paper-with-me

홈 › Papers

Large Language Model for Science: A Study on P vs. NP

2023-09-11 · Qingxiu Dong, Li Dong, Ke Xu, Guangyan Zhou, Yaru Hao, Zhifang Sui, Furu Wei

In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics. Specifically, we propose Socratic reasoning, a general framework that promotes in-depth thinking with LLMs for complex problem-solving. Socratic reasoning encourages LLMs to recursively discover, solve, and integrate problems while facilitating self-evaluation and refinement. Our pilot study on the P vs. NP problem shows that GPT-4 successfully produces a proof schema and engages in rigorous reasoning throughout 97 dialogue turns, concluding "P $\neq$ NP", which is in alignment with (Xu and Zhou, 2023). The investigation uncovers novel insights within the extensive solution space of LLMs, shedding light on LLM for Science.

📄 PDF Abstract BibTeX arXiv:2309.05689

Code (1)

microsoft/LMOps/tree/main/LLM4Science 공식 구현 jax

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
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 $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Developing the PsyCogMetrics AI Lab to Evaluate Large Language Models and Advance Cognitive Science -- A Three-Cycle Action Design Science Study

2026-03-13 · Zhiye Jin, Yibai Li, K. D. Joshi, Xuefei 외 arxiv

This study presents the development of the PsyCogMetrics AI Lab (psycogmetrics.ai), an integrated, cloud-based platform that operationalizes psychometric and cognitive-science methodologies for Large Language Model (LLM)…

Friend or Foe? Exploring the Implications of Large Language Models on the Science System

2023-06-16 · Benedikt Fecher, Marcel Hebing, Melissa Laufer, Jörg Pohle 외

The advent of ChatGPT by OpenAI has prompted extensive discourse on its potential implications for science and higher education. While the impact on education has been a primary focus, there is limited empirical research…

Misinformation

Context Matters: A Strategy to Pre-train Language Model for Science Education

2023-01-27 · Zhengliang Liu, Xinyu He, Lei Liu, Tianming Liu 외

This study aims at improving the performance of scoring student responses in science education automatically. BERT-based language models have shown significant superiority over traditional NLP models in various language-…

ArticlesLanguage ModelingLanguage Modelling

Evaluating the Performance of Large Language Models for Spanish Language in Undergraduate Admissions Exams

2023-12-28 · Sabino Miranda, Obdulia Pichardo-Lagunas, Bella Martínez-Seis, Pierre Baldi

This study evaluates the performance of large language models, specifically GPT-3.5 and BARD (supported by Gemini Pro model), in undergraduate admissions exams proposed by the National Polytechnic Institute in Mexico. Th…

HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science

2023-10-12 · Yu Song, Santiago Miret, huan zhang, Bang Liu

We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee). MatSci…

Language ModelingLanguage Modelling