{"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/a-sober-look-at-llms-for-material-discovery","title":"A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?","arxiv_id":"2402.05015","date":"2024-02-07","proceeding":null,"authors":["Agustinus Kristiadi","Felix Strieth-Kalthoff","Marta Skreta","Pascal Poupart","Alán Aspuru-Guzik","Geoff Pleiss"],"abstract":"Automation is one of the cornerstones of contemporary material discovery. Bayesian optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior domain knowledge into efficient exploration of a large molecular space. While such prior knowledge can take many forms, there has been significant fanfare around the ancillary scientific knowledge encapsulated in large language models (LLMs). However, existing work thus far has only explored LLMs for heuristic materials searches. Indeed, recent work obtains the uncertainty estimate -- an integral part of BO -- from point-estimated, non-Bayesian LLMs. In this work, we study the question of whether LLMs are actually useful to accelerate principled Bayesian optimization in the molecular space. We take a sober, dispassionate stance in answering this question. This is done by carefully (i) viewing LLMs as fixed feature extractors for standard but principled BO surrogate models and by (ii) leveraging parameter-efficient finetuning methods and Bayesian neural networks to obtain the posterior of the LLM surrogate. Our extensive experiments with real-world chemistry problems show that LLMs can be useful for BO over molecules, but only if they have been pretrained or finetuned with domain-specific data.","url_abs":"https://arxiv.org/abs/2402.05015v2","url_pdf":"https://arxiv.org/pdf/2402.05015v2.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":"a-sober-look-at-llms-for-material-discovery","repo_url":"https://github.com/wiseodd/lapeft-bayesopt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.05015","atlas_url":"https://app.syntology.ai/?focus=2402.05015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05015"}},"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/wiseodd/lapeft-bayesopt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"83d50f8a5494d246","entry":"average_llm_features","repo":"wiseodd/lapeft-bayesopt","repo_kind":"official","path":"lapeft_bayesopt/foundation_models/utils.py","file_url":"https://github.com/wiseodd/lapeft-bayesopt/blob/HEAD/lapeft_bayesopt/foundation_models/utils.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":"83d50f8a5494d246"}},{"code_sha256_prefix":"3a9bfdaebf982fb9","entry":"extract_last_llm_features","repo":"wiseodd/lapeft-bayesopt","repo_kind":"official","path":"lapeft_bayesopt/foundation_models/utils.py","file_url":"https://github.com/wiseodd/lapeft-bayesopt/blob/HEAD/lapeft_bayesopt/foundation_models/utils.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":"3a9bfdaebf982fb9"}},{"code_sha256_prefix":"a0638d33ba2b742d","entry":"pop_df","repo":"wiseodd/lapeft-bayesopt","repo_kind":"official","path":"lapeft_bayesopt/utils/helpers.py","file_url":"https://github.com/wiseodd/lapeft-bayesopt/blob/HEAD/lapeft_bayesopt/utils/helpers.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":"a0638d33ba2b742d"}},{"code_sha256_prefix":"93b8e2f052c8b17f","entry":"thompson_sampling","repo":"wiseodd/lapeft-bayesopt","repo_kind":"official","path":"lapeft_bayesopt/utils/acqf.py","file_url":"https://github.com/wiseodd/lapeft-bayesopt/blob/HEAD/lapeft_bayesopt/utils/acqf.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":"93b8e2f052c8b17f"}},{"code_sha256_prefix":"dbb9d23567214671","entry":"thompson_sampling_multivariate","repo":"wiseodd/lapeft-bayesopt","repo_kind":"official","path":"lapeft_bayesopt/utils/acqf.py","file_url":"https://github.com/wiseodd/lapeft-bayesopt/blob/HEAD/lapeft_bayesopt/utils/acqf.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":"dbb9d23567214671"}},{"code_sha256_prefix":"0ff5ff84b8f30ddc","entry":"ucb","repo":"wiseodd/lapeft-bayesopt","repo_kind":"official","path":"lapeft_bayesopt/utils/acqf.py","file_url":"https://github.com/wiseodd/lapeft-bayesopt/blob/HEAD/lapeft_bayesopt/utils/acqf.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":"0ff5ff84b8f30ddc"}},{"code_sha256_prefix":"8b676f1431f2afb3","entry":"y_transform","repo":"wiseodd/lapeft-bayesopt","repo_kind":"official","path":"lapeft_bayesopt/utils/helpers.py","file_url":"https://github.com/wiseodd/lapeft-bayesopt/blob/HEAD/lapeft_bayesopt/utils/helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b676f1431f2afb3"}},{"code_sha256_prefix":"1807fc85a9abfd0a","entry":"get_llama2_tokenizer","repo":"wiseodd/lapeft-bayesopt","repo_kind":"official","path":"lapeft_bayesopt/foundation_models/utils.py","file_url":"https://github.com/wiseodd/lapeft-bayesopt/blob/HEAD/lapeft_bayesopt/foundation_models/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1807fc85a9abfd0a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}