{"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/llm4mat-bench-benchmarking-large-language","title":"LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction","arxiv_id":"2411.00177","date":"2024-10-31","proceeding":null,"authors":["Andre Niyongabo Rubungo","Kangming Li","Jason Hattrick-Simpers","Adji Bousso Dieng"],"abstract":"Large language models (LLMs) are increasingly being used in materials science. However, little attention has been given to benchmarking and standardized evaluation for LLM-based materials property prediction, which hinders progress. We present LLM4Mat-Bench, the largest benchmark to date for evaluating the performance of LLMs in predicting the properties of crystalline materials. LLM4Mat-Bench contains about 1.9M crystal structures in total, collected from 10 publicly available materials data sources, and 45 distinct properties. LLM4Mat-Bench features different input modalities: crystal composition, CIF, and crystal text description, with 4.7M, 615.5M, and 3.1B tokens in total for each modality, respectively. We use LLM4Mat-Bench to fine-tune models with different sizes, including LLM-Prop and MatBERT, and provide zero-shot and few-shot prompts to evaluate the property prediction capabilities of LLM-chat-like models, including Llama, Gemma, and Mistral. The results highlight the challenges of general-purpose LLMs in materials science and the need for task-specific predictive models and task-specific instruction-tuned LLMs in materials property prediction.","url_abs":"https://arxiv.org/abs/2411.00177v3","url_pdf":"https://arxiv.org/pdf/2411.00177v3.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":"llm4mat-bench-benchmarking-large-language","repo_url":"https://github.com/vertaix/llm4mat-bench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.00177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00177"}},"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/vertaix/llm4mat-bench","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"398618b957273bc6","entry":"extract_ans_from_chat_llm","repo":"vertaix/llm4mat-bench","repo_kind":"official","path":"code/llama/llama_inference.py","file_url":"https://github.com/vertaix/llm4mat-bench/blob/HEAD/code/llama/llama_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"398618b957273bc6"}},{"code_sha256_prefix":"c3ac3f45dbcaa8c0","entry":"extract_ans_from_next_token_llm","repo":"vertaix/llm4mat-bench","repo_kind":"official","path":"code/llama/llama_inference.py","file_url":"https://github.com/vertaix/llm4mat-bench/blob/HEAD/code/llama/llama_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3ac3f45dbcaa8c0"}},{"code_sha256_prefix":"e4367e1bb4066106","entry":"readJSON","repo":"vertaix/llm4mat-bench","repo_kind":"official","path":"code/llama/llama_inference.py","file_url":"https://github.com/vertaix/llm4mat-bench/blob/HEAD/code/llama/llama_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e4367e1bb4066106"}},{"code_sha256_prefix":"3de2652a4ecfff48","entry":"evaluate","repo":"vertaix/llm4mat-bench","repo_kind":"official","path":"code/llmprop_and_matbert/evaluate.py","file_url":"https://github.com/vertaix/llm4mat-bench/blob/HEAD/code/llmprop_and_matbert/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3de2652a4ecfff48"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}