paper-with-me

Papers

Small Models, Big Support: A Local LLM Framework for Teacher-Centric Content Creation and Assessment using RAG and CAG

2025-06-06 · Zarreen Reza, Alexander Mazur, Michael T. Dugdale, Robin Ray-Chaudhuri

While Large Language Models (LLMs) are increasingly utilized as student-facing educational aids, their potential to directly support educators, particularly through locally deployable and customizable open-source solutions, remains significantly underexplored. Many existing educational solutions rely on cloud-based infrastructure or proprietary tools, which are costly and may raise privacy concerns. Regulated industries with limited budgets require affordable, self-hosted solutions. We introduce an end-to-end, open-source framework leveraging small (3B-7B parameters), locally deployed LLMs for customized teaching material generation and assessment. Our system uniquely incorporates an interactive loop crucial for effective small-model refinement, and an auxiliary LLM verifier to mitigate jailbreaking risks, enhancing output reliability and safety. Utilizing Retrieval and Context Augmented Generation (RAG/CAG), it produces factually accurate, customized pedagogically-styled content. Deployed on-premises for data privacy and validated through an evaluation pipeline and a college physics pilot, our findings show that carefully engineered small LLM systems can offer robust, affordable, practical, and safe educator support, achieving utility comparable to larger models for targeted tasks.

📄 PDF Abstract BibTeX arXiv:2506.05925

Code (0)

등록된 구현이 없습니다.

Tasks

College PhysicsRAG

Similar Papers 제목 키워드 기반

Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation

2026-05-21 · Dong Nie arxiv

Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forwar…

Reinforcement Learning

EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots

2026-02-20 · Boyuan An, Zhexiong Wang, Yipeng Wang, Jiaqi Li 외 arxiv

Humans can rearrange objects in cluttered environments using egocentric perception, navigating occlusions without global coordinates. Inspired by this capability, we study long-horizon multi-object non-prehensile rearran…

Object Rearrangement

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection

2026-05-26 · Zhengyu Hu, Zheyuan Xiao, Linxin Song, Fengqing Jiang 외 arxiv

LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the highest-performing teacher to generate stude…

Answer Selection

Reasoning Compression with Mixed-Policy Distillation

2026-05-09 · Han Yang, Mingyan Wu, Bailan He, Zeyu Cao 외 arxiv

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, w…

Evolve: A Persistent Knowledge Lifecycle for Small Language Models

2026-04-25 · Dikran Hovagimian arxiv

Evolve pairs a small local language model with a persistent, teacher-compiled knowledge store -- refined through sleep consolidation and usage-driven refresh -- to deliver substantial accuracy gains over the model's para…