paper-with-me

Papers

Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models

2024-04-22 · Vishruth Veerendranath, Vishwa Shah, Kshitish Ghate

Quantitative and numerical comprehension in language is an important task in many fields like education and finance, but still remains a challenging task for language models. While tool and calculator usage has shown to be helpful to improve mathematical reasoning in large pretrained decoder-only language models, this remains unexplored for smaller language models with encoders. In this paper, we propose Pre-Calc, a simple pre-finetuning objective of learning to use the calculator for both encoder-only and encoder-decoder architectures, formulated as a discriminative and generative task respectively. We pre-train BERT and RoBERTa for discriminative calculator use and Flan-T5 for generative calculator use on the MAWPS, SVAMP, and AsDiv-A datasets, which improves performance on downstream tasks that require numerical understanding. Our code and data are available at https://github.com/calc-cmu/pre-calc.

📄 PDF Abstract BibTeX arXiv:2404.14355

Code (1)

calc-cmu/pre-calc 공식 구현 pytorch

Tasks

DecoderMathematical Reasoning

Methods 이 논문이 사용한 방법론

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 &…
Attention 설명 없음
Weight Decay 설명 없음
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…
Residual Connection 설명 없음
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 $x$…
Adam 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

An LLM-Powered Clinical Calculator Chatbot Backed by Verifiable Clinical Calculators and their Metadata

2025-03-21 · Niranjan Kumar, Farid Seifi, Marisa Conte, Allen Flynn

Clinical calculators are widely used, and large language models (LLMs) make it possible to engage them using natural language. We demonstrate a purpose-built chatbot that leverages software implementations of verifiable …

ChatbotRAGRetrieval-augmented Generation

MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents

2026-07-03 · Siran Zhao, Ruihui Hou, Ziyue Huai, Chennuo Zhang 외 arxiv

Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case corresponds to a single calculator and the required tool is explicit…

Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators

2024-11-08 · Nicholas Wan, Qiao Jin, Joey Chan, Guangzhi Xiong 외

Although large language models (LLMs) have been assessed for general medical knowledge using licensing exams, their ability to support clinical decision-making, such as selecting medical calculators, remains uncertain. W…

Decision MakingMultiple-choicePrognosis

AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning

2024-02-20 · Qiao Jin, Zhizheng Wang, Yifan Yang, Qingqing Zhu 외

Clinical calculators play a vital role in healthcare by offering accurate evidence-based predictions for various purposes such as prognosis. Nevertheless, their widespread utilization is frequently hindered by usability …

Prognosis

MeNTi: Bridging Medical Calculator and LLM Agent with Nested Tool Calling

2024-10-17 · Yakun Zhu, Shaohang Wei, Xu Wang, Kui Xue 외

Integrating tools into Large Language Models (LLMs) has facilitated the widespread application. Despite this, in specialized downstream task contexts, reliance solely on tools is insufficient to fully address the complex…

slot-fillingSlot Filling