{"id":"https://openalex.org/W7163989639","doi":"https://doi.org/10.48550/arxiv.2606.08295","title":"TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation","display_name":"TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7163989639","doi":"https://doi.org/10.48550/arxiv.2606.08295"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08295","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08295","pdf_url":null,"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":"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.2606.08295","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129703518","display_name":"Tianyuan Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Tianyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090197998","display_name":"Xuwei Tan","orcid":"https://orcid.org/0000-0003-2948-9535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Xuwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138278379","display_name":"Lei Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138219516","display_name":"Junsheng Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Junsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138223365","display_name":"Ziyu Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Ziyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138226602","display_name":"Tian Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059269708","display_name":"Zhiqun Zuo","orcid":"https://orcid.org/0000-0001-5469-2725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Zhiqun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138230741","display_name":"Xiaodong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xiaodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138254229","display_name":"Xueru Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xueru","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7407000064849854,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7407000064849854,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.05469999834895134,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.028300000354647636,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/bridge","display_name":"Bridge (graph theory)","score":0.7038000226020813},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.545199990272522},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.41440001130104065},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.40119999647140503},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.3463999927043915}],"concepts":[{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.7038000226020813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449999809265137},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4763999879360199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3808000087738037},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.34769999980926514},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.336899995803833},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.33070001006126404},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08295","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08295","pdf_url":null,"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":"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.2606.08295","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08295","pdf_url":null,"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":"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":[{"display_name":"Peace, Justice and strong institutions","score":0.5228483080863953,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tabular":[0],"data":[1,58],"is":[2],"a":[3,88,103,108,170],"primary":[4],"medium":[5],"for":[6,31,60,99,173],"storing":[7],"real-world":[8],"information,":[9],"driving":[10],"many":[11],"industrial":[12],"applications":[13],"of":[14,75,116],"machine":[15],"learning.":[16],"Traditional":[17],"predictors":[18],"achieve":[19],"strong":[20],"predictive":[21],"performance":[22,71,155],"but":[23],"do":[24],"not":[25],"provide":[26],"readable,":[27],"case-specific":[28],"explanations":[29],"essential":[30],"decision-making.":[32,175],"Large":[33],"Language":[34],"Models":[35],"(LLMs)":[36],"can":[37],"naturally":[38],"bridge":[39],"this":[40,80],"gap":[41,156],"by":[42],"generating":[43],"predictions":[44],"alongside":[45],"explanations.":[46],"However,":[47],"dataset-specific":[48],"patterns,":[49],"such":[50],"as":[51],"feature":[52],"distributions":[53],"and":[54,64,123,137,159,166],"interactions,":[55],"make":[56],"tabular":[57,93],"difficult":[59],"LLMs":[61,158],"to":[62,106],"understand":[63],"reason":[65],"over,":[66],"while":[67,163],"label-only":[68,92],"fine-tuning":[69],"improves":[70],"at":[72],"the":[73,129,154],"cost":[74],"catastrophic":[76],"forgetting.":[77],"To":[78],"address":[79],"problem,":[81],"we":[82],"propose":[83],"Tri-Level":[84],"Rationale":[85],"Distillation":[86],"(TLRD),":[87],"framework":[89],"that":[90,150],"converts":[91],"datasets":[94,148],"into":[95,131],"structured":[96],"rationale":[97,109,130],"supervision":[98],"LLMs.":[100],"TLRD":[101,151],"uses":[102],"high-capacity":[104],"teacher":[105],"synthesize":[107],"corpus":[110],"grounded":[111,138,165],"in":[112],"three":[113],"complementary":[114],"levels":[115],"evidence:":[117],"instance-level":[118],"feature,":[119],"dataset-level":[120],"distributional":[121],"context,":[122],"comparison-level":[124],"retrieved":[125],"neighbors,":[126],"then":[127],"distills":[128],"student":[132],"LLMs,":[133],"enabling":[134],"zero-overhead":[135],"prediction":[136],"explanation":[139],"from":[140],"raw":[141],"features":[142],"only.":[143],"Experiments":[144],"on":[145],"multiple":[146],"domain":[147],"show":[149],"significantly":[152],"closes":[153],"between":[157],"state-of-the-art":[160],"tree":[161],"ensembles":[162],"producing":[164],"readable":[167],"explanations,":[168],"offering":[169],"valuable":[171],"reference":[172],"high-stakes":[174]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}