{"id":"https://openalex.org/W4416429571","doi":"https://doi.org/10.1109/iccad66269.2025.11240962","title":"TOGGLE: Temporal Logic-Guided Large Language Model Compression for Edge","display_name":"TOGGLE: Temporal Logic-Guided Large Language Model Compression for Edge","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429571","doi":"https://doi.org/10.1109/iccad66269.2025.11240962"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.16855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070759206","display_name":"Khurram Khalil","orcid":"https://orcid.org/0000-0003-1718-7150"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khurram Khalil","raw_affiliation_strings":["University of Missouri,Department of Electrical Engineering and Computer Science,Columbia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Missouri,Department of Electrical Engineering and Computer Science,Columbia,USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069684684","display_name":"Khaza Anuarul Hoque","orcid":"https://orcid.org/0000-0002-1625-6479"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khaza Anuarul Hoque","raw_affiliation_strings":["University of Missouri,Department of Electrical Engineering and Computer Science,Columbia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Missouri,Department of Electrical Engineering and Computer Science,Columbia,USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76835614"],"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":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2443999946117401,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2443999946117401,"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"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.14079999923706055,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.09160000085830688,"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/quantization","display_name":"Quantization (signal processing)","score":0.583899974822998},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5695000290870667},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.532800018787384},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.45179998874664307},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4131999909877777},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39579999446868896},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3853999972343445},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3846000134944916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484999895095825},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C146072743","wikidata":"https://www.wikidata.org/wiki/Q192161","display_name":"Formal language","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C2985583900","wikidata":"https://www.wikidata.org/wiki/Q722617","display_name":"Formal description","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.16855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.16855","pdf_url":"https://arxiv.org/pdf/2512.16855","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.16855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.16855","pdf_url":"https://arxiv.org/pdf/2512.16855","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1533557569","https://openalex.org/W1547304883","https://openalex.org/W2785700716","https://openalex.org/W2802329608","https://openalex.org/W3170647102","https://openalex.org/W3201174429","https://openalex.org/W4379116114","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"Large":[0,49],"Language":[1,50],"Models":[2],"(LLMs)":[3],"deliver":[4],"exceptional":[5],"performance":[6],"across":[7],"natural":[8],"language":[9],"tasks":[10],"but":[11],"demand":[12],"substantial":[13],"computational":[14,121],"resources,":[15],"limiting":[16],"their":[17],"deployment":[18,152],"on":[19,101,155],"resource-constrained":[20],"edge":[21,156],"devices.":[22],"Existing":[23],"compression":[24],"techniques,":[25],"such":[26],"as":[27],"quantization":[28,82],"and":[29,36,65,83,111,124],"pruning,":[30],"often":[31],"degrade":[32],"critical":[33],"linguistic":[34,67,93,136],"properties":[35,68],"lack":[37],"formal":[38,144],"guarantees":[39],"for":[40],"preserving":[41],"model":[42,131],"behavior.":[43],"We":[44],"propose":[45],"TOGGLE":[46,71,100,138],"(Temporal":[47],"Logic-Guided":[48],"Model":[51],"Compression),":[52],"a":[53,127],"novel":[54],"framework":[55],"that":[56,89],"leverages":[57],"Signal":[58],"Temporal":[59],"Logic":[60],"(STL)":[61],"to":[62,78,117,126],"formally":[63,90],"specify":[64],"enforce":[66],"during":[69],"compression.":[70],"employs":[72],"an":[73],"STL":[74],"robustness-guided":[75],"Bayesian":[76],"optimization":[77],"systematically":[79],"explore":[80],"layer-wise":[81],"pruning":[84],"configurations,":[85],"generating":[86],"compressed":[87],"models":[88],"satisfy":[91],"specified":[92],"constraints":[94],"without":[95],"re-training":[96],"or":[97],"fine-tuning.":[98],"Evaluating":[99],"four":[102],"LLM":[103,147],"architectures":[104],"(GPT-2,":[105],"DeepSeek-V2":[106],"7B,":[107],"LLaMA":[108],"3":[109],"8B,":[110],"Mistral":[112],"7B),":[113],"we":[114],"achieve":[115],"up":[116,125],"3.3\u00d7":[118],"reduction":[119,129],"in":[120,130],"costs":[122],"(FLOPs)":[123],"68.8%":[128],"size":[132],"while":[133],"satisfying":[134],"all":[135],"properties.":[137],"represents":[139],"the":[140],"first":[141],"integration":[142],"of":[143,153],"methods":[145],"into":[146],"compression,":[148],"enabling":[149],"efficient,":[150],"verifiable":[151],"LLMs":[154],"hardware.":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-20T00:00:00"}