paper-with-me

Papers

Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning

2024-07-05 · Eric Pasewark, Kyle Montgomery, Kefei Duan, Dawn Song, Chenguang Wang

We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the solution depends on solving smaller instances of the same problem. We propose a natural approach to solve compositional tasks recursively. Our method, Re-Tuning, tunes models to break down a problem into subproblems, solve those subproblems, and combine the results. We show that our method significantly improves model performance on three representative compositional tasks: integer addition, dynamic programming, and parity. Compared to state-of-the-art methods that keep intermediate steps towards solving the problems, Re-Tuning achieves significantly higher accuracy and is more GPU memory efficient.

📄 PDF Abstract BibTeX arXiv:2407.04787

Code (1)

Pasewark/ReTuning 공식 구현 pytorch

Tasks

GPU

Similar Papers 제목 키워드 기반

Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning

2024-05-05 · Jun Zhao, Jingqi Tong, Yurong Mou, Ming Zhang 외

Human cognition exhibits systematic compositionality, the algebraic ability to generate infinite novel combinations from finite learned components, which is the key to understanding and reasoning about complex logic. In …

GSM8KMathMathematical Reasoning

From Words to Worlds: Compositionality for Cognitive Architectures

2024-07-18 · Ruchira Dhar, Anders Søgaard

Large language models (LLMs) are very performant connectionist systems, but do they exhibit more compositionality? More importantly, is that part of why they perform so well? We present empirical analyses across four LLM…

Convolutional Neural Networks with Recurrent Neural Filters

2018-08-28 · EMNLP 2018 10 · Yi Yang

We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters. A convolution filter is typically implemented as a linear affine transformation followed …

SentenceSentiment Analysis

An Examination of the Compositionality of Large Generative Vision-Language Models

2023-08-21 · Teli Ma, Rong Li, Junwei Liang

With the success of Large Language Models (LLMs), many Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning. However, the performance of GVLMs in multimodal compositional reas…

Visual Reasoning

MASS: Overcoming Language Bias in Image-Text Matching

2025-01-20 · Jiwan Chung, Seungwon Lim, Sangkyu Lee, Youngjae Yu

Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantl…

Image-text matchingImage-text RetrievalMultimodal AssociationRetrieval+2