大型语言模型中可靠且可泛化知识编辑的博士研究员

PhD Studentship: Reliable and Generalisable Knowledge Editing in Large Language Models

The University of East Anglia · 英国 · Norwich

原帖优先:申请材料、截止时间与资格以原帖和学校官方说明为准。

AI 中文速览

研究内容
本项目旨在开发和评估大语言模型中可靠、局部化且可泛化的知识更新方法,通过适应如 ROME 和 MEMIT 等既定编辑方法,并将其与检索增强生成(RAG)、外部记忆机制及传统微调进行对比,从而纠正错误信息并纳入专业知识。实验将利用开源权重语言模型及UEA的高性能计算设施,通过 CounterFact 和 zsRE 等基准评估编辑效果、泛化能力、局部性以及保留性。项目还将在具身AI系统或社交机器人(如Furhat)中部署选定的模型,开展人机交互实验。
申请条件
申请者的标准最低入学要求为计算机科学专业二等一级(2:1)学位。本博士项目面向英国本土申请者(UK applicants)。
待遇
提供为期3年的资助,包括英国本土学费(‘home’ tuition fees)以及每年 £20,409 的生活津贴(stipend),该津贴将根据 2027/28 学年的商定通货膨胀率进行调整。
申请方式
原文未说明具体的申请方式与截止提交平台,截止日期为2027年2月24日。

由 gemini-2.5-flash-lite 生成,博士岗判定置信度 100%。

岗位信息

截止
(Europe/London) 剩 93 天
学科
计算机科学
合同类型
雇佣合同
原文薪资
GBP 20,409 / 年(税前)
税后月薪(估)
¥12,800;房租后 ¥4,500
估算假设
单身、无子女、雇佣合同的粗略估算,以学校 offer 为准;扣除率 18%;汇率日期 2026-10-01
原帖发布
本站收录
内容更新
原帖导师候选(待核验)
Dr Farhana Ferdousi Liza
来源
jobs.ac.uk(英国博士项目及学术招聘) · 最近核对 2026-11-22
详情核验
判定依据(原文摘录)
  • 该职位是博士培养机会
    The overall aim of this PhD project is to develop and evaluate methods for reliable, localised, and generalisable knowledge updating in large language models.
  • 英语授课与工作环境(强烈的英语适用背景,英国计算机科学 PhD 默认英语)
    Primary Supervisor - Dr Farhana Ferdousi Liza
  • 仅要求计算机科学学士/本科学位(2:1)而非强制要求硕士
    The standard minimum entry requirement is 2:1 in Computer Science.
原文

About the Project

Primary Supervisor - Dr Farhana Ferdousi Liza

Emerging techniques in model editing , also discussed in the literature as knowledge editing and memory editing , offer promising approaches for correcting erroneous or harmful information, incorporating specialised knowledge, and improving the usability, security, and accountability of large language models (LLMs). The overall aim of this PhD project is to develop and evaluate methods for reliable, localised, and generalisable knowledge updating in large language models. Using accessible open-weight language models suited to available computational resources, including NVIDIA RTX 6000 Ada 48GB GPUs and UEA high-performance computing (HPC) facilities, you will adapt established editing methods, such as ROME and MEMIT , and compare them with retrieval-augmented generation (RAG), external memory mechanisms, and conventional fine-tuning. Experiments will investigate how models can incorporate new information or knowledge, correct inaccurate information, and remove outdated or unwanted information while minimising unintended changes to existing capabilities. Evaluation will use established factual model-editing benchmarks, such as CounterFact and zsRE, supplemented where appropriate by a domain-specific dataset. Performance will be assessed in terms of editing efficacy (whether the target knowledge is successfully updated), generalisation (whether updates remain effective across paraphrases and related queries), locality (whether unrelated knowledge and capabilities are preserved), and retention (whether updates persist following subsequent edits or conflicting information). Further evaluations will examine factual consistency, general reasoning, and robustness to adversarial prompts. Where feasible, the project will also investigate knowledge provenance and update traceability to support accountability. Comparative experiments will establish the strengths, limitations, and trade-offs of different knowledge-updating approaches. You will also have the opportunity to deploy selected models in embodied AI systems or social robots, such as Furhat , and conduct human-AI interaction experiments to investigate how knowledge updates affect responses, consistency, and behaviour during real-time interactions. The project will contribute practical methods and empirical evidence for developing reliable, trustworthy, and accountable LLMs for knowledge-intensive applications.

Entry Requirements

The standard minimum entry requirement is 2:1 in Computer Science.

Mode of Study

Full-time

Start Date

1 October 2027

Additional Funding Information

This PhD project is in a competition for a Faculty of Science funded studentship. Funding is available to UK applicants and comprises ‘home’ tuition fees and an annual stipend for 3 years. The current UEA / institutional PhD stipend rate is £20,409 and will be subject to any agreed inflationary uplift for 2027/28.

信息有误?提交纠错