{"ID":2852478,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.19116","arxiv_id":"2510.19116","title":"That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation","abstract":"This paper investigates how large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt. Building on prior question-answering (QA) research, we extend the investigation of knowledge conflicts to the realm of code generation. We propose a domain-agnostic framework for constructing and interpreting such conflicts, along with a novel evaluation method and dataset tailored to code conflict scenarios. Our experiments indicate that sufficiently large LLMs encode the notion of a knowledge conflict in their parameters, enabling us to detect knowledge conflicts with up to \\textbf{80.65\\%} accuracy. Building on these insights, we show that activation-level steering can achieve up to a \\textbf{12.6\\%} improvement in steering success over a random baseline. However, effectiveness depends critically on balancing model size, task domain, and steering direction. The experiment code and data will be made publicly available after acceptance.","short_abstract":"This paper investigates how large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt. Building on prior question-answering (QA) research, we extend the investigation of knowledge conflicts to the realm of code generation. We p...","url_abs":"https://arxiv.org/abs/2510.19116","url_pdf":"https://arxiv.org/pdf/2510.19116v1","authors":"[\"Jaesung Bae\",\"Cameron Churchwell\",\"Mitchell Hermon\",\"Tsun-An Hsieh\",\"Jocelyn Xu\",\"Yekaterina Yegorova\",\"Mark Hasegawa-Johnson\",\"Heng Ji\"]","published":"2025-10-21T22:27:56Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}