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.
@article{arxiv.2510.19116,
title = {That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation},
author = {Jaesung Bae and Cameron Churchwell and Mitchell Hermon and Tsun-An Hsieh and Jocelyn Xu and Yekaterina Yegorova and Mark Hasegawa-Johnson and Heng Ji},
journal= {arXiv preprint arXiv:2510.19116},
year = {2025}
}