paper-with-me

Papers

Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization

2024-04-02 · Tobias Schnabel, Jennifer Neville

In many modern LLM applications, such as retrieval augmented generation, prompts have become programs themselves. In these settings, prompt programs are repeatedly called with different user queries or data instances. A big practical challenge is optimizing such prompt programs. Recent work has mostly focused on either simple prompt programs or assumed that the general structure of a prompt program is fixed. We introduce SAMMO, a framework to perform symbolic prompt program search for compile-time optimizations of prompt programs. SAMMO represents prompt programs on a symbolic level which allows for a rich set of transformations that can be searched over during optimization. We show that SAMMO generalizes previous methods and improves the performance of complex prompts on (1) instruction tuning, (2) RAG pipeline tuning, and (3) prompt compression, across several different LLMs. We make all code available open-source at https://github.com/microsoft/sammo .

📄 PDF Abstract BibTeX arXiv:2404.02319

Code (1)

microsoft/sammo 공식 구현

Tasks

RAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Attention 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
WordPiece 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning

2023-09-19 · Tianhua Zhang, Jiaxin Ge, Hongyin Luo, Yung-Sung Chuang 외

How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning? We propose natural language embedded programs (NLEP) as a unifying framework for addressin…

Instruction FollowingLanguage ModelingLanguage ModellingMath+4

Fitness Landscape Analysis of Dimensionally-Aware Genetic Programming Featuring Feynman Equations

2020-04-27 · Marko Durasevic, Domagoj Jakobovic, Marcella Scoczynski Ribeiro Martins, Stjepan Picek 외

Genetic programming is an often-used technique for symbolic regression: finding symbolic expressions that match data from an unknown function. To make the symbolic regression more efficient, one can also use dimensionall…

regressionSymbolic Regression

Specify What? Enhancing Neural Specification Synthesis by Symbolic Methods

2024-06-21 · George Granberry, Wolfgang Ahrendt, Moa Johansson

We investigate how combinations of Large Language Models (LLMs) and symbolic analyses can be used to synthesise specifications of C programs. The LLM prompts are augmented with outputs from two formal methods tools in th…

Predicting Performance of Symbolic and Prompt Programs with Examples

2026-05-15 · Chengqi Zheng, Keya Hu, Shuzhi Liu, Tao Wu 외 arxiv

LLM prompting is widely used for naturally stated tasks, yet it is unreliable it may succeed on a few test cases but fail at deployment time. We study performance prediction: given a program, either symbolic (e.g. Python…

FunctionEvolve: Structure-Guided Symbolic Regression with LLMs

2026-06-05 · Zeyu Xia, Jun Zhu, Dong Yan arxiv

Symbolic regression aims to uncover explicit scientific laws from data. Recent methods use LLMs to guide mutation from background text, which is more directed than random genetic programming. However, exact symbolic reco…