{"id":"https://openalex.org/W7160891203","doi":"https://doi.org/10.48550/arxiv.2605.10831","title":"SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing","display_name":"SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160891203","doi":"https://doi.org/10.48550/arxiv.2605.10831"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10831","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10831","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.10831","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135926137","display_name":"Mingxu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Mingxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135926499","display_name":"Yuhan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yuhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008680227","display_name":"Leya Li","orcid":"https://orcid.org/0009-0001-6533-5034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Lujundong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135931839","display_name":"Dazhong Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Dazhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135949581","display_name":"Hui Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135952096","display_name":"Ying Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.5806999802589417,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.5806999802589417,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.12600000202655792,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.09200000017881393,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7117000222206116},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6116999983787537},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5946999788284302},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.583299994468689},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4099000096321106},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.40610000491142273},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.35749998688697815},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3571000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426999807357788},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7117000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6498000025749207},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6116999983787537},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5946999788284302},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10831","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10831","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10831","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10831","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"possess":[3],"strong":[4],"chemical":[5],"reasoning":[6],"capabilities,":[7],"making":[8],"them":[9],"effective":[10],"molecular":[11,117],"editors.":[12],"However,":[13],"property-relevant":[14,85],"information":[15],"is":[16],"implicitly":[17],"entangled":[18],"across":[19,111],"their":[20],"dense":[21],"hidden":[22,63],"states,":[23],"providing":[24],"no":[25],"explicit":[26],"handle":[27],"for":[28],"property":[29],"control:":[30],"a":[31,56,70],"substantial":[32],"fraction":[33],"of":[34,103,126],"edits":[35],"fail":[36],"to":[37,128],"improve":[38],"or":[39],"even":[40],"degrade":[41],"target":[42],"properties.":[43],"To":[44],"address":[45],"these":[46],"issues,":[47],"we":[48],"propose":[49],"SLIM":[50],"(Sparse":[51],"Latent":[52],"Interpretable":[53],"Molecular":[54],"editing),":[55],"plug-and-play":[57],"framework":[58],"that":[59],"decomposes":[60],"the":[61,108],"editor's":[62],"states":[64],"into":[65],"sparse,":[66],"property-aligned":[67],"features":[68],"via":[69],"Sparse":[71],"Autoencoder":[72],"with":[73,124],"learnable":[74],"importance":[75],"gates.":[76],"Steering":[77],"in":[78],"this":[79],"sparse":[80,97],"feature":[81],"space":[82],"precisely":[83],"activates":[84],"dimensions,":[86],"improving":[87],"editing":[88,104],"success":[89],"rate":[90],"without":[91],"modifying":[92],"model":[93,113],"parameters.":[94],"The":[95],"same":[96],"basis":[98],"further":[99],"supports":[100],"interpretable":[101],"analysis":[102],"behavior.":[105],"Experiments":[106],"on":[107],"MolEditRL":[109],"benchmark":[110],"four":[112],"architectures":[114],"and":[115],"eight":[116],"properties":[118],"show":[119],"consistent":[120],"gains":[121],"over":[122],"baselines,":[123],"improvements":[125],"up":[127],"42.4":[129],"points.":[130]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}