{"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/metallm-a-high-performant-and-cost-efficient","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","arxiv_id":"2407.10834","date":"2024-07-15","proceeding":null,"authors":["Quang H. Nguyen","Duy C. Hoang","Juliette Decugis","Saurav Manchanda","Nitesh V. Chawla","Khoa D. Doan"],"abstract":"The rapid progress in machine learning (ML) has brought forth many large language models (LLMs) that excel in various tasks and areas. These LLMs come with different abilities and costs in terms of computation or pricing. Since the demand for each query can vary, e.g., because of the queried domain or its complexity, defaulting to one LLM in an application is not usually the best choice, whether it is the biggest, priciest, or even the one with the best average test performance. Consequently, picking the right LLM that is both accurate and cost-effective for an application remains a challenge. In this paper, we introduce MetaLLM, a framework that dynamically and intelligently routes each query to the optimal LLM (among several available LLMs) for classification tasks, achieving significantly improved accuracy and cost-effectiveness. By framing the selection problem as a multi-armed bandit, MetaLLM balances prediction accuracy and cost efficiency under uncertainty. Our experiments, conducted on popular LLM platforms such as OpenAI's GPT models, Amazon's Titan, Anthropic's Claude, and Meta's LLaMa, showcase MetaLLM's efficacy in real-world scenarios, laying the groundwork for future extensions beyond classification tasks.","url_abs":"https://arxiv.org/abs/2407.10834v2","url_pdf":"https://arxiv.org/pdf/2407.10834v2.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":"metallm-a-high-performant-and-cost-efficient","repo_url":"https://github.com/mail-research/metallm-wrapper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.10834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10834"}},"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/mail-research/metallm-wrapper","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"10a73330aef4702b","entry":"build_prompt","repo":"mail-research/metallm-wrapper","repo_kind":"official","path":"benchmark.py","file_url":"https://github.com/mail-research/metallm-wrapper/blob/HEAD/benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"10a73330aef4702b"}},{"code_sha256_prefix":"88db7ece348edfb5","entry":"build_prompts","repo":"mail-research/metallm-wrapper","repo_kind":"official","path":"benchmark.py","file_url":"https://github.com/mail-research/metallm-wrapper/blob/HEAD/benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"88db7ece348edfb5"}},{"code_sha256_prefix":"a340f86444fc4c40","entry":"get_feat_e5","repo":"mail-research/metallm-wrapper","repo_kind":"official","path":"get_embedding_mmlu.py","file_url":"https://github.com/mail-research/metallm-wrapper/blob/HEAD/get_embedding_mmlu.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a340f86444fc4c40"}},{"code_sha256_prefix":"f51c3ee33b3c4b10","entry":"get_feat_mpnet","repo":"mail-research/metallm-wrapper","repo_kind":"official","path":"get_embedding_mmlu.py","file_url":"https://github.com/mail-research/metallm-wrapper/blob/HEAD/get_embedding_mmlu.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f51c3ee33b3c4b10"}},{"code_sha256_prefix":"8003ae884ff0ba3a","entry":"parse_output","repo":"mail-research/metallm-wrapper","repo_kind":"official","path":"benchmark.py","file_url":"https://github.com/mail-research/metallm-wrapper/blob/HEAD/benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"8003ae884ff0ba3a"}},{"code_sha256_prefix":"2ded070fabe7bdc7","entry":"last_token_pool","repo":"mail-research/metallm-wrapper","repo_kind":"official","path":"get_embedding_mmlu.py","file_url":"https://github.com/mail-research/metallm-wrapper/blob/HEAD/get_embedding_mmlu.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2ded070fabe7bdc7"}},{"code_sha256_prefix":"739e248d0a655bf6","entry":"split_data","repo":"mail-research/metallm-wrapper","repo_kind":"official","path":"online_router.py","file_url":"https://github.com/mail-research/metallm-wrapper/blob/HEAD/online_router.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"739e248d0a655bf6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}