Happy Open Access Week from arXiv! YOU make open access possible! Tell us why you support #openaccess and give to arXiv this week to help keep science open for all. Donate! Skip to main content We gratefully acknowledge support from the Simons Foundation, member institutions , and all contributors. Donate > cs > arXiv:2502.05167 Help | Advanced Search All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text Search open search GO open navigation menu quick links Login Help Pages About --> Computer Science > Computation and Language arXiv:2502.05167 (cs) [Submitted on 7 Feb 2025 ( v1 ), last revised 9 Jul 2025 (this version, v3)] Title: NoLiMa: Long-Context Evaluation Beyond Literal Matching Authors: Ali Modarressi , Hanieh Deilamsalehy , Franck Dernoncourt , Trung Bui , Ryan A. Rossi , Seunghyun Yoon , Hinrich Schütze View a PDF of the paper titled NoLiMa: Long-Context Evaluation Beyond Literal Matching, by Ali Modarressi and 6 other authors View PDF HTML (experimental) Abstract: Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a "needle" (relevant information) from a "haystack" (long irrelevant context). Extensions of this approach include increasing distractors, fact chaining, and in-context reasoning. However, in these benchmarks, models can exploit existing literal matches between the needle and haystack to simplify the task. To address this, we introduce NoLiMa, a benchmark extending NIAH with a carefully designed needle set, where questions and needles have minimal lexical overlap, requiring models to infer latent associations to locate the needle within the haystack. We evaluate 13 popular LLMs that claim to support contexts of at least 128K tokens. While they perform well in short contexts (<1K), performance degrades significantly as context length increases. At 32K, for instance, 11 models drop below 50% of their strong short-length baselines. Even GPT-4o, one of the top-performing exceptions, experiences a reduction from an almost-perfect baseline of 99.3% to 69.7%. Our analysis suggests these declines stem from the increased difficulty the attention mechanism faces in longer contexts when literal matches are absent, making it harder to retrieve relevant information. Even models enhanced with reasoning capabilities or CoT prompting struggle to maintain performance in long contexts. We publicly release the dataset and evaluation code at this https URL . Comments: Accepted at ICML 2025 Subjects: Computation and Language (cs.CL) Cite as: arXiv:2502.05167 [cs.CL] (or arXiv:2502.05167v3 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2502.05167 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ali Modarressi [ view email ] [v1] Fri, 7 Feb 2025 18:49:46 UTC (351 KB) [v2] Wed, 26 Mar 2025 13:23:30 UTC (352 KB) [v3] Wed, 9 Jul 2025 14:35:23 UTC (575 KB) Full-text links: Access Paper: View a PDF of the paper titled NoLiMa: Long-Context Evaluation Beyond Literal Matching, by Ali Modarressi and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2025-02 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation &times; loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) Links to Code Toggle Papers with Code ( What is Papers with Code? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) About Help contact arXiv Click here to contact arXiv Contact subscribe to arXiv mailings Click here to subscribe Subscribe Copyright Privacy Policy Web Accessibility Assistance arXiv Operational Status