{"task":"answerability prediction","dataset":"PeerQA","metric_names":["Macro F1"],"rows":[{"id":146536,"task":"answerability prediction","parent_task":null,"dataset":"PeerQA","model_name":"Mistral-IT-v02-7B-32k","metrics":{"Macro F1":"0.4703"},"paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","paper_date":"2023-10-10","code_links":[{"title":"mistralai/mistral-src","url":"https://github.com/mistralai/mistral-src"},{"title":"facebookresearch/fairseq2","url":"https://github.com/facebookresearch/fairseq2"},{"title":"mgmalek/efficient_cross_entropy","url":"https://github.com/mgmalek/efficient_cross_entropy"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"knowlab/bi-weekly-paper-presentation","url":"https://github.com/knowlab/bi-weekly-paper-presentation"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mistral"}],"metrics_order":"[\"Macro F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":146537,"task":"answerability prediction","parent_task":null,"dataset":"PeerQA","model_name":"Command-R-v01-34B-128k","metrics":{"Macro F1":"0.4197"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Macro F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":146538,"task":"answerability prediction","parent_task":null,"dataset":"PeerQA","model_name":"GPT-3.5-Turbo-0613-16k","metrics":{"Macro F1":"0.3304"},"paper_url":"https://arxiv.org/abs/2005.14165v4","paper_title":"Language Models are Few-Shot Learners","paper_date":"2020-05-28","code_links":[{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"karpathy/llm.c","url":"https://github.com/karpathy/llm.c"},{"title":"openai/gpt-3","url":"https://github.com/openai/gpt-3"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt-3"},{"title":"EleutherAI/lm_evaluation_harness","url":"https://github.com/EleutherAI/lm_evaluation_harness"},{"title":"EleutherAI/lm-evaluation-harness","url":"https://github.com/EleutherAI/lm-evaluation-harness"},{"title":"EleutherAI/gpt-neo","url":"https://github.com/EleutherAI/gpt-neo"},{"title":"karpathy/build-nanogpt","url":"https://github.com/karpathy/build-nanogpt"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"bigscience-workshop/Megatron-DeepSpeed","url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed"},{"title":"NVIDIA/NeMo-Curator","url":"https://github.com/NVIDIA/NeMo-Curator"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"allenai/macaw","url":"https://github.com/allenai/macaw"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"tonyzhaozh/few-shot-learning","url":"https://github.com/tonyzhaozh/few-shot-learning"},{"title":"haiyang-w/git","url":"https://github.com/haiyang-w/git"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/gpt"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"ethanjperez/true_few_shot","url":"https://github.com/ethanjperez/true_few_shot"},{"title":"ai21labs/lm-evaluation","url":"https://github.com/ai21labs/lm-evaluation"},{"title":"lambert-x/prolab","url":"https://github.com/lambert-x/prolab"},{"title":"asahi417/relbert","url":"https://github.com/asahi417/relbert"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"turkunlp/megatron-deepspeed","url":"https://github.com/turkunlp/megatron-deepspeed"},{"title":"contextlab/abstract2paper","url":"https://github.com/contextlab/abstract2paper"},{"title":"kyegomez/GPT3","url":"https://github.com/kyegomez/GPT3"},{"title":"Samyu0304/thought-propagation","url":"https://github.com/Samyu0304/thought-propagation"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"smile-data/smile","url":"https://github.com/smile-data/smile"},{"title":"postech-ami/smile-dataset","url":"https://github.com/postech-ami/smile-dataset"},{"title":"opengptx/lm-evaluation-harness","url":"https://github.com/opengptx/lm-evaluation-harness"},{"title":"gmum/dl-mo-2021","url":"https://github.com/gmum/dl-mo-2021"},{"title":"fywalter/label-bias","url":"https://github.com/fywalter/label-bias"},{"title":"nlx-group/overlapy","url":"https://github.com/nlx-group/overlapy"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"insait-institute/lm-evaluation-harness-bg","url":"https://github.com/insait