paper-with-me

홈 › Papers

Unlocking Structured Thinking in Language Models with Cognitive Prompting

2024-10-03 · Oliver Kramer, Jill Baumann

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern recognition. By employing systematic, step-by-step reasoning, cognitive prompting enables LLMs to tackle complex, multi-step tasks more efficiently. We introduce three variants: a deterministic sequence of cognitive operations, a self-adaptive variant in which the LLM dynamically selects the sequence of cognitive operations, and a hybrid variant that uses generated correct solutions as few-shot chain-of-thought prompts. Experiments with LLaMA, Gemma~2, and Qwen models in each two sizes on the arithmetic reasoning benchmark GSM8K demonstrate that cognitive prompting significantly improves performance compared to standard question answering.

📄 PDF Abstract BibTeX arXiv:2410.02953

Code (0)

등록된 구현이 없습니다.

Tasks

Arithmetic ReasoningGSM8KQuestion Answering

Methods 이 논문이 사용한 방법론

LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…

Similar Papers 제목 키워드 기반

Intention Chain-of-Thought Prompting with Dynamic Routing for Code Generation

2025-12-16 · Shen Li, Li Huang, Shaoxiong Zhan, Weifeng Sun 외 arxiv

Large language models (LLMs) exhibit strong generative capabilities and have shown great potential in code generation. Existing chain-of-thought (CoT) prompting methods enhance model reasoning by eliciting intermediate s…

Code Generation

Reasoning Riddles: How Explainability Reveals Cognitive Limits in Vision-Language Models

2025-10-03 · Prahitha Movva arxiv

Vision-Language Models (VLMs) excel at many multimodal tasks, yet their cognitive processes remain opaque on complex lateral thinking challenges like rebus puzzles. While recent work has demonstrated these models struggl…

The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models

2023-05-24 · Jingyuan Qi, Zhiyang Xu, Ying Shen, Minqian Liu 외

Chain-of-Thought (CoT) prompting enables large language models to solve complex reasoning problems by generating intermediate steps. However, confined by its inherent single-pass and sequential generation process, CoT he…

Language ModellingMathMMLUQuestion Answering+1

Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education

2026-01-21 · Unggi Lee, Jiyeong Bae, Jaehyeon Park, Haeun Park 외 arxiv

Large language models (LLMs) are increasingly deployed as intelligent tutoring systems, yet research on optimizing LLMs specifically for educational contexts remains limited. Recent works have proposed reinforcement lear…

Reinforcement Learning

RISCORE: Enhancing In-Context Riddle Solving in Language Models through Context-Reconstructed Example Augmentation

2024-09-24 · Ioannis Panagiotopoulos, Giorgos Filandrianos, Maria Lymperaiou, Giorgos Stamou

Riddle-solving requires advanced reasoning skills, pushing LLMs to engage in abstract thinking and creative problem-solving, often revealing limitations in their cognitive abilities. In this paper, we examine the riddle-…

Multiple-choiceSentence