{"id":"https://openalex.org/W7204920185","doi":"https://doi.org/10.48550/arxiv.2608.29477","title":"MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects","display_name":"MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects","publication_year":2026,"publication_date":"2026-08-30","ids":{"openalex":"https://openalex.org/W7204920185","doi":"https://doi.org/10.48550/arxiv.2608.29477"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.29477","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29477","pdf_url":"https://arxiv.org/pdf/2608.29477","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":null,"license_id":null,"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/2608.29477","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128057699","display_name":"Jason Luo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120410861","display_name":"Saibilila Abudukelimu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abudukelimu, Saibilila","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113003778","display_name":"Judy Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Judy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159901160","display_name":"Andrew Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Andrew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101382789","display_name":"Shivank Garg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garg, Shivank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102320649","display_name":"Vasu Sharma","orcid":"https://orcid.org/0009-0006-4348-7412","observed_orcids":["https://orcid.org/0009-0006-4348-7412"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Vasu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101471343","display_name":"Kevin Zhu","orcid":"https://orcid.org/0009-0008-1881-8384","observed_orcids":["https://orcid.org/0009-0008-1881-8384"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Kevin","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":false,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6176999807357788,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6176999807357788,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.364300012588501,"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":0.002400000113993883,"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/document-question-answering","display_name":"document question answering","score":0.9649999737739563},{"id":"https://openalex.org/keywords/distractor-effects","display_name":"distractor effects","score":0.7910000085830688},{"id":"https://openalex.org/keywords/context-length","display_name":"context length","score":0.6200000047683716},{"id":"https://openalex.org/keywords/hard-negatives","display_name":"hard negatives","score":0.7390000224113464},{"id":"https://openalex.org/keywords/topical-similarity","display_name":"topical similarity","score":0.593999981880188},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5960000157356262},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6769999861717224},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.5709999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686000227928162},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6385999917984009},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5471000075340271},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5184999704360962},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478999972343445},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C76188268","wikidata":"https://www.wikidata.org/wiki/Q1783165","display_name":"Context effect","level":3,"score":0.39559999108314514},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C73782692","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Random error","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.29477","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29477","pdf_url":"https://arxiv.org/pdf/2608.29477","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.29477","doi":"https://doi.org/10.48550/arxiv.2608.29477","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.29477","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:2608.29477","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29477","pdf_url":"https://arxiv.org/pdf/2608.29477","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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/W7204110156","https://openalex.org/W7138917939","https://openalex.org/W7172489165","https://openalex.org/W4404781042","https://openalex.org/W7162754718","https://openalex.org/W7160929973","https://openalex.org/W4404783613","https://openalex.org/W7134813429","https://openalex.org/W7140144908","https://openalex.org/W4400433861"],"abstract_inverted_index":{"Document":[0],"question-answering":[1],"systems":[2,29],"increasingly":[3],"answer":[4],"questions":[5],"over":[6],"collections":[7],"of":[8,243],"retrieved":[9],"documents":[10,195,204],"rather":[11,133],"than":[12,134,192],"one":[13],"clean":[14],"source,":[15],"so":[16,122],"robustness":[17],"to":[18,47,54,75,114],"distracting":[19],"context":[20,37,198,230,244],"matters":[21],"as":[22,24],"much":[23],"reading":[25],"ability.":[26],"When":[27],"such":[28],"fail,":[30],"it":[31],"is":[32,154,212],"often":[33],"unclear":[34],"whether":[35],"the":[36,42,48,87,90,101,115,127,149,183,207,234],"was":[38],"too":[39,45],"long":[40],"or":[41,94,105],"distractors":[43,111,163,226],"were":[44],"close":[46],"topic,":[49],"because":[50],"prior":[51],"work":[52],"tends":[53],"conflate":[55],"these":[56],"two":[57,93,104,128],"effects.":[58],"We":[59,171,232],"present":[60],"MUDDLE,":[61],"a":[62,76,159,240],"controlled":[63],"benchmark":[64],"that":[65],"separates":[66],"them.":[67],"MUDDLE":[68],"uses":[69],"270":[70],"human-annotated":[71],"questions,":[72],"each":[73],"tied":[74],"single":[77],"source":[78,88,91,102,160],"document,":[79],"and":[80,100,120,145,167,217,236],"instantiates":[81],"every":[82],"question":[83],"in":[84,118,141,156],"five":[85,137],"conditions:":[86],"alone,":[89],"with":[92,103,174],"four":[95,106],"topically":[96],"similar":[97],"hard":[98,116,187,220],"negatives,":[99],"random":[107,110,194,203,225],"distractors.":[108],"The":[109,210],"are":[112,139],"matched":[113],"negatives":[117,188,221],"length":[119],"provenance,":[121],"an":[123,175],"accuracy":[124,190],"gap":[125],"between":[126],"arms":[129],"reflects":[130],"topical":[131],"similarity":[132],"length.":[135],"All":[136],"conditions":[138],"rendered":[140],"markdown,":[142,157],"page":[143],"images,":[144],"raw":[146],"PDF,":[147],"but":[148,214],"distractor":[150],"sweep":[151],"reported":[152],"here":[153],"run":[155],"since":[158],"plus":[161],"its":[162],"exceeds":[164],"current":[165],"image":[166],"PDF":[168],"input":[169],"limits.":[170],"score":[172],"answers":[173],"LLM":[176],"judge":[177],"across":[178,229],"three":[179],"model":[180],"families.":[181],"In":[182],"complete":[184],"markdown":[185],"sweep,":[186],"lower":[189],"more":[191],"length-matched":[193,224],"at":[196],"both":[197],"sizes":[199],"for":[200,218,239],"gpt-5-mini,":[201],"while":[202],"stay":[205],"near":[206],"no-distractor":[208],"baseline.":[209],"effect":[211],"small":[213],"directionally":[215],"consistent,":[216],"gpt-5-mini":[219],"significantly":[222],"underperform":[223],"when":[227],"pooled":[228],"sizes.":[231],"release":[233],"data":[235],"evaluation":[237],"code":[238],"reproducible":[241],"study":[242],"degradation.":[245]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}