{"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/marathon-a-race-through-the-realm-of-long","title":"Marathon: A Race Through the Realm of Long Context with Large Language Models","arxiv_id":"2312.09542","date":"2023-12-15","proceeding":null,"authors":["Lei Zhang","Yunshui Li","Ziqiang Liu","Jiaxi Yang","Junhao Liu","Longze Chen","Run Luo","Min Yang"],"abstract":"With the advancement of large language models (LLMs) and the expansion of their context windows, existing long-context benchmarks fall short in effectively evaluating the models' comprehension and reasoning abilities in extended texts. Moreover, conventional benchmarks relying on F1 metrics often inaccurately score responses: they may undervalue correct answers that differ from the reference responses and overvalue incorrect ones that resemble the reference texts. In response to these limitations, we introduce Marathon, a novel evaluation benchmark that adopts a multiple-choice question format. It is specifically designed to overcome the constraints of previous benchmarks and provide a rapid, precise, and unbiased appraisal of the long-context comprehension skills of large language models. We conducted comprehensive evaluations on the Marathon benchmark with a range of state-of-the-art LLMs and assessed the effectiveness of various optimization strategies tailored for long-context generation. We anticipate that the Marathon benchmark and its associated leaderboard will enable a more precise and equitable evaluation of LLMs' capabilities in understanding and reasoning over extended contexts. Marathon is available at https://github.com/Hambaobao/Marathon.","url_abs":"https://arxiv.org/abs/2312.09542v2","url_pdf":"https://arxiv.org/pdf/2312.09542v2.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":"marathon-a-race-through-the-realm-of-long","repo_url":"https://github.com/hambaobao/marathon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"long-context-understanding","task_name":"Long-Context Understanding"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.09542","atlas_url":"https://app.syntology.ai/?focus=2312.09542","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}