{"id":"https://openalex.org/W7166796731","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1824","title":"Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time","display_name":"Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166796731","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1824"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1824","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1824","pdf_url":"https://aclanthology.org/2026.findings-acl.1824.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1824.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139782427","display_name":"Mingkuan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingkuan Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137661174","display_name":"Yide Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yide Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809333","display_name":"Wentao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentao Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137693638","display_name":"Suquan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suquan Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068378237","display_name":"Tianqi Huang","orcid":"https://orcid.org/0009-0008-4028-8244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianchen Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137678057","display_name":"Zhenhua An","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenhua An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137684170","display_name":"Zetao Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zetao Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137636657","display_name":"Xiayu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiayu Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139746312","display_name":"Yuheng Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuheng Min","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84368009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36600","last_page":"36611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.1378999948501587,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.1378999948501587,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10580000281333923,"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.10119999945163727,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5514000058174133},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5212000012397766},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4544000029563904},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.39500001072883606},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3709000051021576},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.35190001130104065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6071000099182129},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4544000029563904},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.39500001072883606},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3610000014305115},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1824","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1824","pdf_url":"https://aclanthology.org/2026.findings-acl.1824.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1824","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1824","pdf_url":"https://aclanthology.org/2026.findings-acl.1824.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166796731.pdf","grobid_xml":"https://content.openalex.org/works/W7166796731.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"frequently":[4],"exhibit":[5],"\"contextual":[6],"disregard\"":[7],"when":[8],"faced":[9],"with":[10,15],"input":[11,153],"evidence":[12,83,154],"that":[13,179,199],"conflicts":[14],"their":[16],"internal":[17],"parametric":[18,195],"memory,":[19],"leading":[20],"to":[21,76,127,136,166],"persistent":[22],"factual":[23,187],"hallucinations.Existing":[24],"mitigation":[25],"strategies":[26],"primarily":[27],"rely":[28],"on":[29,173],"suppressing":[30,194],"specific":[31],"neuron":[32],"activations":[33],"or":[34,47],"employing":[35],"computationally":[36,204],"expensive":[37],"contrastive":[38],"decoding":[39],"mechanisms,":[40],"which":[41],"often":[42],"result":[43],"in":[44,67,213],"increased":[45],"perplexity":[46],"significantly":[48,181],"elevated":[49],"inference":[50],"latency.To":[51],"address":[52],"these":[53],"limitations,":[54],"we":[55,118],"propose":[56],"Resonant":[57],"Context":[58],"Anchoring":[59],"(RCA),":[60],"a":[61,120,201,210],"lightweight":[62],"inference-time":[63],"intervention":[64],"method":[65],"grounded":[66],"the":[68,78,93,103,130,141,148,156,163,167,174,219],"perspective":[69],"of":[70,81,96,115,132,152],"residual":[71,157],"stream":[72,158],"signal":[73,79],"dynamics.RCA":[74],"aims":[75],"resolve":[77],"attenuation":[80],"external":[82],"during":[84,170],"its":[85],"propagation":[86],"through":[87],"deep":[88],"networks.The":[89],"core":[90],"mechanism":[91,145],"involves":[92],"orthogonal":[94],"decoupling":[95],"routing":[97],"logic":[98],"and":[99,189,203,215],"information":[100],"magnitude":[101],"within":[102,155],"self-attention":[104],"module.By":[105],"utilizing":[106],"raw":[107],"pre-softmax":[108],"attention":[109,142],"scores":[110],"as":[111,200],"an":[112],"instantaneous":[113],"metric":[114],"semantic":[116],"alignment,":[117],"construct":[119],"dynamic":[121],"gain":[122],"field":[123],"via":[124],"non-linear":[125],"rectification":[126],"selectively":[128],"amplify":[129],"norms":[131],"value":[133],"vectors":[134],"corresponding":[135],"context":[137,169],"tokens,":[138],"without":[139],"altering":[140],"probability":[143],"distribution.This":[144],"effectively":[146,193],"elevates":[147],"signal-to-noise":[149],"ratio":[150],"(SNR)":[151],"mixture,":[159],"thereby":[160],"robustly":[161],"anchoring":[162],"generation":[164],"trajectory":[165],"truthful":[168],"inference.Extensive":[171],"experiments":[172],"Llama-3":[175],"model":[176],"series":[177],"demonstrate":[178],"RCA":[180,208],"improves":[182],"contextual":[183],"faithfulness":[184,214],"across":[185],"multiple":[186],"consistency":[188],"strong":[190],"knowledge-conflict":[191],"tasks,":[192],"hallucinations.Furthermore,":[196],"results":[197],"confirm":[198],"trainingfree":[202],"negligible":[205],"plug-andplay":[206],"module,":[207],"achieves":[209],"Pareto":[211],"improvement":[212],"fluency":[216],"while":[217],"maintaining":[218],"model's":[220],"general":[221],"language":[222],"understanding":[223],"capabilities.":[224]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}