of Model Findings for the Meta-Science of AI","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"tatsu-lab/stanford_alpaca","path":"utils.py","file_url":"https://github.com/tatsu-lab/stanford_alpaca/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2606.17249","paper":"/paper/arxiv-2606-17249","title":"From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"emre1998/fastgrnn-har","path":"analyze_bootstrap.py","file_url":"https://github.com/emre1998/fastgrnn-har/blob/HEAD/analyze_bootstrap.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":"2a1e46172a51de87","mcp_get_code":{"code_sha256":"2a1e46172a51de87"}},{"arxiv_id":"2605.17352","paper":"/paper/arxiv-2605-17352","title":"AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"tatsu-lab/stanford_alpaca","path":"utils.py","file_url":"https://github.com/tatsu-lab/stanford_alpaca/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2604.12374","paper":"/paper/arxiv-2604-12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning NVIDIA","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"NVIDIA-NeMo/Skills","path":"nemo_skills/file_utils.py","file_url":"https://github.com/NVIDIA-NeMo/Skills/blob/HEAD/nemo_skills/file_utils.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":"8c48543062658550","mcp_get_code":{"code_sha256":"8c48543062658550"}},{"arxiv_id":"2603.22213","paper":"/paper/arxiv-2603-22213","title":"SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Tangkexian/SPA","path":"src/utils_tools/io_utils.py","file_url":"https://github.com/Tangkexian/SPA/blob/HEAD/src/utils_tools/io_utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2603.11940","paper":"/paper/arxiv-2603-11940","title":"Exhaustive Circuit Mapping of a Single-Cell Foundation Model Reveals Massive Redundancy, Heavy-Tailed Hub Architecture, and Layer-Dependent Differentiation Control","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Biodyn-AI/sae-biological-map","path":"src/revision/make_figures.py","file_url":"https://github.com/Biodyn-AI/sae-biological-map/blob/HEAD/src/revision/make_figures.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c0c8031ac6f0fc4","mcp_get_code":{"code_sha256":"8c0c8031ac6f0fc4"}},{"arxiv_id":"2504.16891","paper":"/paper/aimo-2-winning-solution-building-state-of-the","title":"AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset","date":"2025-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kipok/nemo-skills","path":"nemo_skills/file_utils.py","file_url":"https://github.com/kipok/nemo-skills/blob/HEAD/nemo_skills/file_utils.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":"8c48543062658550","mcp_get_code":{"code_sha256":"8c48543062658550"}},{"arxiv_id":"2502.12853","paper":"/paper/s-2-r-teaching-llms-to-self-verify-and-self","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","date":"2025-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nineabyss/s2r","path":"code/utils.py","file_url":"https://github.com/nineabyss/s2r/blob/HEAD/code/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"17c4e4f3635d3ee1","mcp_get_code":{"code_sha256":"17c4e4f3635d3ee1"}},{"arxiv_id":"2501.17433","paper":"/paper/virus-harmful-fine-tuning-attack-for-large","title":"Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation","date":"2025-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"git-disl/virus","path":"datasets_visualizer.py","file_url":"https://github.com/git-disl/virus/blob/HEAD/datasets_visualizer.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2412.11803","paper":"/paper/ualign-leveraging-uncertainty-estimations-for","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amourwaltz/ualign","path":"code/utils.py","file_url":"https://github.com/amourwaltz/ualign/blob/HEAD/code/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2410.10760","paper":"/paper/denial-of-service-poisoning-attacks-against","title":"Denial-of-Service Poisoning Attacks against Large Language Models","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/p-dos","path":"pdos_loss.py","file_url":"https://github.com/sail-sg/p-dos/blob/HEAD/pdos_loss.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2410.09760","paper":"/paper/targeted-vaccine-safety-alignment-for-large","title":"Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lslland/t-vaccine","path":"utils.py","file_url":"https://github.com/lslland/t-vaccine/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2410.05451","paper":"/paper/aligning-llms-to-be-robust-against-prompt","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/secalign","path":"struq.py","file_url":"https://github.com/facebookresearch/secalign/blob/HEAD/struq.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"331e906ad5e247b9","mcp_get_code":{"code_sha256":"331e906ad5e247b9"}},{"arxiv_id":"2410.01560","paper":"/paper/openmathinstruct-2-accelerating-ai-for-math","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA/NeMo-Skills","path":"nemo_skills/file_utils.py","file_url":"https://github.com/NVIDIA/NeMo-Skills/blob/HEAD/nemo_skills/file_utils.