AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。
[Submitted on 12 Aug 2026] Title:Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models View a PDF of the paper titled Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models, by Meysam Ghaffari and 4 other authors View PDF HTML (experimental) Abstract:Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusable context is added. We formulate this phenomenon, which we call context poisoning, as extreme-value interference in attention: the decisive-evidence score is upper-bounded, while the maximum score among effective distractors grows with their number. Under a softmax retrieval abstraction, we derive a finite-sample upper bound showing that maintaining a fixed accuracy target above base rate requires the evidence margin to scale as $\Omega(\sqrt{\log N})$, where N denotes the effective distractor count rather than necessarily the raw context length. The analysis connects long-context degradation to score aliasing, positional aliasing, and softmax dilution. Controlled experiments show that retrieval accuracy decreases as total context grows in the presence of embedded hard negatives, that the same-format condition produces the largest observed accuracy drop among the tested distractor constructions at fixed context length, and that retrieval gating can improve evidence use while its net benefit depends on preserving evidence recall. These results motivate evidence bottlenecks, alias-resistant representations, retrieve-then-reason architectures, verifier-mediated memory, and contrastive anti-poison training. Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2609.22101 [cs.CL] (or arXiv:2609.22101v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2609.22101 arXiv-issued DOI via DataCite Submission history From: Meysam Ghaffari [view email] [v1] Wed, 12 Aug 2026 14:39:15 UTC (963 KB) Full-text links: Access Paper: View a PDF of the paper titled Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models, by Meysam Ghaffari and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-09 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: 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?) 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?)