paper-with-me

Papers

Arithmetic Reasoning with LLM: Prolog Generation & Permutation

2024-05-28 · Xiaocheng Yang, Bingsen Chen, Yik-Cheung Tam

Instructing large language models (LLMs) to solve elementary school math problems has shown great success using Chain of Thought (CoT). However, the CoT approach relies on an LLM to generate a sequence of arithmetic calculations which can be prone to cascaded calculation errors. We hypothesize that an LLM should focus on extracting predicates and generating symbolic formulas from the math problem description so that the underlying calculation can be done via an external code interpreter. We investigate using LLM to generate Prolog programs to solve mathematical questions. Experimental results show that our Prolog-based arithmetic problem-solving outperforms CoT generation in the GSM8K benchmark across three distinct LLMs. In addition, given the insensitive ordering of predicates and symbolic formulas in Prolog, we propose to permute the ground truth predicates for more robust LLM training via data augmentation.

📄 PDF Abstract BibTeX arXiv:2405.17893

Code (0)

등록된 구현이 없습니다.

Tasks

Arithmetic ReasoningData AugmentationGSM8KMath

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Exploring an LM to generate Prolog Predicates from Mathematics Questions

2023-09-07 · Xiaocheng Yang, Yik-Cheung Tam

Recently, there has been a surge in interest in NLP driven by ChatGPT. ChatGPT, a transformer-based generative language model of substantial scale, exhibits versatility in performing various tasks based on natural langua…

GSM8KLanguage ModelingLanguage Modelling

Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs

2023-11-16 · Sen yang, Xin Li, Leyang Cui, Lidong Bing 외

Two lines of approaches are adopted for complex reasoning with LLMs. One line of work prompts LLMs with various reasoning structures, while the structural outputs can be naturally regarded as intermediate reasoning steps…

Arithmetic ReasoningGSM8KLogical Reasoning

Reliable Reasoning Beyond Natural Language

2024-07-16 · Nasim Borazjanizadeh, Steven T. Piantadosi

Despite their linguistic competence, Large Language models (LLMs) often exhibit limitations in their ability to reason reliably and flexibly. To address this, we propose a neurosymbolic approach that prompts LLMs to extr…

GSM8KMathematical ReasoningNavigate

DeonticBench: A Benchmark for Reasoning over Rules

2026-04-06 · Guangyao Dou, Luis Brena, Akhil Deo, William Jurayj 외 arxiv

Reasoning with complex, context-specific rules remains challenging for large language models (LLMs). In legal and policy settings, this manifests as deontic reasoning: reasoning about obligations, permissions, and prohib…

Reinforcement LearningMathematical Reasoning

Autoregressive Visual Generation Needs a Prologue

2026-05-07 · Bowen Zheng, Weijian Luo, Guang Yang, Colin Zhang 외 arxiv

In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction and generation, Prol…

Image Generation