{"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/cache-me-if-you-can-an-online-cost-aware","title":"Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models","arxiv_id":"2310.13395","date":"2023-10-20","proceeding":null,"authors":["Ilias Stogiannidis","Stavros Vassos","Prodromos Malakasiotis","Ion Androutsopoulos"],"abstract":"Prompting Large Language Models (LLMs) performs impressively in zero- and few-shot settings. Hence, small and medium-sized enterprises (SMEs) that cannot afford the cost of creating large task-specific training datasets, but also the cost of pretraining their own LLMs, are increasingly turning to third-party services that allow them to prompt LLMs. However, such services currently require a payment per call, which becomes a significant operating expense (OpEx). Furthermore, customer inputs are often very similar over time, hence SMEs end-up prompting LLMs with very similar instances. We propose a framework that allows reducing the calls to LLMs by caching previous LLM responses and using them to train a local inexpensive model on the SME side. The framework includes criteria for deciding when to trust the local model or call the LLM, and a methodology to tune the criteria and measure the tradeoff between performance and cost. For experimental purposes, we instantiate our framework with two LLMs, GPT-3.5 or GPT-4, and two inexpensive students, a k-NN classifier or a Multi-Layer Perceptron, using two common business tasks, intent recognition and sentiment analysis. Experimental results indicate that significant OpEx savings can be obtained with only slightly lower performance.","url_abs":"https://arxiv.org/abs/2310.13395v1","url_pdf":"https://arxiv.org/pdf/2310.13395v1.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":"cache-me-if-you-can-an-online-cost-aware","repo_url":"https://github.com/stoyian/OCaTS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"intent-detection","task_name":"Intent Detection"},{"task_slug":"intent-recognition","task_name":"Intent Recognition"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"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":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"k-nn","method_name":"k-NN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/intent-detection-on-banking77","task":"Intent Detection","dataset":"BANKING77","model":"OCaTS (kNN-GPT-4)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy (%)":"82.7"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"OCaTS (kNN & GPT-3.5-turbo","rank_in_archive_order":29,"of":49,"metrics":{"Accuracy":"93.06"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.13395","atlas_url":"https://app.syntology.ai/?focus=2310.13395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13395"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/stoyian/OCaTS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"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":"691f8679fc4e3729","entry":"register_class","repo":"stoyian/OCaTS","repo_kind":"official","path":"src/caches/base.py","file_url":"https://github.com/stoyian/OCaTS/blob/HEAD/src/caches/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"691f8679fc4e3729"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}