{"id":"https://openalex.org/W4404402417","doi":"https://doi.org/10.48550/arxiv.2411.07037","title":"LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios","display_name":"LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios","publication_year":2024,"publication_date":"2024-11-11","ids":{"openalex":"https://openalex.org/W4404402417","doi":"https://doi.org/10.48550/arxiv.2411.07037"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.07037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.07037","pdf_url":"https://arxiv.org/pdf/2411.07037","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.07037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044520965","display_name":"Xiaodong Wu","orcid":"https://orcid.org/0000-0001-9703-0326"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Xiaodong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070601319","display_name":"Minhao Wang","orcid":"https://orcid.org/0000-0002-8469-8295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Minhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056335032","display_name":"Yichen Liu","orcid":"https://orcid.org/0000-0003-0774-6932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yichen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018955823","display_name":"Xiaoming Shi","orcid":"https://orcid.org/0000-0002-7071-571X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Xiaoming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101788692","display_name":"Yan He","orcid":"https://orcid.org/0000-0002-3668-6126"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101988849","display_name":"Xingyu Lu","orcid":"https://orcid.org/0000-0001-5981-0516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Xiangju","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhu, Junmin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Junmin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038039971","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-4184-8855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5044520965"],"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/T10028","display_name":"Topic Modeling","score":0.9779000282287598,"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":0.9779000282287598,"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":0.941100001335144,"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/stability","display_name":"Stability (learning theory)","score":0.6667235493659973},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6496545672416687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6217401027679443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17319926619529724},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09463310241699219}],"concepts":[{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6667235493659973},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6496545672416687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6217401027679443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17319926619529724},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09463310241699219},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.07037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.07037","pdf_url":"https://arxiv.org/pdf/2411.07037","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.07037","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.07037","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.07037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.07037","pdf_url":"https://arxiv.org/pdf/2411.07037","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1314841804","display_name":null,"funder_award_id":"92270119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404402417.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"evolve":[5],"in":[6,17,33,153,165],"natural":[7],"language":[8],"processing":[9],"(NLP),":[10],"their":[11],"ability":[12],"to":[13,52,161],"stably":[14],"follow":[15],"instructions":[16,73],"long-context":[18,34,65,156],"inputs":[19],"has":[20],"become":[21],"critical":[22],"for":[23,116,149],"real-world":[24],"applications.":[25],"However,":[26],"existing":[27],"benchmarks":[28],"seldom":[29],"focus":[30],"on":[31,38,107,132],"instruction-following":[32,55],"scenarios":[35,66],"or":[36,110],"stability":[37,58,124],"different":[39],"inputs.":[40],"To":[41],"bridge":[42],"this":[43],"gap,":[44],"we":[45,89],"introduce":[46],"LIFBench,":[47],"a":[48,92,117],"scalable":[49],"dataset":[50],"designed":[51],"evaluate":[53],"LLMs'":[54],"capabilities":[56],"and":[57,67,85,123,144,155],"across":[59,80,136],"long":[60],"contexts.":[61],"LIFBench":[62,143],"comprises":[63],"three":[64,81],"eleven":[68],"diverse":[69],"tasks,":[70],"featuring":[71],"2,766":[72],"generated":[74],"through":[75],"an":[76],"automated":[77,99],"expansion":[78],"method":[79,95,114],"dimensions:":[82],"length,":[83],"expression,":[84],"variables.":[86],"For":[87],"evaluation,":[88],"propose":[90],"LIFEval,":[91],"rubric-based":[93],"assessment":[94],"that":[96],"enables":[97],"precise,":[98],"scoring":[100],"of":[101,120],"complex":[102,154],"LLM":[103,151,166],"responses":[104],"without":[105],"reliance":[106],"LLM-assisted":[108],"assessments":[109],"human":[111],"judgment.":[112],"This":[113],"allows":[115],"comprehensive":[118],"analysis":[119],"model":[121],"performance":[122,152],"from":[125],"multiple":[126],"perspectives.":[127],"We":[128],"conduct":[129],"detailed":[130],"experiments":[131],"20":[133],"prominent":[134],"LLMs":[135],"six":[137],"length":[138],"intervals.":[139],"Our":[140],"work":[141],"contributes":[142],"LIFEval":[145],"as":[146],"robust":[147],"tools":[148],"assessing":[150],"settings,":[157],"offering":[158],"valuable":[159],"insights":[160],"guide":[162],"future":[163],"advancements":[164],"development.":[167]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}