{"id":"https://openalex.org/W4412888371","doi":"https://doi.org/10.18653/v1/2025.findings-acl.660","title":"Express What You See: Can Multimodal LLMs Decode Visual Ciphers with Intuitive Semiosis Comprehension?","display_name":"Express What You See: Can Multimodal LLMs Decode Visual Ciphers with Intuitive Semiosis Comprehension?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888371","doi":"https://doi.org/10.18653/v1/2025.findings-acl.660"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.660","pdf_url":"https://aclanthology.org/2025.findings-acl.660.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.660.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095084159","display_name":"Jiayi Kuang","orcid":"https://orcid.org/0009-0009-5764-1398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayi Kuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101752106","display_name":"Yinghui Li","orcid":"https://orcid.org/0000-0002-7596-9508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghui Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337548","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0002-1728-4076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113067512","display_name":"Haohao Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohao Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109087995","display_name":"Ying Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101564877","display_name":"Wenhao Jiang","orcid":"https://orcid.org/0000-0001-6589-324X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Jiang","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12743","last_page":"12774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7975000143051147,"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":0.7975000143051147,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7562000155448914,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.6798999905586243,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6658689975738525},{"id":"https://openalex.org/keywords/semiosis","display_name":"Semiosis","score":0.576740562915802},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.54317307472229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3480578064918518},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25885114073753357},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25828468799591064},{"id":"https://openalex.org/keywords/semiotics","display_name":"Semiotics","score":0.14322113990783691},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0626838207244873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658689975738525},{"id":"https://openalex.org/C64999355","wikidata":"https://www.wikidata.org/wiki/Q681696","display_name":"Semiosis","level":3,"score":0.576740562915802},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.54317307472229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3480578064918518},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25885114073753357},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25828468799591064},{"id":"https://openalex.org/C139997677","wikidata":"https://www.wikidata.org/wiki/Q60195","display_name":"Semiotics","level":2,"score":0.14322113990783691},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0626838207244873}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.660","pdf_url":"https://aclanthology.org/2025.findings-acl.660.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.660","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.660","pdf_url":"https://aclanthology.org/2025.findings-acl.660.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888371.pdf","grobid_xml":"https://content.openalex.org/works/W4412888371.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1989548363","https://openalex.org/W4392666743","https://openalex.org/W4392666929","https://openalex.org/W4392666849","https://openalex.org/W2082486007","https://openalex.org/W2073983200","https://openalex.org/W1981094099"],"abstract_inverted_index":{"Bridging":[0],"the":[1,12,48,143,158,161],"gap":[2,20],"between":[3],"visual":[4,35,49,85,106,127,137],"and":[5,21,108,148],"language":[6,24],"remains":[7],"a":[8,18,57],"pivotal":[9],"challenge":[10],"for":[11,135,145],"multimodal":[13],"community.Traditional":[14],"VQA":[15],"benchmarks":[16],"encounter":[17],"modality":[19],"over-reliance":[22],"on":[23,46,120],"priors,":[25],"whereas":[26],"human":[27],"cognition":[28,151],"excels":[29],"at":[30],"intuitive":[31,97,128,150],"semiosis,":[32],"associating":[33],"abstract":[34,52,62],"symbols":[36],"to":[37,115],"linguistic":[38],"semantics.Inspired":[39],"by":[40],"this":[41,165],"neurocognitive":[42],"mechanism,":[43],"we":[44,55],"focus":[45],"emojis,":[47],"cipher":[50],"conveying":[51],"textual":[53],"semantics.Specifically,":[54],"propose":[56],"novel":[58],"task":[59],"of":[60,80,84,96,153],"generating":[61],"linguistics":[63],"from":[64],"emoji":[65],"sequence":[66],"images,":[67],"where":[68],"such":[69],"reasoning":[70,79],"underpins":[71],"critical":[72,124],"applications":[73],"in":[74,126,139,164],"cryptography,":[75],"thus":[76],"challenging":[77],"MLLMs'":[78,94],"decoding":[81],"complex":[82],"semantics":[83],"ciphers.We":[86],"introduce":[87],"eWe-bench":[88],"(Express":[89],"What":[90],"you":[91],"SeE),":[92],"assessing":[93],"capability":[95],"semiosis":[98,138],"like":[99],"humans.Our":[100],"data":[101,109,117],"construction":[102],"framework":[103],"ensures":[104],"high":[105],"sensitivity":[107],"quality,":[110],"which":[111],"can":[112],"be":[113],"extended":[114],"future":[116],"enhancement.Evaluation":[118],"results":[119],"advanced":[121],"MLLMs":[122,140,154],"highlight":[123],"deficiencies":[125],"symbolic":[129],"reasoning.We":[130],"believe":[131],"our":[132],"interesting":[133],"insights":[134],"advancing":[136],"will":[141],"pave":[142],"way":[144],"cryptographic":[146],"analysis":[147],"high-level":[149],"intelligence":[152],"1":[155],".What":[156],"is":[157],"English":[159],"idiom":[160],"emojis":[162],"represented":[163],"image?":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}