paper-with-me

홈 › Papers

Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge

2024-02-22 · Jinlan Fu, Shenzhen Huangfu, Hang Yan, See-Kiong Ng, Xipeng Qiu

Large Language Models (LLMs) have recently showcased remarkable generalizability in various domains. Despite their extensive knowledge, LLMs still face challenges in efficiently utilizing encoded knowledge to develop accurate and logical reasoning processes. To mitigate this problem, we introduced Hint-before-Solving Prompting (HSP), which guides the model to generate hints (e.g., specific knowledge or key ideas) for solving the problem and then generate solutions containing intermediate reasoning steps. Since HSP is orthogonal to prompting methods (e.g., Chain-of-Thought (CoT)), we applied HSP to CoT, Least-to-Most, Plan-and-Solve, and Standard promptings. The results of extensive experiments on 6 reasoning benchmarks and 4 open-source LLMs demonstrate that HSP can effectively improve the accuracy of reasoning tasks: (1) By applying high-quality hint-enhanced HSP to CoT prompting, Llama2-70B-Chat shows an improvement of 9.7. (2) Beyond exploring training-free LLM capabilities, we built the HSPMATH dataset based on HSP and fine-tuned Llemma-7B, reaching 64.3 accuracy, surpassing GPT-3.5 and WizardMath-13B. We make our code and dataset publicly available at \url{https://github.com/jinlanfu/HSP}.

📄 PDF Abstract BibTeX arXiv:2402.14310

Code (1)

jinlanfu/hsp 공식 구현 pytorch

Tasks

Logical 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 &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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…
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…

Similar Papers 제목 키워드 기반

Give me a hint: Can LLMs take a hint to solve math problems?

2024-10-08 · Vansh Agrawal, Pratham Singla, Amitoj Singh Miglani, Shivank Garg 외

While state-of-the-art LLMs have shown poor logical and basic mathematical reasoning, recent works try to improve their problem-solving abilities using prompting techniques. We propose giving "hints" to improve the langu…

Adversarial RobustnessMathMathematical ReasoningSensitivity

Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints

2024-05-28 · Aryo Pradipta Gema, Chaeeun Lee, Pasquale Minervini, Luke Daines 외

The MEDIQA-CORR 2024 shared task aims to assess the ability of Large Language Models (LLMs) to identify and correct medical errors in clinical notes. In this study, we evaluate the capability of general LLMs, specificall…

Multiple-choiceSentence

From Text to Visuals: Using LLMs to Generate Math Diagrams with Vector Graphics

2025-03-10 · Jaewook Lee, Jeongah Lee, Wanyong Feng, Andrew Lan

Advances in large language models (LLMs) offer new possibilities for enhancing math education by automating support for both teachers and students. While prior work has focused on generating math problems and high-qualit…

MathQuestion AnsweringVector GraphicsVisual Question Answering

R$^3$ Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context

2023-10-25 · Qingyuan Tian, Hanlun Zhu, Lei Wang, Yang Li 외

With the help of Chain-of-Thought (CoT) prompting, Large Language Models (LLMs) have achieved remarkable performance on various reasoning tasks. However, most of them have been evaluated under noise-free context and the …

Sentence

Guiding Large Language Models via Directional Stimulus Prompting

2023-02-22 · NeurIPS 2023 11 · Zekun Li, Baolin Peng, Pengcheng He, Michel Galley 외

We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable po…

Response Generation