{"id":"https://openalex.org/W7203604529","doi":"https://doi.org/10.48550/arxiv.2608.14280","title":"LLM-Assisted LDPC Decoding via Syndrome-Verified Semantic Priors","display_name":"LLM-Assisted LDPC Decoding via Syndrome-Verified Semantic Priors","publication_year":2026,"publication_date":"2026-08-14","ids":{"openalex":"https://openalex.org/W7203604529","doi":"https://doi.org/10.48550/arxiv.2608.14280"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.14280","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14280","pdf_url":"https://arxiv.org/pdf/2608.14280","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.14280","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123100652","display_name":"Sojeong Park","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Park, Sojeong","raw_affiliation_strings":["Dept. of Electrical Engineering Pohang University of Science and Technology Pohang , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering Pohang University of Science and Technology Pohang , Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144370346","display_name":"Hyeonsu Lyu","orcid":"https://orcid.org/0009-0002-8551-4184","observed_orcids":["https://orcid.org/0009-0002-8551-4184"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Hyeonsu","raw_affiliation_strings":["Institute of New Media and Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of New Media and Communications","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147331447","display_name":"Jaehyun Choi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choi, Jaehyun","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering Seoul National University Seoul , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering Seoul National University Seoul , Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031190689","display_name":"Hyun Jong Yang","orcid":"https://orcid.org/0000-0002-0717-3794","observed_orcids":["https://orcid.org/0000-0002-0717-3794"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yang, Hyun Jong","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering Seoul National University Seoul , Republic of Korea","Institute of New Media and Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering Seoul National University Seoul , Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Institute of New Media and Communications","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11130","display_name":"Coding theory and cryptography","score":0.00019999999494757503,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.0,"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/ldpc-decoding","display_name":"LDPC decoding","score":0.9179999828338623},{"id":"https://openalex.org/keywords/semantic-communication","display_name":"semantic communication","score":0.9390000104904175},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.765999972820282},{"id":"https://openalex.org/keywords/semantic-priors","display_name":"semantic priors","score":0.8820000290870667},{"id":"https://openalex.org/keywords/belief-propagation","display_name":"belief propagation","score":0.9639999866485596},{"id":"https://openalex.org/keywords/channel-decoding","display_name":"channel decoding","score":0.4620000123977661},{"id":"https://openalex.org/keywords/bit-error-rate-reduction","display_name":"bit error rate reduction","score":0.703000009059906}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8101000189781189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603999972343445},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.550000011920929},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5202999711036682},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5077000260353088},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48170000314712524},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2776639698","wikidata":"https://www.wikidata.org/wiki/Q4927140","display_name":"Block Error Rate","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C153207627","wikidata":"https://www.wikidata.org/wiki/Q863873","display_name":"Code word","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C56296756","wikidata":"https://www.wikidata.org/wiki/Q840922","display_name":"Bit error rate","level":3,"score":0.2524000108242035},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.14280","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14280","pdf_url":"https://arxiv.org/pdf/2608.14280","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2608.14280","doi":"https://doi.org/10.48550/arxiv.2608.14280","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14280","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.14280","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14280","pdf_url":"https://arxiv.org/pdf/2608.14280","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203604529.pdf","grobid_xml":"https://content.openalex.org/works/W7203604529.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7155192259","https://openalex.org/W4411737184","https://openalex.org/W7156005584","https://openalex.org/W7203691069","https://openalex.org/W7138875915","https://openalex.org/W7100484712","https://openalex.org/W7202168063","https://openalex.org/W3114346169","https://openalex.org/W7083678833","https://openalex.org/W4417170098"],"abstract_inverted_index":{"Semantic":[0],"communication":[1],"exploits":[2],"the":[3,6,21,28,37,41,59,83,86,91,97,112,117,123,131,135,141,146,150,175],"meaning":[4],"of":[5],"payload,":[7,20],"which":[8],"bit-level":[9],"processing":[10],"discards.":[11],"When":[12],"channel":[13,113,119],"decoding":[14,71],"fails":[15,152],"on":[16],"a":[17,157,164],"natural":[18],"language":[19,33],"errors":[22,57,148],"appear":[23],"as":[24,100,108],"corrupted":[25],"characters":[26,39,62,88],"in":[27],"recovered":[29],"text.":[30],"A":[31,125],"large":[32],"model":[34],"(LLM)":[35],"infers":[36],"intended":[38],"from":[40],"semantic":[42,102,195],"context,":[43],"but":[44,144],"it":[45],"can":[46,197],"also":[47,145],"produce":[48],"incorrect":[49],"corrections.":[50],"Applying":[51],"them":[52],"directly":[53],"introduces":[54],"new":[55],"bit":[56,159],"when":[58],"LLM":[60,81,151,191],"modifies":[61],"incorrectly.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"propose":[68],"an":[69,184],"LLM-assisted":[70],"framework":[72],"for":[73],"low-density":[74],"parity-check":[75,92],"(LDPC)":[76],"codes.":[77],"Rather":[78],"than":[79],"trusting":[80],"predictions,":[82,192],"decoder":[84,166],"evaluates":[85],"modified":[87],"jointly":[89],"against":[90],"constraints":[93],"and":[94],"admits":[95],"only":[96,140,179],"accepted":[98],"corrections":[99],"verified":[101],"priors.":[103],"These":[104],"priors":[105],"are":[106],"injected":[107,132,142],"soft":[109],"updates":[110],"to":[111,153,174],"log-likelihood":[114],"ratios,":[115],"preserving":[116],"original":[118],"evidence":[120,133],"without":[121],"modifying":[122],"decoder.":[124],"subsequent":[126],"belief":[127],"propagation":[128],"pass":[129],"distributes":[130],"across":[134],"check":[136],"nodes,":[137],"recovering":[138],"not":[139],"bits":[143],"residual":[147],"that":[149,194],"correct.":[154],"Simulations":[155],"demonstrate":[156],"73%":[158],"error":[160],"rate":[161],"reduction":[162],"over":[163],"conventional":[165],"at":[167],"2.0":[168],"dB,":[169],"whereas":[170],"doubling":[171],"its":[172],"iterations":[173],"same":[176],"budget":[177],"yields":[178],"21%.":[180],"The":[181],"verification":[182],"maintains":[183],"injection":[185],"precision":[186],"above":[187],"0.88":[188],"despite":[189],"inaccurate":[190],"demonstrating":[193],"knowledge":[196],"be":[198],"reliably":[199],"translated":[200],"into":[201],"physical-layer":[202],"reliability":[203],"gains.":[204]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-18T00:00:00"}