{"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/hlm-cite-hybrid-language-model-workflow-for","title":"HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction","arxiv_id":"2410.09112","date":"2024-10-10","proceeding":null,"authors":["Qianyue Hao","Jingyang Fan","Fengli Xu","Jian Yuan","Yong Li"],"abstract":"Citation networks are critical in modern science, and predicting which previous papers (candidates) will a new paper (query) cite is a critical problem. However, the roles of a paper's citations vary significantly, ranging from foundational knowledge basis to superficial contexts. Distinguishing these roles requires a deeper understanding of the logical relationships among papers, beyond simple edges in citation networks. The emergence of LLMs with textual reasoning capabilities offers new possibilities for discerning these relationships, but there are two major challenges. First, in practice, a new paper may select its citations from gigantic existing papers, where the texts exceed the context length of LLMs. Second, logical relationships between papers are implicit, and directly prompting an LLM to predict citations may result in surface-level textual similarities rather than the deeper logical reasoning. In this paper, we introduce the novel concept of core citation, which identifies the critical references that go beyond superficial mentions. Thereby, we elevate the citation prediction task from a simple binary classification to distinguishing core citations from both superficial citations and non-citations. To address this, we propose $\\textbf{HLM-Cite}$, a $\\textbf{H}$ybrid $\\textbf{L}$anguage $\\textbf{M}$odel workflow for citation prediction, which combines embedding and generative LMs. We design a curriculum finetune procedure to adapt a pretrained text embedding model to coarsely retrieve high-likelihood core citations from vast candidates and then design an LLM agentic workflow to rank the retrieved papers through one-shot reasoning, revealing the implicit relationships among papers. With the pipeline, we can scale the candidate sets to 100K papers. We evaluate HLM-Cite across 19 scientific fields, demonstrating a 17.6% performance improvement comparing SOTA methods.","url_abs":"https://arxiv.org/abs/2410.09112v1","url_pdf":"https://arxiv.org/pdf/2410.09112v1.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":"hlm-cite-hybrid-language-model-workflow-for","repo_url":"https://github.com/tsinghua-fib-lab/H-LM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"citation-prediction","task_name":"Citation Prediction"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.09112","atlas_url":"https://app.syntology.ai/?focus=2410.09112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09112"}},"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":"deterministic:regex_extraction","url":"https://github.com/tsinghua-fib-lab/H-LM","reach":{"status":"ok"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"df4f39f6cba1abae","entry":"loss_func","repo":"tsinghua-fib-lab/H-LM","repo_kind":"official","path":"code/model_train/functions.py","file_url":"https://github.com/tsinghua-fib-lab/H-LM/blob/HEAD/code/model_train/functions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df4f39f6cba1abae"}},{"code_sha256_prefix":"23ec52d5537994f3","entry":"test_cp_logits_topk","repo":"tsinghua-fib-lab/H-LM","repo_kind":"official","path":"code/functions.py","file_url":"https://github.com/tsinghua-fib-lab/H-LM/blob/HEAD/code/functions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23ec52d5537994f3"}},{"code_sha256_prefix":"da78af27b71bc211","entry":"average_pool","repo":"tsinghua-fib-lab/H-LM","repo_kind":"official","path":"code/model_train/functions.py","file_url":"https://github.com/tsinghua-fib-lab/H-LM/blob/HEAD/code/model_train/functions.py","link_basis":"harvester_set","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":"da78af27b71bc211"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}