{"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":"/paper/llm-blender-ensembling-large-language-models","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","arxiv_id":"2306.02561","date":"2023-06-05","proceeding":null,"authors":["Dongfu Jiang","Xiang Ren","Bill Yuchen Lin"],"abstract":"We present LLM-Blender, an ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths of multiple open-source large language models (LLMs). Our framework consists of two modules: PairRanker and GenFuser, addressing the observation that optimal LLMs for different examples can significantly vary. PairRanker employs a specialized pairwise comparison method to distinguish subtle differences between candidate outputs. It jointly encodes the input text and a pair of candidates, using cross-attention encoders to determine the superior one. Our results demonstrate that PairRanker exhibits the highest correlation with ChatGPT-based ranking. Then, GenFuser aims to merge the top-ranked candidates, generating an improved output by capitalizing on their strengths and mitigating their weaknesses. To facilitate large-scale evaluation, we introduce a benchmark dataset, MixInstruct, which is a mixture of multiple instruction datasets featuring oracle pairwise comparisons. Our LLM-Blender significantly outperform individual LLMs and baseline methods across various metrics, establishing a substantial performance gap.","url_abs":"https://arxiv.org/abs/2306.02561v3","url_pdf":"https://arxiv.org/pdf/2306.02561v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"llm-blender-ensembling-large-language-models","repo_url":"https://github.com/yuchenlin/LLM-Blender","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"llm-blender-ensembling-large-language-models","repo_url":"https://github.com/baaivision/judgelm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"llm-blender-ensembling-large-language-models","repo_url":"https://github.com/cnut1648/Model-Fingerprint","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.02561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02561"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baaivision/judgelm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuchenlin/LLM-Blender","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cnut1648/Model-Fingerprint","reach":null}],"summary":{"ran":1,"unverified":9},"by_repo_kind":{"official":{"samples":10,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"81990a380398703e","entry":"get_torch_dtype","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/blender/blender_utils.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/blender/blender_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81990a380398703e"}},{"code_sha256_prefix":"6c3c4fd80392b2b3","entry":"ListMLE_loss","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/pair_ranker/loss.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/pair_ranker/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c3c4fd80392b2b3"}},{"code_sha256_prefix":"918c37e6d590c221","entry":"ListNet_loss","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/pair_ranker/loss.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/pair_ranker/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"918c37e6d590c221"}},{"code_sha256_prefix":"59209a93cb9f6249","entry":"beam_search_step","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/candidates_generation/engine.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/candidates_generation/engine.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59209a93cb9f6249"}},{"code_sha256_prefix":"f959a13305017609","entry":"build_model","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/candidates_generation/model_utils.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/candidates_generation/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f959a13305017609"}},{"code_sha256_prefix":"c6530fc447002e2f","entry":"build_pretrained_model","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/pair_ranker/model_util.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/pair_ranker/model_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6530fc447002e2f"}},{"code_sha256_prefix":"55761e9e27661128","entry":"build_ranker","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/pair_ranker/model_util.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/pair_ranker/model_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55761e9e27661128"}},{"code_sha256_prefix":"9e63c7f428bcf976","entry":"build_tokenizer","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/candidates_generation/model_utils.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/candidates_generation/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e63c7f428bcf976"}},{"code_sha256_prefix":"dea0c7d7d27028b1","entry":"build_tokenizer","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/pair_ranker/model_util.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/pair_ranker/model_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dea0c7d7d27028b1"}},{"code_sha256_prefix":"c92f69693fc7c0e9","entry":"permutation_prob","repo":"yuchenlin/LLM-Blender","repo_kind":"official","path":"llm_blender/pair_ranker/loss.py","file_url":"https://github.com/yuchenlin/LLM-Blender/blob/HEAD/llm_blender/pair_ranker/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c92f69693fc7c0e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}