paper-with-me

홈 › Papers

SMART SLM: Structured Memory and Reasoning Transformer, A Small Language Model for Accurate Document Assistance

2025-12-24 · Divij Dudeja, Mayukha Pal arxiv

The user of Engineering Manuals (EM) finds it difficult to read EM s because they are long, have a dense format which includes written documents, step by step procedures, and standard parameter lists for engineering equipment. Off the shelf transformers, especially compact ones, treat this material as a flat stream of tokens. This approach leads to confident but incorrect numeric answers and forces the models to memorize separate facts inefficiently. SMART (Structured Memory and Reasoning Transformer) offers a different and practical solution to the above problem. SMART structures its processing by using a hierarchical approach, and is based upon three main job categories (1) A syntax-aware Fact Extractor (Grammarian) Tree LSTM which extracts facts as subject relation object relations from EM sentences (2) A compact indexed memory MANN (Memory Augmented Neural Network) that indexes these Rational Subject Relation Objects as 384 dimensional vectors that are associated with the source of the information, and (3) A 6 layer Transformer that learns to fuse the previously retrieved facts into its generated response. The entire SMART model utilizes 45.51M parameters, which is 64% less than GPT-2 (124M) and 69% less than BERT (133M), and it achieves a 21.3% higher accuracy than GPT-2, indicating that SMART fits the data better with the least amount of processing requirements. SMART employs dual modes of inference an indexed fast path for known documents (sub-second answer times) and an indexed dynamic path assisted by RAGs for new uploads (FAISS Top 20 results with memory severed at 64 slots). In real world deployment, this framework leads to more well supported results with reduced hallucinations than comparable small transformer models.

📄 PDF Abstract BibTeX arXiv:2512.21280

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SCENIC: Semantic-Conditioned Edge-Aware Neural Framework for Structured IoT Command Generation

2026-06-21 · Luke Ztz Hu, Hongbing Lang, Songping Mai arxiv

Edge Internet of Things (IoT) agents are often constrained by memory capacity, privacy requirements, communication latency, and recurring inference cost. Current smart-home assistants commonly rely on API-level command i…

D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree

2025-10-15 · Xiang Lei, Qin Li, Min Zhang, Min Zhang arxiv

Large Language Models (LLMs) often exhibit factual inconsistencies and logical decay in extended, multi-turn dialogues, a challenge stemming from their reliance on static, pre-trained knowledge and an inability to reason…

PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs

2026-03-10 · Jinyue Li, Yuci Liang, Qiankun Li, Xinheng Lyu 외 arxiv

Computational pathology demands both visual pattern recognition and dynamic integration of structured domain knowledge, including taxonomy, grading criteria, and clinical evidence. In practice, diagnostic reasoning requi…

TPRF: A Transformer-based Pseudo-Relevance Feedback Model for Efficient and Effective Retrieval

2024-01-24 · Hang Li, Chuting Yu, Ahmed Mourad, Bevan Koopman 외

This paper considers Pseudo-Relevance Feedback (PRF) methods for dense retrievers in a resource constrained environment such as that of cheap cloud instances or embedded systems (e.g., smartphones and smartwatches), wher…

CPURetrieval

Detecting Transportation Mode Using Dense Smartphone GPS Trajectories and Transformer Models

2026-02-27 · Yuandong Zhang, Othmane Echchabi, Tianshu Feng, Wenyi Zhang 외 arxiv

Transportation mode detection is an important topic within GeoAI and transportation research. In this study, we introduce SpeedTransformer, a novel Transformer-based model that relies solely on speed inputs to infer tran…

Transfer Learning