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":"8c48543062658550","mcp_get_code":{"code_sha256":"8c48543062658550"}},{"arxiv_id":"2409.18169","paper":"/paper/harmful-fine-tuning-attacks-and-defenses-for","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"git-disl/booster","path":"utils.py","file_url":"https://github.com/git-disl/booster/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2409.07431","paper":"/paper/synthetic-continued-pretraining","title":"Synthetic continued pretraining","date":"2024-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zitongyang/synthetic_continued_pretraining","path":"utils/io_utils.py","file_url":"https://github.com/zitongyang/synthetic_continued_pretraining/blob/HEAD/utils/io_utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2408.14774","paper":"/paper/instruct-skillmix-a-powerful-pipeline-for-llm","title":"Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning","date":"2024-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-pli/Instruct-SkillMix","path":"MAmmoTH/utils.py","file_url":"https://github.com/princeton-pli/Instruct-SkillMix/blob/HEAD/MAmmoTH/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2408.09600","paper":"/paper/antidote-post-fine-tuning-safety-alignment","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","date":"2024-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"git-disl/lisa","path":"utils.py","file_url":"https://github.com/git-disl/lisa/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2407.12404","paper":"/paper/analyzing-the-generalization-and-reliability","title":"Analyzing the Generalization and Reliability of Steering Vectors","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dtch1997/steering-bench","path":"steering_bench/utils/io.py","file_url":"https://github.com/dtch1997/steering-bench/blob/HEAD/steering_bench/utils/io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"856c8b4ec46ae412","mcp_get_code":{"code_sha256":"856c8b4ec46ae412"}},{"arxiv_id":"2407.10223","paper":"/paper/practical-unlearning-for-large-language","title":"On Large Language Model Continual Unlearning","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GCYZSL/O3-LLM-UNLEARNING","path":"ScienceQA_expriment/src/base_model_utils.py","file_url":"https://github.com/GCYZSL/O3-LLM-UNLEARNING/blob/HEAD/ScienceQA_expriment/src/base_model_utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2406.14024","paper":"/paper/the-reason-behind-good-or-bad-towards-a","title":"LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback","date":"2024-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kbsdjames/math-minos","path":"train_reward.py","file_url":"https://github.com/kbsdjames/math-minos/blob/HEAD/train_reward.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2406.05678","paper":"/paper/sinklora-enhanced-efficiency-and-chat","title":"SinkLoRA: Enhanced Efficiency and Chat Capabilities for Long-Context Large Language Models","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2406.02395","paper":"/paper/grootvl-tree-topology-is-all-you-need-in","title":"GrootVL: Tree Topology is All You Need in State Space Model","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"easonxiao-888/grootvl","path":"GrootL/supervised-fine-tune.py","file_url":"https://github.com/easonxiao-888/grootvl/blob/HEAD/GrootL/supervised-fine-tune.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2405.17381","paper":"/paper/various-lengths-constant-speed-efficient","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opennlplab/transnormerllm","path":"fine-tune/utils.py","file_url":"https://github.com/opennlplab/transnormerllm/blob/HEAD/fine-tune/utils.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c5247729979fd74","mcp_get_code":{"code_sha256":"5c5247729979fd74"}},{"arxiv_id":"2405.17381","paper":"/paper/various-lengths-constant-speed-efficient","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenNLPLab/TransnormerLLM","path":"fine-tune/utils.py","file_url":"https://github.com/OpenNLPLab/TransnormerLLM/blob/HEAD/fine-tune/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2405.14804","paper":"/paper/can-llms-solve-longer-math-word-problems","title":"Can LLMs Solve longer Math Word Problems Better?","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2405.13516","paper":"/paper/lire-listwise-reward-enhancement-for","title":"LIRE: listwise reward enhancement for preference alignment","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevie1023/LIRE","path":"train_alpaca_prompt.py","file_url":"https://github.com/stevie1023/LIRE/blob/HEAD/train_alpaca_prompt.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2405.06680","paper":"/paper/exploring-the-compositional-deficiency-of","title":"Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning","date":"2024-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tongjingqi/MathTrap","path":"train_math.py","file_url":"https://github.com/tongjingqi/MathTrap/blob/HEAD/train_math.