{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bamboo-a-comprehensive-benchmark-for","title":"BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models","arxiv_id":"2309.13345","date":"2023-09-23","proceeding":null,"authors":["Zican Dong","Tianyi Tang","Junyi Li","Wayne Xin Zhao","Ji-Rong Wen"],"abstract":"Large language models (LLMs) have achieved dramatic proficiency over NLP tasks with normal length. Recently, multiple studies have committed to extending the context length and enhancing the long text modeling capabilities of LLMs. To comprehensively evaluate the long context ability of LLMs, we propose BAMBOO, a multi-task long context benchmark. BAMBOO has been designed with four principles: comprehensive capacity evaluation, avoidance of data contamination, accurate automatic evaluation, and different length levels. It consists of 10 datasets from 5 different long text understanding tasks, i.e. question answering, hallucination detection, text sorting, language modeling, and code completion, to cover core capacities and various domains of LLMs. We conduct experiments with five long context models on BAMBOO and further discuss four key research questions of long text. We also qualitatively analyze current long context models and point out future directions for enhancing long text modeling capacities. We release our data, prompts, and code at https://github.com/RUCAIBox/BAMBOO.","url_abs":"https://arxiv.org/abs/2309.13345v3","url_pdf":"https://arxiv.org/pdf/2309.13345v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bamboo-a-comprehensive-benchmark-for","repo_url":"https://github.com/rucaibox/bamboo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"code-completion","task_name":"Code Completion"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.13345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13345"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rucaibox/bamboo","reach":null}],"summary":{"ran_honours":1,"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"f147c6a6c2d7c8cd","entry":"altqa_accuracy","repo":"rucaibox/bamboo","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/rucaibox/bamboo/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f147c6a6c2d7c8cd"}},{"code_sha256_prefix":"a8b0c9b324725da9","entry":"calculate_metrics","repo":"rucaibox/bamboo","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/rucaibox/bamboo/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a8b0c9b324725da9"}},{"code_sha256_prefix":"7ce932b84d6e7fa4","entry":"concordinary_index","repo":"rucaibox/bamboo","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/rucaibox/bamboo/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ce932b84d6e7fa4"}},{"code_sha256_prefix":"e080db2eaa81fdb3","entry":"estimate_pass_at_k","repo":"rucaibox/bamboo","repo_kind":"official","path":"private_eval/evaluation.py","file_url":"https://github.com/rucaibox/bamboo/blob/HEAD/private_eval/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e080db2eaa81fdb3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}