{"id":"https://openalex.org/W7155076006","doi":"https://doi.org/10.48550/arxiv.2604.17574","title":"Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation","display_name":"Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation","publication_year":2026,"publication_date":"2026-04-19","ids":{"openalex":"https://openalex.org/W7155076006","doi":"https://doi.org/10.48550/arxiv.2604.17574"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.17574","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17574","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.2604.17574","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013668207","display_name":"Elaf Alhazmi","orcid":"https://orcid.org/0009-0003-3550-3898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alhazmi, Elaf","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134163267","display_name":"Quan Z. Sheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng, Quan Z.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134101918","display_name":"Wei Emma Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wei Emma","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":0.8256999850273132,"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":0.8256999850273132,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06210000067949295,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.008500000461935997,"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/task","display_name":"Task (project management)","score":0.6657999753952026},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4636000096797943},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.39329999685287476},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3846000134944916},{"id":"https://openalex.org/keywords/implicit-learning","display_name":"Implicit learning","score":0.35370001196861267}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6657999753952026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5655999779701233},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.44279998540878296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4187000095844269},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3846000134944916},{"id":"https://openalex.org/C2777379011","wikidata":"https://www.wikidata.org/wiki/Q938545","display_name":"Implicit learning","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33329999446868896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.266400009393692}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.17574","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17574","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.2604.17574","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17574","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":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5622550845146179}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Distractor":[0],"generation":[1],"(DG)":[2],"remains":[3],"a":[4,53,70,115,127],"labor-intensive":[5],"task":[6,15],"that":[7,82,119,143,170],"still":[8],"significantly":[9],"depends":[10],"on":[11,17,132],"domain":[12],"experts.":[13],"The":[14],"focuses":[16],"generating":[18,167],"plausible":[19],"yet":[20],"incorrect":[21],"options,":[22],"known":[23],"as":[24],"distractors,":[25],"for":[26,69,100,109,126],"multiple-choice":[27],"questions.":[28],"A":[29],"reliable":[30],"distractor":[31,138],"must":[32],"be":[33],"contextually":[34],"relevant":[35,67],"to":[36,41,64,76,154],"the":[37,49,78,151],"question":[38],"and":[39,123,140,162],"able":[40],"mislead":[42],"examinees":[43],"through":[44,102],"implicit":[45],"reasoning":[46,80,99],"when":[47,85],"identifying":[48],"correct":[50],"answer.":[51],"While":[52],"recent":[54,155,160],"method":[55],"integrates":[56],"fine-tuning":[57],"pre-trained":[58],"encoder-decoder":[59],"models":[60,97],"with":[61,105,135,146,172],"contrastive":[62],"learning":[63,104],"generate":[65],"semantically":[66],"distractors":[68,87,122,169],"given":[71,128],"question-answer,":[72],"it":[73],"often":[74],"fails":[75],"capture":[77],"underlying":[79],"process":[81],"experts":[83],"utilize":[84],"selecting":[86,110],"in":[88,166],"benchmarks.":[89,174],"In":[90],"this":[91],"paper,":[92],"we":[93],"explore":[94],"large":[95],"language":[96],"(LLMs)":[98],"DG":[101,117,156],"in-context":[103],"unsupervised":[106],"semantic":[107],"retrieval":[108],"few-shot":[111,147],"examples.":[112],"We":[113],"design":[114],"rationale-augmented":[116],"framework":[118],"jointly":[120],"generates":[121],"their":[124],"rationales":[125],"question-answer.":[129],"Extensive":[130],"experiments":[131],"six":[133],"benchmarks,":[134],"varying":[136],"average":[137],"lengths":[139],"domains,":[141],"demonstrate":[142],"prompting":[144],"LLMs":[145],"examples":[148],"substantially":[149],"improves":[150],"performance":[152],"compared":[153],"models.":[157],"It":[158],"outperforms":[159],"approaches":[161],"achieves":[163],"state-of-the-art":[164],"results":[165],"reasoned":[168],"align":[171],"human-labeled":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}