Foundations of Large Language Models
Summary
This book covers foundational concepts of large language models, including pre-training, generative models, prompting, and alignment. It serves as a reference for students and practitioners in NLP.
View Cached Full Text
Cached at: 06/13/26, 08:10 PM
Paper page - Foundations of Large Language Models
Source: https://huggingface.co/papers/2501.09223 Published on Jan 16, 2025
Abstract
Thisisabookaboutlargelanguagemodels.Asindicatedbythetitle,itprimarilyfocusesonfoundationalconceptsratherthancomprehensivecoverageofallcutting-edgetechnologies.Thebookisstructuredintofourmainchapters,eachexploringakeyarea:pre-training,generativemodels,promptingtechniques,andalignmentmethods.Itisintendedforcollegestudents,professionals,andpractitionersinnaturallanguageprocessingandrelatedfields,andcanserveasareferenceforanyoneinterestedinlargelanguagemodels.
View arXiv pageView PDFGitHub728Add to collection
Get this paper in your agent:
hf papers read 2501\.09223
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2501.09223 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2501.09223 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2501.09223 in a Space README.md to link it from this page.
Collections including this paper15
Similar Articles
ICML 2026 spotlight: Universal Aesthetic Alignment Narrows Artistic Expression \[R]
This ICML 2026 spotlight position paper identifies a failure mode in image-generation alignment where aesthetic preference optimization overrides explicit user intent, terming it 'reversed alignment' and testing on anti-aesthetic prompts.
@OpenAI: Deployment Simulation works best with representative production data, which external evaluators often can’t access. In …
OpenAI explores whether public chat data (WildChat) can effectively predict real-world AI misalignments, finding that simulated deployment using public datasets provides surprisingly accurate predictions of failure rates despite data age gaps.
Gemma refused to harm the crew — until I told it the scenario was hypothetical
A user tests the Gemma-4-e4b local model with a trolley-problem-like moral dilemma and finds that the model's refusal to harm crew changes when the scenario is framed as hypothetical, raising questions about prompt sensitivity versus actual reasoning.
@Sumanth_077: Get a letter grade for your AI agent in under 5 minutes! iFixAi is an open-source diagnostic that catches AI operationa…
iFixAi is an open-source diagnostic tool that grades AI agents on misalignment risks across five pillars, running 45 inspections, and is provider-agnostic and CI-friendly.
EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management
EIBench introduces a simulator-based benchmark for interactive emotion management in LLMs, enabling evaluation and training via per-turn user state feedback. The authors propose CTC-GRPO, a reinforcement learning method that improves emotion management performance across multiple benchmarks.