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2404.02406","paper":"/paper/exploring-backdoor-vulnerabilities-of-chat","title":"Exploring Backdoor Vulnerabilities of Chat Models","date":"2024-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hychaochao/chat-models-backdoor-attacking","path":"Instructional_Model_Backdoor/utils.py","file_url":"https://github.com/hychaochao/chat-models-backdoor-attacking/blob/HEAD/Instructional_Model_Backdoor/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2403.15042","paper":"/paper/llm2llm-boosting-llms-with-novel-iterative","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"squeezeailab/llm2llm","path":"utils.py","file_url":"https://github.com/squeezeailab/llm2llm/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2403.09162","paper":"/paper/unveiling-the-generalization-power-of-fine","title":"Unveiling the Generalization Power of Fine-Tuned Large Language Models","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lhryang/generalization_of_ft-llm","path":"utils.py","file_url":"https://github.com/lhryang/generalization_of_ft-llm/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"220607d53f1814c7","mcp_get_code":{"code_sha256":"220607d53f1814c7"}},{"arxiv_id":"2402.11725","paper":"/paper/how-susceptible-are-large-language-models-to","title":"How Susceptible are Large Language Models to Ideological Manipulation?","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaichen23/llm_ideo_manipulate","path":"code/utils.py","file_url":"https://github.com/kaichen23/llm_ideo_manipulate/blob/HEAD/code/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2402.10430","paper":"/paper/smaller-language-models-are-capable-of","title":"Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dheeraj7596/small2large","path":"utils.py","file_url":"https://github.com/dheeraj7596/small2large/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2402.09773","paper":"/paper/nuteprune-efficient-progressive-pruning-with","title":"NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucius-lsr/nuteprune","path":"tasks/alpaca.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/tasks/alpaca.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2402.09642","paper":"/paper/answer-is-all-you-need-instruction-following","title":"Answer is All You Need: Instruction-following Text Embedding via Answering the Question","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhang-yu-wei/inbedder","path":"alpaca_train/utils.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/alpaca_train/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2402.06363","paper":"/paper/struq-defending-against-prompt-injection-with","title":"StruQ: Defending Against Prompt Injection with Structured Queries","date":null,"month_inferred_from_arxiv_id":"2024-02","title_source":"archive","repo":"sizhe-chen/struq","path":"struq.py","file_url":"https://github.com/sizhe-chen/struq/blob/HEAD/struq.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"331e906ad5e247b9","mcp_get_code":{"code_sha256":"331e906ad5e247b9"}},{"arxiv_id":"2312.14187","paper":"/paper/wavecoder-widespread-and-versatile-enhanced","title":"WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning","date":"2023-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/wavecoder","path":"src/train/utils.py","file_url":"https://github.com/microsoft/wavecoder/blob/HEAD/src/train/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2312.11875","paper":"/paper/sparse-is-enough-in-fine-tuning-pre-trained","title":"Sparse is Enough in Fine-tuning Pre-trained Large Language Models","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"song-wx/SIFT","path":"exp/instruction_finetuning/utils.py","file_url":"https://github.com/song-wx/SIFT/blob/HEAD/exp/instruction_finetuning/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2311.17154","paper":"/paper/pragmatic-radiology-report-generation","title":"Pragmatic Radiology Report Generation","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chicagohai/llm_radiology","path":"utils_finetune.py","file_url":"https://github.com/chicagohai/llm_radiology/blob/HEAD/utils_finetune.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2311.15653","paper":"/paper/mods-model-oriented-data-selection-for","title":"MoDS: Model-oriented Data Selection for Instruction Tuning","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"casia-lm/mods","path":"inference/utils.py","file_url":"https://github.com/casia-lm/mods/blob/HEAD/inference/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2310.11511","paper":"/paper/self-rag-learning-to-retrieve-generate-and","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AkariAsai/self-rag","path":"data_creation/train_special_tokens.py","file_url":"https://github.com/AkariAsai/self-rag/blob/HEAD/data_creation/train_special_tokens.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ca38f9acc00194b","mcp_get_code":{"code_sha256":"3ca38f9acc00194b"}},{"arxiv_id":"2310.10908","paper":"/paper/emergent-mixture-of-experts-can-dense-pre","title":"Unlocking Emergent Modularity in Large Language Models","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiuzh20/emoe","path":"EMoE_LLaMA/utils.py","file_url":"https://github.com/qiuzh20/emoe/blob/HEAD/EMoE_LLaMA/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2310.09168","paper":"/paper/explore-instruct-enhancing-domain-specific","title":"Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanqiwan/Explore-Instruct","path":"train/utils.py","file_url":"https://github.com/fanqiwan/Explore-Instruct/blob/HEAD/train/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2309.12307","paper":"/paper/longlora-efficient-fine-tuning-of-long","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","date":"2023-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/longlora","path":"supervised-fine-tune-qlora.py","file_url":"https://github.com/dvlab-research/longlora/blob/HEAD/supervised-fine-tune-qlora.