{"id":"https://openalex.org/W7220215780","doi":null,"title":"Improving Reasoning Stability in Large Language Models via Iterative Self-Questioning and Semantic Calibration","display_name":"Improving Reasoning Stability in Large Language Models via Iterative Self-Questioning and Semantic Calibration","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7220215780"},"language":"en","primary_location":{"id":"pmh:oai:ojs2.50.18.18.40:article/271","doi":null,"is_oa":true,"landing_page_url":"https://www.mfacademia.org/index.php/jcssa/article/download/271/242","pdf_url":null,"source":{"id":"https://openalex.org/S7407075970","display_name":"Journal of Computer Science and Software Applications","issn_l":"2377-0430","issn":["2377-0430"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2377-0430","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mfacademia.org/index.php/jcssa/article/download/271/242","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157006587","display_name":"Callum Redfern","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Redfern, Callum","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5157006587"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9146000146865845,"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":0.9146000146865845,"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":0.03790000081062317,"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":0.022700000554323196,"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/large-language-models","display_name":"large language models","score":0.9629999995231628},{"id":"https://openalex.org/keywords/reasoning-stability","display_name":"reasoning stability","score":0.9330000281333923},{"id":"https://openalex.org/keywords/semantic-calibration","display_name":"semantic calibration","score":0.9959999918937683},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.7429999709129333},{"id":"https://openalex.org/keywords/chain-of-thought-prompting","display_name":"chain-of-thought prompting","score":0.8920000195503235},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.8119999766349792},{"id":"https://openalex.org/keywords/reasoning-consistency","display_name":"reasoning consistency","score":0.7699999809265137},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.46700000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296000123023987},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7071999907493591},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6665999889373779},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6000000238418579},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662999749183655},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.45980000495910645},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ojs2.50.18.18.40:article/271","doi":null,"is_oa":true,"landing_page_url":"https://www.mfacademia.org/index.php/jcssa/article/download/271/242","pdf_url":null,"source":{"id":"https://openalex.org/S7407075970","display_name":"Journal of Computer Science and Software Applications","issn_l":"2377-0430","issn":["2377-0430"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2377-0430","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:ojs2.50.18.18.40:article/271","doi":null,"is_oa":true,"landing_page_url":"https://www.mfacademia.org/index.php/jcssa/article/download/271/242","pdf_url":null,"source":{"id":"https://openalex.org/S7407075970","display_name":"Journal of Computer Science and Software Applications","issn_l":"2377-0430","issn":["2377-0430"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2377-0430","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160550328","https://openalex.org/W7171536394","https://openalex.org/W4416249822","https://openalex.org/W7220182676","https://openalex.org/W7165231303","https://openalex.org/W4412609334","https://openalex.org/W4416456107","https://openalex.org/W4403364941","https://openalex.org/W4414756466","https://openalex.org/W4416550146"],"abstract_inverted_index":{"Large":[0],"language":[1,10],"models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"strong":[6],"capabilities":[7],"in":[8,23,51,158],"natural":[9],"understanding":[11],"and":[12,18,58,75],"generation;":[13],"however,":[14],"their":[15],"reasoning":[16,42,49,81,147,160],"stability":[17],"consistency":[19,104,122],"remain":[20],"limited,":[21],"particularly":[22],"multi-step":[24],"inference":[25],"tasks.":[26],"This":[27],"paper":[28],"proposes":[29],"a":[30,47,61],"novel":[31],"framework":[32],"that":[33,127,145],"integrates":[34],"iterative":[35,139],"self-questioning":[36],"with":[37],"semantic":[38,128],"calibration":[39,129],"to":[40,85,91,101],"improve":[41,152],"robustness.":[43],"The":[44,77],"approach":[45],"introduces":[46],"multi-stage":[48],"loop":[50],"which":[52],"intermediate":[53],"outputs":[54,157],"are":[55,66,114],"recursively":[56],"evaluated":[57],"refined":[59],"using":[60],"confidence-aware":[62],"scoring":[63],"mechanism.":[64],"Experiments":[65],"conducted":[67],"on":[68,88],"multiple":[69],"benchmark":[70],"datasets,":[71],"including":[72],"GSM8K,":[73],"StrategyQA,":[74,96],"MultiArith.":[76],"proposed":[78],"method":[79],"improves":[80,108],"accuracy":[82,97],"from":[83,99],"78.4%":[84],"85.9%":[86],"(+7.5%)":[87],"GSM8K":[89],"compared":[90],"standard":[92],"chain-of-thought":[93],"prompting.":[94],"On":[95],"increases":[98],"71.2%":[100],"76.8%,":[102],"while":[103],"across":[105],"repeated":[106],"runs":[107],"by":[109,116,120,138],"12.3%.":[110],"Furthermore,":[111],"hallucination":[112],"rates":[113],"reduced":[115],"18.6%,":[117],"as":[118],"measured":[119],"factual":[121],"metrics.":[123],"Ablation":[124],"studies":[125],"show":[126],"contributes":[130],"the":[131,153],"most":[132],"significant":[133],"performance":[134],"gain":[135],"(+4.2%),":[136],"followed":[137],"refinement":[140],"(+3.1%).":[141],"These":[142],"results":[143],"demonstrate":[144],"structured":[146],"enhancement":[148],"mechanisms":[149],"can":[150],"substantially":[151],"reliability":[154],"of":[155],"LLM":[156],"complex":[159],"scenarios.":[161]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2026-10-05T00:00:00"}