{"id":"https://openalex.org/W4416036689","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.351","title":"Information Integration in Large Language Models is Gated by Linguistic Structural Markers","display_name":"Information Integration in Large Language Models is Gated by Linguistic Structural Markers","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036689","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.351"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.351","pdf_url":"https://aclanthology.org/2025.emnlp-main.351.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.351.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006240458","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0001-8585-861X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847016","display_name":"Nai Ding","orcid":"https://orcid.org/0000-0003-3428-2723"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nai Ding","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006240458"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17298296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6903","last_page":"6915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2248000055551529,"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":0.2248000055551529,"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/T10028","display_name":"Topic Modeling","score":0.125,"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/T12090","display_name":"Language and cultural evolution","score":0.09529999643564224,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.5368000268936157},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3635999858379364},{"id":"https://openalex.org/keywords/information-structure","display_name":"Information structure","score":0.34769999980926514},{"id":"https://openalex.org/keywords/information-model","display_name":"Information model","score":0.34290000796318054},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.3391999900341034},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3172000050544739},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.30869999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585999727249146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5467000007629395},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860999882221222},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45669999718666077},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2779954242","wikidata":"https://www.wikidata.org/wiki/Q6031227","display_name":"Information structure","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C64249296","wikidata":"https://www.wikidata.org/wiki/Q5250411","display_name":"Deep linguistic processing","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C19527686","wikidata":"https://www.wikidata.org/wiki/Q1665453","display_name":"System integration","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.351","pdf_url":"https://aclanthology.org/2025.emnlp-main.351.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.351","pdf_url":"https://aclanthology.org/2025.emnlp-main.351.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1927860575","display_name":null,"funder_award_id":"32222035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8413024604","display_name":null,"funder_award_id":"2021ZD0204100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036689.pdf","grobid_xml":"https://content.openalex.org/works/W4416036689.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Language":[0],"comprehension":[1],"relies":[2],"on":[3,46,73,100,151],"integrating":[4],"information":[5,19,68,158],"across":[6],"both":[7,86],"local":[8,49,75],"words":[9,101],"and":[10,27,31,59,88,96,120],"broader":[11],"context.We":[12],"propose":[13],"a":[14,42,48,112],"method":[15],"to":[16,40,65,132,155],"quantify":[17],"the":[18,54,67,74,78,103,116,124],"integration":[20,83,159],"window":[21,50,117],"of":[22,85],"large":[23],"language":[24],"models":[25],"(LLMs)":[26],"examine":[28],"how":[29],"sentence":[30,94,105,125],"clause":[32],"boundaries":[33],"constrain":[34],"this":[35],"window.Specifically,":[36],"LLMs":[37,89,149],"are":[38,90],"required":[39],"predict":[41],"target":[43],"word":[44],"based":[45],"either":[47],"(local":[51],"prediction)":[52],"or":[53,106,142],"full":[55],"context":[56],"(global":[57],"prediction),":[58],"we":[60],"use":[61],"Jensen-Shannon":[62],"(JS)":[63],"divergence":[64],"measure":[66],"loss":[69],"from":[70],"relying":[71],"solely":[72],"window,":[76],"termed":[77],"local-prediction":[79],"deficit.Results":[80],"show":[81],"that":[82,148],"windows":[84],"humans":[87],"strongly":[91],"modulated":[92],"by":[93],"boundaries,":[95],"predictions":[97],"primarily":[98,130],"rely":[99,150],"within":[102],"same":[104],"clause:":[107],"The":[108],"localprediction":[109],"deficit":[110],"follows":[111],"power-law":[113],"decay":[114],"as":[115],"length":[118],"increases":[119],"drops":[121],"sharply":[122],"at":[123],"boundary.This":[126],"boundary":[127],"effect":[128],"is":[129],"attributed":[131],"linguistic":[133],"structural":[134,153],"markers,":[135],"e.g.,":[136],"punctuation,":[137],"rather":[138],"than":[139],"implicit":[140],"syntactic":[141],"semantic":[143],"cues.Together,":[144],"these":[145],"results":[146],"indicate":[147],"explicit":[152],"cues":[154],"guide":[156],"their":[157],"strategy.":[160]},"counts_by_year":[],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-11-08T00:00:00"}