{"work":{"id":"bb1fd52f-6b2f-437c-9516-37bdf6eb9be8","openalex_id":null,"doi":null,"arxiv_id":"2309.16609","raw_key":null,"title":"Qwen Technical Report","authors":null,"authors_text":"Qwen technical report , author=","year":2023,"venue":"cs.CL","abstract":"Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a multitude of downstream tasks, and the chat models, particularly those trained using Reinforcement Learning from Human Feedback (RLHF), are highly competitive. The chat models possess advanced tool-use and planning capabilities for creating agent applications, showcasing impressive performance even when compared to bigger models on complex tasks like utilizing a code interpreter. Furthermore, we have developed coding-specialized models, Code-Qwen and Code-Qwen-Chat, as well as mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These models demonstrate significantly improved performance in comparison with open-source models, and slightly fall behind the proprietary models.","external_url":"https://arxiv.org/abs/2309.16609","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-06-29T12:13:27.340422+00:00","pith_arxiv_id":"2309.16609","created_at":"2026-05-09T05:45:22.024718+00:00","updated_at":"2026-06-29T12:13:27.340422+00:00","title_quality_ok":false,"display_title":"Qwen Technical Report","render_title":"Qwen Technical Report"},"hub":{"state":{"work_id":"bb1fd52f-6b2f-437c-9516-37bdf6eb9be8","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":436,"external_cited_by_count":null,"distinct_field_count":23,"first_pith_cited_at":"2023-03-31T17:28:46+00:00","last_pith_cited_at":"2026-06-25T21:24:17+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-29T12:18:45.753633+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":82},{"context_role":"baseline","n":16},{"context_role":"method","n":16},{"context_role":"dataset","n":1},{"context_role":"extension","n":1},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":78},{"context_polarity":"baseline","n":16},{"context_polarity":"use_method","n":16},{"context_polarity":"unclear","n":4},{"context_polarity":"extend","n":1},{"context_polarity":"support","n":1},{"context_polarity":"use_dataset","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Qwen Technical Report","claims":[{"claim_text":"Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a mult","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Qwen Technical Report because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:03:32.409457+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"475adb1b-1a75-4cf0-a387-626be216b9bd","orcid":null,"display_name":"Qwen technical report"},{"id":"fe4d5dbf-e369-4296-8f93-544d5ed81b09","orcid":null,"display_name":"author="}]},"error":null,"updated_at":"2026-05-13T20:03:32.406974+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-13T20:03:31.836865+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":66},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":51},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":41},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":41},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":39},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":31},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":30},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":27},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":22},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":22},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":22},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":21},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":20},{"title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","work_id":"a7e3a737-e007-42bc-be89-c4d34c5ee071","shared_citers":19},{"title":"Qwen2.5 Technical Report","work_id":"d8432992-4980-4a81-85c7-9fa2c2b87f85","shared_citers":19},{"title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","work_id":"8abcfe4f-e0fb-44b7-9123-448fac95f90a","shared_citers":19},{"title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","work_id":"80e3e977-f1bb-4c83-8d0c-1ab0a0c5c3f1","shared_citers":18},{"title":"GPT-4o System Card","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","shared_citers":18},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":17},{"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","shared_citers":17},{"title":"Qwen2 Technical Report","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","shared_citers":17},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":16},{"title":"Gemma: Open Models Based on Gemini Research and Technology","work_id":"a9ea2870-df28-40b8-a9e0-a7e9a116f793","shared_citers":15},{"title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","shared_citers":15}],"time_series":[{"n":4,"year":2023},{"n":17,"year":2024},{"n":5,"year":2025},{"n":173,"year":2026}]},"error":null,"updated_at":"2026-05-13T20:03:31.947561+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"fixed":1,"items":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-13T20:03:30.879234+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Qwen Technical Report","claims":[{"claim_text":"Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a mult","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Qwen Technical Report because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:03:31.841719+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Qwen Technical Report","claims":[{"claim_text":"Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a mult","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Qwen Technical Report because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T20:03:31.839913+00:00"}},"summary":{"title":"Qwen Technical Report","claims":[{"claim_text":"Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a mult","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Qwen Technical Report because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":66},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":51},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":41},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":41},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":39},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":31},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":30},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":27},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":22},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":22},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":22},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":21},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":20},{"title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","work_id":"a7e3a737-e007-42bc-be89-c4d34c5ee071","shared_citers":19},{"title":"Qwen2.5 Technical Report","work_id":"d8432992-4980-4a81-85c7-9fa2c2b87f85","shared_citers":19},{"title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","work_id":"8abcfe4f-e0fb-44b7-9123-448fac95f90a","shared_citers":19},{"title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","work_id":"80e3e977-f1bb-4c83-8d0c-1ab0a0c5c3f1","shared_citers":18},{"title":"GPT-4o System Card","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","shared_citers":18},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":17},{"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","shared_citers":17},{"title":"Qwen2 Technical Report","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","shared_citers":17},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":16},{"title":"Gemma: Open Models Based on Gemini Research and Technology","work_id":"a9ea2870-df28-40b8-a9e0-a7e9a116f793","shared_citers":15},{"title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","shared_citers":15}],"time_series":[{"n":4,"year":2023},{"n":17,"year":2024},{"n":5,"year":2025},{"n":173,"year":2026}]},"authors":[{"id":"fe4d5dbf-e369-4296-8f93-544d5ed81b09","orcid":null,"display_name":"author=","source":"manual","import_confidence":0.72},{"id":"475adb1b-1a75-4cf0-a387-626be216b9bd","orcid":null,"display_name":"Qwen technical report","source":"manual","import_confidence":0.72}]}}