{"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/make-your-llm-fully-utilize-the-context","title":"Make Your LLM Fully Utilize the Context","arxiv_id":"2404.16811","date":"2024-04-25","proceeding":null,"authors":["Shengnan An","Zexiong Ma","Zeqi Lin","Nanning Zheng","Jian-Guang Lou"],"abstract":"While many contemporary large language models (LLMs) can process lengthy input, they still struggle to fully utilize information within the long context, known as the lost-in-the-middle challenge. We hypothesize that it stems from insufficient explicit supervision during the long-context training, which fails to emphasize that any position in a long context can hold crucial information. Based on this intuition, our study presents information-intensive (IN2) training, a purely data-driven solution to overcome lost-in-the-middle. Specifically, IN2 training leverages a synthesized long-context question-answer dataset, where the answer requires (1) fine-grained information awareness on a short segment (~128 tokens) within a synthesized long context (4K-32K tokens), and (2) the integration and reasoning of information from two or more short segments. Through applying this information-intensive training on Mistral-7B, we present FILM-7B (FILl-in-the-Middle). To thoroughly assess the ability of FILM-7B for utilizing long contexts, we design three probing tasks that encompass various context styles (document, code, and structured-data context) and information retrieval patterns (forward, backward, and bi-directional retrieval). The probing results demonstrate that FILM-7B can robustly retrieve information from different positions in its 32K context window. Beyond these probing tasks, FILM-7B significantly improves the performance on real-world long-context tasks (e.g., 23.5->26.9 F1 score on NarrativeQA), while maintaining a comparable performance on short-context tasks (e.g., 59.3->59.2 accuracy on MMLU). Github Link: https://github.com/microsoft/FILM.","url_abs":"https://arxiv.org/abs/2404.16811v2","url_pdf":"https://arxiv.org/pdf/2404.16811v2.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":"make-your-llm-fully-utilize-the-context","repo_url":"https://github.com/microsoft/FILM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"make-your-llm-fully-utilize-the-context","repo_url":"https://github.com/nvidia/ruler","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"mmlu","task_name":"MMLU"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.16811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16811"}},"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/microsoft/FILM","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvidia/ruler","reach":null}],"summary":{"ran":3,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"477258f8938c0fd2","entry":"f1_score","repo":"microsoft/FILM","repo_kind":"official","path":"real_world_long/metrics.py","file_url":"https://github.com/microsoft/FILM/blob/HEAD/real_world_long/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"477258f8938c0fd2"}},{"code_sha256_prefix":"23df4ceddbf42308","entry":"get_csqa_match","repo":"microsoft/FILM","repo_kind":"official","path":"short_tasks/utils.py","file_url":"https://github.com/microsoft/FILM/blob/HEAD/short_tasks/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23df4ceddbf42308"}},{"code_sha256_prefix":"37773130a24557b7","entry":"last_boxed_only_string","repo":"microsoft/FILM","repo_kind":"official","path":"short_tasks/utils.py","file_url":"https://github.com/microsoft/FILM/blob/HEAD/short_tasks/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37773130a24557b7"}},{"code_sha256_prefix":"e7e75981cb464788","entry":"normalize_answer","repo":"microsoft/FILM","repo_kind":"official","path":"real_world_long/metrics.py","file_url":"https://github.com/microsoft/FILM/blob/HEAD/real_world_long/metrics.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7e75981cb464788"}},{"code_sha256_prefix":"f3bbe264b05aadd3","entry":"remove_boxed","repo":"microsoft/FILM","repo_kind":"official","path":"short_tasks/utils.py","file_url":"https://github.com/microsoft/FILM/blob/HEAD/short_tasks/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3bbe264b05aadd3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}