一种用于大语言模型中动态实体跟踪的检索条件化重绑定回路

Computer Science > Computation and Language arXiv:2606.08644 (cs) [Submitted on 7 Jun 2026 (v1), last revised 11 Sep 2026 (this version, v2)] Title:A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models Authors:Soyoung Oh, Vera Demberg View a PDF of the paper titled A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models, by Soyoung Oh and 1 other authors View PDF HTML (experimental) Abstract:To interpret context correctly and retrieve relevant information, large language models must bind entities to their attributes and update these bindings as state changes. We analyze how LLMs implement this binding process in a dynamic state tracking. Using causal interventions, we identify a retrieval conditioned rebinding mechanism, a compact attention head circuit that propagated binding information and when the entity is queried, uses the updated binding to retrieve the corresponding attribute. Across Gemma and Llama models, this circuit supports rebinding behavior, but the representational signature of the mechanism differs across model families. In Gemma models, the binding signature is clearly expressed in the query/key subspaces of the relevant attention heads, whereas in Llama models, the binding information is carried primarily in key vectors. Overall, our results reveal an interpretable mechanism for context dependent state tracking in LLMs. Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2606.08644 [cs.CL] (or arXiv:2606.08644v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2606.08644 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Soyoung Oh [view email] [v1] Sun, 7 Jun 2026 14:16:44 UTC (2,472 KB) [v2] Fri, 11 Sep 2026 12:06:59 UTC (2,565 KB) Full-text links: Access Paper: View a PDF of the paper titled A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models, by Soyoung Oh and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-06 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × 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?) 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?)