arXiv subjects

Shaohua Hu

Publications and source records attributed to Shaohua Hu.

3 recordsLinked to original sources

arXiv2024

Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models

Large language models (LLMs) still grapple with complex tasks like mathematical reasoning. Despite significant efforts invested in improving prefix prompts or reasoning process, the crucial role of problem context might have been neglected. Accurate recognition of inputs is fundamental for solving mathematical tasks, as ill-formed problems could potentially mislead LLM's reasoning. In this study, we propose a new approach named Problem Elaboration Prompting (PEP) to enhance the mathematical capacities of LLMs. Specifically, PEP decomposes and elucidates the problem context before reasoning, therefore enhancing the context modeling and parsing efficiency. Experiments across datasets and models demonstrate promising performances: (1) PEP demonstrates an overall enhancement in various mathematical tasks. For instance, with the GPT-3.5 model, PEP exhibits improvements of 9.93% and 8.80% on GSM8k through greedy decoding and self-consistency, respectively. (2) PEP can be easily implemented and integrated with other prompting methods. (3) PEP shows particular strength in handling distraction problems.

cs.CL↗

arXiv2023

Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent

Large language models (LLMs) face challenges in solving complex mathematical problems that require comprehensive capacities to parse the statements, associate domain knowledge, perform compound logical reasoning, and integrate the intermediate rationales. Tackling all these problems once could be arduous for LLMs, thus leading to confusion in generation. In this work, we explore the potential of enhancing LLMs with agents by meticulous decomposition and modeling of mathematical reasoning process. Specifically, we propose a formal description of the mathematical solving and extend LLMs with an agent-based zero-shot framework named $\bf{P}$lanner-$\bf{R}$easoner-$\bf{E}$xecutor-$\bf{R}$eflector (PRER). We further provide and implement two MathAgents that define the logical forms and inherent relations via a pool of actions in different grains and orientations: MathAgent-M adapts its actions to LLMs, while MathAgent-H aligns with humankind. Experiments on miniF2F and MATH have demonstrated the effectiveness of PRER and proposed MathAgents, achieving an increase of $12.3\%$($53.9\%\xrightarrow{}66.2\%$) on the MiniF2F, $9.2\%$ ($49.8\%\xrightarrow{}59.0\%$) on MATH, and $13.2\%$($23.2\%\xrightarrow{}35.4\%$) for level-5 problems of MATH against GPT-4. Further analytical results provide more insightful perspectives on exploiting the behaviors of LLMs as agents.

cs.AI↗

arXiv2023

Integrated Simulation Platform for Quantifying the Traffic-Induced Environmental and Health Impacts

Air quality and human exposure to mobile source pollutants have become major concerns in urban transportation. Existing studies mainly focus on mitigating traffic congestion and reducing carbon footprints, with limited understanding of traffic-related health impacts from the environmental justice perspective. To address this gap, we present an innovative integrated simulation platform that models traffic-related air quality and human exposure at the microscopic level. The platform consists of five modules: SUMO for traffic modeling, MOVES for emissions modeling, a 3D grid-based dispersion model, a Matlab-based concentration visualizer, and a human exposure model. Our case study on multi-modal mobility on-demand services demonstrates that a distributed pickup strategy can reduce human cancer risk associated with PM2.5 by 33.4% compared to centralized pickup. Our platform offers quantitative results of traffic-related air quality and health impacts, useful for evaluating environmental issues and improving transportation systems management and operations strategies.

physics.soc-ph↗