paper-with-me

홈 › Papers

SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddings

2025-03-25 · Farhana Keya, Gollam Rabby, Prasenjit Mitra, Sahar Vahdati, Sören Auer, Yaser Jaradeh

Every scientific discovery starts with an idea inspired by prior work, interdisciplinary concepts, and emerging challenges. Recent advancements in large language models (LLMs) trained on scientific corpora have driven interest in AI-supported idea generation. However, generating context-aware, high-quality, and innovative ideas remains challenging. We introduce SCI-IDEA, a framework that uses LLM prompting strategies and Aha Moment detection for iterative idea refinement. SCI-IDEA extracts essential facets from research publications, assessing generated ideas on novelty, excitement, feasibility, and effectiveness. Comprehensive experiments validate SCI-IDEA's effectiveness, achieving average scores of 6.84, 6.86, 6.89, and 6.84 (on a 1-10 scale) across novelty, excitement, feasibility, and effectiveness, respectively. Evaluations employed GPT-4o, GPT-4.5, DeepSeek-32B (each under 2-shot prompting), and DeepSeek-70B (3-shot prompting), with token-level embeddings used for Aha Moment detection. Similarly, it achieves scores of 6.87, 6.86, 6.83, and 6.87 using GPT-4o under 5-shot prompting, GPT-4.5 under 3-shot prompting, DeepSeek-32B under zero-shot chain-of-thought prompting, and DeepSeek-70B under 5-shot prompting with sentence-level embeddings. We also address ethical considerations such as intellectual credit, potential misuse, and balancing human creativity with AI-driven ideation. Our results highlight SCI-IDEA's potential to facilitate the structured and flexible exploration of context-aware scientific ideas, supporting innovation while maintaining ethical standards.

📄 PDF Abstract BibTeX arXiv:2503.19257

Code (0)

등록된 구현이 없습니다.

Tasks

scientific discoverySentenceSentence Embeddings

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network

2025-11-04 · Keyu Zhao, Weiquan Lin, Qirui Zheng, Fengli Xu 외 arxiv

Novel research ideas play a critical role in advancing scientific inquiries. Recent advancements in Large Language Models (LLMs) have demonstrated their potential to generate novel research ideas by leveraging large-scal…

Semantic Similarity

MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models

2026-03-19 · Chenyang Gu, Jiahao Cheng, Meicong Zhang, Pujun Zheng 외 arxiv

Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research workflows, yet inadequately model scientific reasoning, resulting in sur…

Reinforcement Learning

IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation

2026-07-11 · Hengquan Guo arxiv

Scientific ideation unfolds over multiple stages, including literature search, paper reading, tool use, claim checking, cross-paper synthesis, brainstorming, rejection of weak directions, and iterative writing. Yet most …

Text Generation

IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery

2025-04-23 · Aniketh Garikaparthi, Manasi Patwardhan, Lovekesh Vig, Arman Cohan

The rapid advancement in capabilities of large language models (LLMs) raises a pivotal question: How can LLMs accelerate scientific discovery? This work tackles the crucial first stage of research, generating novel hypot…

scientific discovery

PHASE: Learning Emotional Phase-aware Representations for Suicide Ideation Detection on Social Media

2021-04-01 · EACL 2021 2 · Ramit Sawhney, Harshit Joshi, Lucie Flek, Rajiv Ratn Shah

Recent psychological studies indicate that individuals exhibiting suicidal ideation increasingly turn to social media rather than mental health practitioners. Contextualizing the build-up of such ideation is critical for…