paper-with-me

Papers

Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems

2023-05-24 · Marek Kadlčík, Michal Štefánik, Ondřej Sotolář, Vlastimil Martinek

Despite outstanding performance in many tasks, language models are notoriously inclined to make factual errors in tasks requiring arithmetic computation. We address this deficiency by creating Calc-X, a collection of datasets that demonstrates the appropriate use of a calculator in reasoning chains. Calc-X is suitable for teaching language models to offload computations to a symbolic system. We survey and unify several existing chain-of-thought datasets into a proposed format, resulting in a standard collection of over 300,000 samples requiring arithmetic reasoning. Finally, we use the new Calc-X collection to train open-source calculator-using models we call Calcformers and show that these models approximately double the accuracy of generating correct results compared to vanilla language model baselines. We make all Calc-X datasets, source code and Calcformers models publicly available.

📄 PDF Abstract BibTeX arXiv:2305.15017

Code (1)

prompteus/calc-x 공식 구현 pytorch

Tasks

Arithmetic ReasoningGSM8KLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

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

Quantifying the Necessity of Chain of Thought through Opaque Serial Depth

2026-03-10 · Jonah Brown-Cohen, David Lindner, Rohin Shah arxiv

Large language models (LLMs) tend to externalize their reasoning in their chain of thought, making the chain of thought a good target for monitoring. This is partially an inherent feature of the Transformer architecture:…

SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation

2025-10-29 · Sina Bagheri Nezhad, Yao Li, Ameeta Agrawal arxiv

Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought s…

Mathematical ReasoningLogical FallaciesCode Generation

Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts

2023-11-14 · Leonardo Ranaldi, Giulia Pucci, Federico Ranaldi, Elena Sofia Ruzzetti 외

Reasoning methods, best exemplified by the well-known Chain-of-Thought (CoT), empower the reasoning abilities of Large Language Models (LLMs) by eliciting them to solve complex tasks in a step-by-step manner. Although th…

ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting

2024-03-21 · Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen

Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs), establishing itself as a primary approach to solving complex reasoning tasks. Existing CoT synthesis approaches usu…