{"id":"https://openalex.org/W7148560183","doi":"https://doi.org/10.48550/arxiv.2604.01206","title":"RELISH: LLM REgression with a Latent Iterative State Head","display_name":"RELISH: LLM REgression with a Latent Iterative State Head","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7148560183","doi":"https://doi.org/10.48550/arxiv.2604.01206"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01206","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,"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.2604.01206","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064728857","display_name":"Yiheng Su","orcid":"https://orcid.org/0009-0004-8988-876X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Yiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023397430","display_name":"Matthew Lease","orcid":"https://orcid.org/0000-0002-0056-2834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lease, Matthew","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/T10028","display_name":"Topic Modeling","score":0.3659999966621399,"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/T10028","display_name":"Topic Modeling","score":0.3659999966621399,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08749999850988388,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.058800000697374344,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/regression","display_name":"Regression","score":0.5997999906539917},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5371000170707703},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.5285999774932861},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.525600016117096},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.48730000853538513},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4016999900341034},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.39399999380111694}],"concepts":[{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5997999906539917},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5246999859809875},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4505999982357025},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3910999894142151},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C44648626","wikidata":"https://www.wikidata.org/wiki/Q1049848","display_name":"Percentage point","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01206","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,"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.2604.01206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01206","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,"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":{"We":[0],"present":[1],"RELISH":[2,34,80,105],"(REgression":[3],"with":[4,18,65,129],"a":[5,10,46,62,66],"Latent":[6],"Iterative":[7],"State":[8],"Head),":[9],"novel,":[11],"lightweight":[12],"architecture":[13],"designed":[14],"for":[15],"text":[16,28],"regression":[17,90],"large":[19],"language":[20],"models.":[21],"Rather":[22],"than":[23,124],"decoding":[24],"numeric":[25],"targets":[26],"as":[27],"or":[29],"aggregating":[30],"multiple":[31],"generated":[32],"outputs,":[33],"predicts":[35],"scalar":[36],"values":[37],"directly":[38],"from":[39,85],"frozen":[40,115],"LLM":[41,73,77,89,116],"representations":[42],"by":[43],"iteratively":[44],"refining":[45],"learned":[47],"latent":[48],"state":[49,60],"through":[50],"cross-attention":[51],"over":[52],"token-level":[53],"representations,":[54],"and":[55,75,97],"then":[56],"mapping":[57],"the":[58],"final":[59],"to":[61],"point":[63],"estimate":[64],"linear":[67],"regressor.":[68],"Across":[69],"six":[70],"datasets,":[71],"four":[72],"backbones,":[74],"two":[76],"training":[78],"regimes,":[79],"consistently":[81],"outperforms":[82],"prior":[83],"baselines":[84],"all":[86],"three":[87],"major":[88],"families,":[91],"including":[92],"autoregressive":[93],"decoding,":[94],"regression-aware":[95],"inference,":[96],"existing":[98],"predictive":[99],"head":[100],"methods.":[101],"Despite":[102],"these":[103],"gains,":[104],"remains":[106],"highly":[107],"parameter-efficient,":[108],"requiring":[109],"only":[110],"$\\sim$3.4-3.7M":[111],"trainable":[112],"parameters":[113],"across":[114],"backbones":[117],"(only":[118],"0.01-0.04$\\%$":[119],"additional":[120],"overhead),":[121],"far":[122],"less":[123],"LoRA-based":[125],"alternatives":[126],"that":[127],"grow":[128],"model":[130],"size":[131],"(0.26-0.42$\\%$).":[132],"Our":[133],"code":[134],"is":[135],"available":[136],"at":[137],"https://github.com/SamSoup/RELISH.":[138]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-03T00:00:00"}