-institute/lm-evaluation-harness-bg"},{"title":"x-lance/neusym-rag","url":"https://github.com/x-lance/neusym-rag"},{"title":"crazydigger/Callibration-of-GPT","url":"https://github.com/crazydigger/Callibration-of-GPT"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"vilm-ai/viet-llm-eval","url":"https://github.com/vilm-ai/viet-llm-eval"},{"title":"roberttwomey/machine-imagination-workshop","url":"https://github.com/roberttwomey/machine-imagination-workshop"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"neuralmagic/lm-evaluation-harness","url":"https://github.com/neuralmagic/lm-evaluation-harness"},{"title":"scrayish/ML_NLP","url":"https://github.com/scrayish/ML_NLP"},{"title":"sambanova/lm-evaluation-harness","url":"https://github.com/sambanova/lm-evaluation-harness"},{"title":"roberttwomey/machine-imagination-isea","url":"https://github.com/roberttwomey/machine-imagination-isea"},{"title":"ltruncel/Microsoft_Azure_50daysofudacity","url":"https://github.com/ltruncel/Microsoft_Azure_50daysofudacity"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"juletx/lm-evaluation-harness","url":"https://github.com/juletx/lm-evaluation-harness"},{"title":"national-center-for-ai-saudi-arabia/lm-evaluation-harness","url":"https://github.com/national-center-for-ai-saudi-arabia/lm-evaluation-harness"},{"title":"hilberthit/gpt-3","url":"https://github.com/hilberthit/gpt-3"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"EightRice/atn_GPT-3","url":"https://github.com/EightRice/atn_GPT-3"},{"title":"Mind23-2/MindCode-138","url":"https://github.com/Mind23-2/MindCode-138"},{"title":"mbzuai-paris/lm-evaluation-harness-atlas-chat","url":"https://github.com/mbzuai-paris/lm-evaluation-harness-atlas-chat"},{"title":"Sypherd/lm-evaluation-harness","url":"https://github.com/Sypherd/lm-evaluation-harness"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"},{"title":"zphang/lm_evaluation_harness","url":"https://github.com/zphang/lm_evaluation_harness"}],"metrics_order":"[\"Macro F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":146539,"task":"answerability prediction","parent_task":null,"dataset":"PeerQA","model_name":"Llama-3-IT-8B-8k","metrics":{"Macro F1":"0.3112"},"paper_url":"https://arxiv.org/abs/2407.21783v3","paper_title":"The Llama 3 Herd of Models","paper_date":"2024-07-31","code_links":[{"title":"zhuzilin/ring-flash-attention","url":"https://github.com/zhuzilin/ring-flash-attention"},{"title":"wenet-e2e/west","url":"https://github.com/wenet-e2e/west"},{"title":"zechenli03/sensorllm","url":"https://github.com/zechenli03/sensorllm"},{"title":"ziye2chen/LLMs-for-Mathematical-Analysis","url":"https://github.com/ziye2chen/LLMs-for-Mathematical-Analysis"},{"title":"willemsenbram/mention-detection-vgd","url":"https://github.com/willemsenbram/mention-detection-vgd"}],"metrics_order":"[\"Macro F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":146540,"task":"answerability prediction","parent_task":null,"dataset":"PeerQA","model_name":"GPT-4o-2024-08-06","metrics":{"Macro F1":"0.3087"},"paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","paper_date":"2023-03-15","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"metrics_order":"[\"Macro F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":146541,"task":"answerability prediction","parent_task":null,"dataset":"PeerQA","model_name":"Llama-3-IT-8B-32k","metrics":{"Macro F1":"0.2881"},"paper_url":"https://arxiv.org/abs/2407.21783v3","paper_title":"The Llama 3 Herd of Models","paper_date":"2024-07-31","code_links":[{"title":"zhuzilin/ring-flash-attention","url":"https://github.com/zhuzilin/ring-flash-attention"},{"title":"wenet-e2e/west","url":"https://github.com/wenet-e2e/west"},{"title":"zechenli03/sensorllm","url":"https://github.com/zechenli03/sensorllm"},{"title":"ziye2chen/LLMs-for-Mathematical-Analysis","url":"https://github.com/ziye2chen/LLMs-for-Mathematical-Analysis"},{"title":"willemsenbram/mention-detection-vgd","url":"https://github.com/willemsenbram/mention-detection-vgd"}],"metrics_order":"[\"Macro F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}