{"id":"https://openalex.org/W4392425883","doi":"https://doi.org/10.48550/arxiv.2403.00199","title":"Improving Socratic Question Generation using Data Augmentation and Preference Optimization","display_name":"Improving Socratic Question Generation using Data Augmentation and Preference Optimization","publication_year":2024,"publication_date":"2024-03-01","ids":{"openalex":"https://openalex.org/W4392425883","doi":"https://doi.org/10.48550/arxiv.2403.00199"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.00199","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00199","pdf_url":"https://arxiv.org/pdf/2403.00199","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.00199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116335870","display_name":"Nischal Ashok Kumar","orcid":"https://orcid.org/0000-0002-7022-5948","observed_orcids":["https://orcid.org/0000-0002-7022-5948"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kumar, Nischal Ashok","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063813962","display_name":"Andrew Lan","orcid":"https://orcid.org/0000-0002-8475-6600","observed_orcids":["https://orcid.org/0000-0002-8475-6600"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan, Andrew","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.42820000648498535,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.42820000648498535,"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/T10533","display_name":"Teaching and Learning Programming","score":0.14429999887943268,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10260","display_name":"Software Engineering Research","score":0.10270000249147415,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/socratic-method","display_name":"Socratic method","score":0.8529999852180481},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.7269999980926514},{"id":"https://openalex.org/keywords/preference-optimization","display_name":"preference optimization","score":0.7699999809265137},{"id":"https://openalex.org/keywords/direct-preference-optimization","display_name":"direct preference optimization","score":0.9539999961853027},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8379999995231628},{"id":"https://openalex.org/keywords/llama-2","display_name":"Llama 2","score":0.8149999976158142},{"id":"https://openalex.org/keywords/prompting","display_name":"prompting","score":0.41600000858306885}],"concepts":[{"id":"https://openalex.org/C2801541","wikidata":"https://www.wikidata.org/wiki/Q839475","display_name":"Socratic method","level":2,"score":0.7641603946685791},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6892224550247192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.390065997838974},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3721829354763031},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.33029651641845703},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.21280360221862793},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.20187851786613464},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.10030165314674377}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.00199","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00199","pdf_url":"https://arxiv.org/pdf/2403.00199","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.00199","doi":"https://doi.org/10.48550/arxiv.2403.00199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.00199","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.00199","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00199","pdf_url":"https://arxiv.org/pdf/2403.00199","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6164000034332275,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G815501669","display_name":"An Educational Tool for Teaching and Learning Concurrent Computer Programming Techniques","funder_award_id":"2215193","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392425883.pdf","grobid_xml":"https://content.openalex.org/works/W4392425883.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4392546030","https://openalex.org/W7130579666","https://openalex.org/W4385573161","https://openalex.org/W7221830144","https://openalex.org/W7134972501","https://openalex.org/W7214151964","https://openalex.org/W4404781412","https://openalex.org/W4386566896","https://openalex.org/W4417454476","https://openalex.org/W4416034108"],"abstract_inverted_index":{"The":[0],"Socratic":[1,56,110,151],"method":[2,24,106,125],"is":[3],"a":[4,11,36,103,124,150,160,174],"way":[5],"of":[6],"guiding":[7],"students":[8],"toward":[9],"solving":[10],"problem":[12,81],"independently":[13],"without":[14],"directly":[15,75],"revealing":[16],"the":[17,20,77,80],"solution":[18,78],"to":[19,28,49,79,107,126,134],"problem.":[21],"Although":[22],"this":[23,90],"has":[25],"been":[26],"shown":[27],"significantly":[29],"improve":[30],"student":[31,155],"learning":[32,95],"outcomes,":[33],"it":[34],"remains":[35],"complex":[37],"labor-intensive":[38],"task":[39],"for":[40,58,154],"instructors.":[41],"Large":[42],"language":[43],"models":[44],"(LLMs)":[45],"can":[46,166],"be":[47],"used":[48],"augment":[50],"human":[51],"effort":[52],"by":[53,93],"automatically":[54],"generating":[55,169],"questions":[57,114,137,152],"students.":[59],"However,":[60],"existing":[61,109,177],"methods":[62],"that":[63,74,115,159],"involve":[64],"prompting":[65,179],"these":[66],"LLMs":[67,129],"sometimes":[68],"produce":[69],"invalid":[70,117,140,170],"outputs,":[71],"e.g.,":[72],"those":[73],"reveal":[76],"or":[82,85],"provide":[83],"irrelevant":[84],"premature":[86],"questions.":[87],"To":[88],"alleviate":[89],"problem,":[91],"inspired":[92],"reinforcement":[94],"with":[96,113],"AI":[97],"feedback":[98],"(RLAIF),":[99],"we":[100,122],"first":[101],"propose":[102,123],"data":[104],"augmentation":[105],"enrich":[108],"questioning":[111],"datasets":[112],"are":[116],"in":[118],"specific":[119],"ways.":[120],"Next,":[121],"optimize":[127],"open-source":[128],"such":[130],"as":[131,173],"LLama":[132,163],"2":[133,164],"prefer":[135],"ground-truth":[136],"over":[138],"generated":[139],"ones,":[141],"using":[142],"direct":[143],"preference":[144],"optimization":[145],"(DPO).":[146],"Our":[147],"experiments":[148],"on":[149],"dataset":[153],"code":[156],"debugging":[157],"show":[158],"DPO-optimized":[161],"7B":[162],"model":[165],"effectively":[167],"avoid":[168],"questions,":[171],"and":[172],"result,":[175],"outperforms":[176],"state-of-the-art":[178],"methods.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2024-03-05T00:00:00"}