论文研究
arxiv.org ·
指导大型语言模型实现领域自适应、精确与安全
arXiv 论文（学位论文）提出面向“负责任智能”的框架，包含三部分：利用主动学习与图结构知识提升专业领域自适应并减少幻觉；通过解码时对齐机制实时阻止有害文本生成；以及按语言进行 steering 以兼顾多语言与文化安全。摘要未给出实验数据、基准结果或代码，实际效果尚待验证。
AI推荐理由 arXiv 学位论文（thesis），提出“responsible intelligence”框架，涵盖三部分：用主动学习与图知识改进领域自适应以减少幻觉、解码时对齐机制实时阻断有害文本生成、以及语言特定 steering 保障多语言文化安全。属学术预印本，摘要层面信息明确但无实验数据、基准或代码链接，实际效果未经验证；对 LLM 安全与领域适配方向有参考价值，但作为论文摘要新意与可验证性有限。
62
正文
Computer Science > Artificial Intelligence
arXiv:2609.23071 (cs)
[Submitted on 19 Sep 2026]
Title:Tutoring Large Language Models to be Domain-adaptive, Precise and Safe
Authors:Somnath Banerjee
View a PDF of the paper titled Tutoring Large Language Models to be Domain-adaptive, Precise and Safe, by Somnath Banerjee
View PDF
HTML (experimental)
Abstract:This thesis proposes a framework for "responsible intelligence" to address AI's critical challenges in safety, ethics, and cultural sensitivity. It advances three core areas: First, it improves domain adaptation in specialized fields using active learning and graph-based knowledge to reduce hallucinations. Second, it enhances ethical rigor via a novel decoding-time alignment mechanism that proactively blocks harmful text generation in real-time. Finally, it ensures cultural and multilingual safety through language-specific steering that respects diverse linguistic and social norms. Ultimately, this work provides a blueprint for building next-generation AI that is contextually knowledgeable, ethically sound, and culturally adaptable.
Comments:
Subjects:
Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computation and Language (cs.CL)
Cite as:
arXiv:2609.23071 [cs.AI]
(or
arXiv:2609.23071v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.23071
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Somnath Banerjee [view email]
[v1]
Sat, 19 Sep 2026 15:06:26 UTC (4,369 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Tutoring Large Language Models to be Domain-adaptive, Precise and Safe, by Somnath Banerjee
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CE
cs.CL
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?)