{"id":"https://openalex.org/W4392576515","doi":"https://doi.org/10.48550/arxiv.2403.03788","title":"PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion","display_name":"PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion","publication_year":2024,"publication_date":"2024-03-06","ids":{"openalex":"https://openalex.org/W4392576515","doi":"https://doi.org/10.48550/arxiv.2403.03788"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.03788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03788","pdf_url":"https://arxiv.org/pdf/2403.03788","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.03788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059863277","display_name":"Ze Zhang","orcid":"https://orcid.org/0000-0002-4136-5263"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Zekai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044941285","display_name":"Yiduo Guo","orcid":"https://orcid.org/0000-0002-6323-6235"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yiduo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678419","display_name":"Yaobo Liang","orcid":"https://orcid.org/0000-0002-6595-5145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Yaobo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037132097","display_name":"Dongyan Zhao","orcid":"https://orcid.org/0000-0002-0396-6703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Dongyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042018181","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Nan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059863277"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.972599983215332,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.972599983215332,"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":0.9585999846458435,"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/T10028","display_name":"Topic Modeling","score":0.9563000202178955,"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/robustness","display_name":"Robustness (evolution)","score":0.8668428063392639},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7204844951629639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6027639508247375},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.600080132484436},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37420785427093506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33950740098953247},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12468516826629639},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09316679835319519},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06718072295188904},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.05320984125137329},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.050825417041778564}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8668428063392639},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7204844951629639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6027639508247375},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.600080132484436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37420785427093506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33950740098953247},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12468516826629639},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09316679835319519},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06718072295188904},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05320984125137329},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.050825417041778564},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.03788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03788","pdf_url":"https://arxiv.org/pdf/2403.03788","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.03788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.03788","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.03788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03788","pdf_url":"https://arxiv.org/pdf/2403.03788","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392576515.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"growing":[1],"dependence":[2],"on":[3],"Large":[4],"Language":[5,74],"Models":[6,75],"(LLMs)":[7],"for":[8,122,188],"finishing":[9],"user":[10,46,57,61],"instructions":[11,58,62],"necessitates":[12],"a":[13,106],"comprehensive":[14],"understanding":[15],"of":[16,73,83,179],"their":[17,155],"robustness":[18,43,72,111,135,156,174,194],"to":[19,40,44,76,86,114,166,190],"complex":[20],"task":[21,48,123,196],"completion":[22,197],"in":[23,136,140,181,195],"real-world":[24],"situations.":[25],"To":[26,69],"address":[27],"this":[28],"critical":[29],"need,":[30],"we":[31,54,79,97,149],"propose":[32],"the":[33,45,71,81,89,130,141,145,173,192,207],"PowerPoint":[34],"Task":[35],"Completion":[36],"Robustness":[37],"benchmark":[38,107],"(PPTC-R)":[39],"measure":[41],"LLMs'":[42,119],"PPT":[47],"instruction":[49],"and":[50,66,92,101,133,144,176,198,203,209],"software":[51,77],"version.":[52],"Specifically,":[53],"construct":[55],"adversarial":[56],"by":[59],"attacking":[60],"at":[63,211],"sentence,":[64],"semantic,":[65],"multi-language":[67],"levels.":[68],"assess":[70],"versions,":[78],"vary":[80],"number":[82],"provided":[84],"APIs":[85],"simulate":[87],"both":[88],"newest":[90],"version":[91,94,142],"earlier":[93],"settings.":[95,147],"Subsequently,":[96],"test":[98],"3":[99],"closed-source":[100],"4":[102],"open-source":[103],"LLMs":[104,153,180,202],"using":[105],"that":[108,127,151],"incorporates":[109],"these":[110],"settings,":[112],"aiming":[113],"evaluate":[115],"how":[116],"deviations":[117],"impact":[118],"API":[120],"calls":[121],"completion.":[124],"We":[125,170,205],"find":[126,150],"GPT-4":[128],"exhibits":[129],"highest":[131],"performance":[132,168],"strong":[134],"our":[137,182],"benchmark,":[138,183],"particularly":[139],"update":[143],"multilingual":[146],"However,":[148],"all":[152],"lose":[154],"when":[157],"confronted":[158],"with":[159],"multiple":[160],"challenges":[161],"(e.g.,":[162],"multi-turn)":[163],"simultaneously,":[164],"leading":[165],"significant":[167],"drops.":[169],"further":[171],"analyze":[172],"behavior":[175],"error":[177],"reasons":[178],"which":[184],"provide":[185],"valuable":[186],"insights":[187],"researchers":[189],"understand":[191],"LLM's":[193],"develop":[199],"more":[200],"robust":[201],"agents.":[204],"release":[206],"code":[208],"data":[210],"\\url{https://github.com/ZekaiGalaxy/PPTCR}.":[212]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2024-03-08T00:00:00"}