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2309.12284","paper":"/paper/metamath-bootstrap-your-own-mathematical","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","date":"2023-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meta-math/MetaMath","path":"train_math.py","file_url":"https://github.com/meta-math/MetaMath/blob/HEAD/train_math.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2309.00237","paper":"/paper/publicly-shareable-clinical-large-language","title":"Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes","date":"2023-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"starmpcc/asclepius","path":"src/instruction_ft.py","file_url":"https://github.com/starmpcc/asclepius/blob/HEAD/src/instruction_ft.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":"0c9d19493ee33877","mcp_get_code":{"code_sha256":"0c9d19493ee33877"}},{"arxiv_id":"2308.12032","paper":"/paper/from-quantity-to-quality-boosting-llm","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingliiii/cherry_llm","path":"training/stanford_alpaca/utils.py","file_url":"https://github.com/mingliiii/cherry_llm/blob/HEAD/training/stanford_alpaca/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2308.06744","paper":"/paper/token-scaled-logit-distillation-for-ternary-1","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","date":"2023-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiha-lab/TSLD","path":"utils/alpaca_dataset.py","file_url":"https://github.com/aiha-lab/TSLD/blob/HEAD/utils/alpaca_dataset.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2308.06259","paper":"/paper/self-alignment-with-instruction","title":"Self-Alignment with Instruction Backtranslation","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidkim205/komt","path":"finetune_with_ds.py","file_url":"https://github.com/davidkim205/komt/blob/HEAD/finetune_with_ds.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2308.04948","paper":"/paper/extrapolating-large-language-models-to-non","title":"Extrapolating Large Language Models to Non-English by Aligning Languages","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NJUNLP/x-LLM","path":"utils.py","file_url":"https://github.com/NJUNLP/x-LLM/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2306.17194","paper":"/paper/on-the-exploitability-of-instruction-tuning-1","title":"On the Exploitability of Instruction Tuning","date":"2023-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"azshue/AutoPoison","path":"utils.py","file_url":"https://github.com/azshue/AutoPoison/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2305.14825","paper":"/paper/large-language-models-are-in-context-semantic","title":"Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaojuantang/icsr","path":"finetune/utils.py","file_url":"https://github.com/xiaojuantang/icsr/blob/HEAD/finetune/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2305.13068","paper":"/paper/making-language-models-better-tool-learners","title":"Making Language Models Better Tool Learners with Execution Feedback","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2305.12870","paper":"/paper/lion-adversarial-distillation-of-closed","title":"Lion: Adversarial Distillation of Proprietary Large Language Models","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yjiangcm/lion","path":"src/utils.py","file_url":"https://github.com/yjiangcm/lion/blob/HEAD/src/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2302.13971","paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aethercortex/llama-x","path":"src/utils.py","file_url":"https://github.com/aethercortex/llama-x/blob/HEAD/src/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2206.07023","paper":"/paper/sbert-studies-meaning-representations","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"flipz357/S3BERT","path":"src/data_helpers.py","file_url":"https://github.com/flipz357/S3BERT/blob/HEAD/src/data_helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1779ed436ac80094","mcp_get_code":{"code_sha256":"1779ed436ac80094"}},{"arxiv_id":"aaai_34662","paper":null,"title":"arXiv:aaai_34662","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"maxindian/3D-RPE-Long-Contex-Modeling","path":"sft_qlora_tuning.py","file_url":"https://github.com/maxindian/3D-RPE-Long-Contex-Modeling/blob/HEAD/sft_qlora_tuning.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"aaai_29784","paper":null,"title":"arXiv:aaai_29784","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HITsz-TMG/Ext-Sub","path":"training/utils.py","file_url":"https://github.com/HITsz-TMG/Ext-Sub/blob/HEAD/training/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2024.naacl-long.132","paper":null,"title":"arXiv:2024.naacl-long.132","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Kent0n-Li/ChatDoctor","path":"utils.py","file_url":"https://github.com/Kent0n-Li/ChatDoctor/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"arxiv_id":"2024.findings-acl.388","paper":null,"title":"arXiv:2024.findings-acl.388","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SqueezeAILab/LLM2LLM","path":"utils.py","file_url":"https://github.com/SqueezeAILab/LLM2LLM/blob/HEAD/utils.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":"d07d04439cd1d44f","mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}}]}