AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。
[Submitted on 14 Oct 2026] Title:Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised View a PDF of the paper titled Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised, by Harsh Kumar and 3 other authors View PDF HTML (experimental) Abstract:Code models write Python when the prompt does not say which language to use. We ask a mechanistic question about that habit: is it produced by a small, findable group of components inside the model? We run one pipeline---mean ablation, activation patching, greedy circuit extraction, a random-control significance test, and activation steering---over 55 model-language settings spanning ten open code models (five base and five instruction-tuned), three target languages (Rust, C#, PHP), two prompt suites, and two component budgets. We report five findings. First, the preference is large, grows with model size, and survives instruction tuning: it is larger on every instruction-tuned checkpoint than on its base version, by 12% on average. Second, its measured size is mostly a property of the probe; replacing our aligned prompts with XLCoST parallel functions takes the same measurement on the same models from about 1.6 to about 0.01. Third, whether the preference looks localised depends on how many components the search may keep: with a budget of 12, 1 of 15 settings yields a circuit that beats size-matched random controls after multiple-comparison correction, and with a budget of 40, 6 of 15 do. Fourth, interventions that a smaller-budget study reports as uniformly failing do sometimes succeed: patching makes a Python prompt prefer target syntax in 2 of 45 settings, and steering changes the most likely next token in 9 of 45. Fifth, every circuit whose effect is significant but points away from the target language comes from a setting where circuit extraction failed, which makes such results a diagnostic rather than a phenomenon. The practical lesson is that a claim about whether a behaviour is localised can turn on analysis choices that papers rarely report. We release the full grid so those choices can be varied. Comments: Accepted at the NeurIPS 2026 Workshop on Linguistic Principles for Foundation Models (LP4FM). All four authors contributed equally Subjects: Machine Learning (cs.LG); Software Engineering (cs.SE) Cite as: arXiv:2610.20683 [cs.LG] (or arXiv:2610.20683v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2610.20683 arXiv-issued DOI via DataCite (pending registration) Submission history From: Rahul Maity [view email] [v1] Wed, 14 Oct 2026 16:31:03 UTC (408 KB) Full-text links: Access Paper: View a PDF of the paper titled Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised, by Harsh Kumar and 3 other authors View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG new | recent | 2026-10 Change to browse by: cs cs.SE 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?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) 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?)