Jove
Visualize
お問い合わせ
JoVE
x logofacebook logolinkedin logoyoutube logo
JoVEについて
概要リーダーシップブログJoVEヘルプセンター
著者向け
出版プロセス編集委員会範囲と方針査読よくある質問投稿
図書館員向け
推薦の声購読アクセスリソース図書館諮問委員会よくある質問
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experimentsアーカイブ
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教員リソースセンター教員サイト
利用規約
プライバシーポリシー
ポリシー

関連する概念動画

Proofreading01:31

Proofreading

6.6K
Synthesis of new DNA molecules is carried out by the enzyme DNA polymerase, which adds nucleotides on the daughter strand complementary to the template DNA strand. DNA polymerase has a higher affinity to add the correct base and ensures fidelity during DNA replication. Furthermore,  it exhibits proofreading activity during replication, using an exonuclease domain that cuts off incorrect nucleotides from the nascent DNA strand.
Errors During Replication are Corrected by the DNA Polymerase...
6.6K
Spanning Openings in Brick Walls01:20

Spanning Openings in Brick Walls

253
In brick wall construction, supporting structures are crucial for openings like windows and doors to maintain the integrity and support the weight of the wall above. These supports include lintels, corbels, and arches, each serving specific structural purposes.
Lintels are primary supports used to span openings and can be crafted from materials such as reinforced concrete, steel-reinforced brick masonry, or simple steel angles. These are straightforward to install and are typically concealed...
253
Hindsight Biases01:12

Hindsight Biases

3.9K
Hindsight bias leads you to believe that the event you just experienced was predictable, even though it really wasn’t. In other words, you knew all along that things would turn out the way they did. Can you relate this to the phrase "Hindsight is 20/20" now? 
3.9K
Longitudinal Research02:20

Longitudinal Research

12.4K
Sometimes we want to see how people change over time, as in studies of human development and lifespan. When we test the same group of individuals repeatedly over an extended period of time, we are conducting longitudinal research. Longitudinal research is a research design in which data-gathering is administered repeatedly over an extended period of time. For example, we may survey a group of individuals about their dietary habits at age 20, retest them a decade later at age 30, and then again...
12.4K
Ogive Graph01:07

Ogive Graph

5.8K
An ogive graph is sometimes called a cumulative frequency polygon. It is one type of frequency polygon that shows cumulative frequency. In other words, the cumulative percentages are added to the graph from left to right. An ogive graph plots cumulative frequency on the vertical y-axis and class boundaries along the horizontal x-axis. It’s very similar to a histogram; only instead of rectangles, an ogive displays a single point where the top right of the rectangle would be. Creating this...
5.8K
Improving Translational Accuracy02:07

Improving Translational Accuracy

2.7K
2.7K

こちらも読む

関連記事

共著者、ジャーナル、引用グラフによってこの研究に関連する記事。

並び替え
Same author

Attention guided fair artificial intelligence modeling for skin cancer diagnosis.

NPJ digital medicine·2026
Same author

Multi-modal deep temporal adversarial network based on multi-head self-attention for breast cancer survival prediction.

Computer methods in biomechanics and biomedical engineering·2026
Same author

Unlocking the acquired ultraviolet-resistance and enhanced antioxidant potential of pterostilbene-loaded pharmaceutical-dots.

International journal of pharmaceutics: X·2026
Same author

Artemiannua A, new sesquiterpenoid from the aerial part of <i>artemisia annua</i> with anti-inflammatory activity.

Natural product research·2026
Same author

Recurring transient brain-wide co-activation patterns from EEG spatially resembling time-averaged resting-state networks.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

3D microscope image acquisition method based on a liquid lens with a translational field of view.

Optics express·2026
Same journal

RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models.

Proceedings of the conference. Association for Computational Linguistics. Meeting·2026
Same journal

Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging.

Proceedings of the conference. Association for Computational Linguistics. Meeting·2026
Same journal

Improving Formality Style Transfer with Context-Aware Rule Injection.

Proceedings of the conference. Association for Computational Linguistics. Meeting·2026
Same journal

SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks.

Proceedings of the conference. Association for Computational Linguistics. Meeting·2025
Same journal

IRIS: Interpretable Retrieval-Augmented Classification for Long Interspersed Document Sequences.

Proceedings of the conference. Association for Computational Linguistics. Meeting·2025
Same journal

Logic-driven Indirect Supervision: An Application to Crisis Counseling.

Proceedings of the conference. Association for Computational Linguistics. Meeting·2025
関連記事をすべて見る

関連する実験動画

Updated: Sep 8, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

565

GraphCheck: 抽出された知識によるグラフ駆動の事実確認により,長期にわたるテキストの障壁を克服する

Yingjian Chen1, Haoran Liu2, Yinhong Liu3

  • 1University of Tokyo.

Proceedings of the conference. Association for Computational Linguistics. Meeting
|August 20, 2025
PubMed
まとめ
この要約は機械生成です。

GraphCheckは,知識グラフを使用して事実の正確性を高めるために,大規模な言語モデル (LLM) を強化します. このフレームワークは,医療および一般的なテキストの事実確認を改善し,エラーと計算コストを削減します.

さらに関連する動画

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.7K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

680

関連する実験動画

Last Updated: Sep 8, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

565
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.7K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

680

科学分野:

  • 人工知能
  • 自然言語処理
  • コンピュータ言語学

背景:

  • 大型言語モデル (LLM) は,特に広範なテキストでは,しばしば微妙な事実上のエラーを生成します.
  • これらの不正確さは 医学のような専門分野において 重要なリスクをもたらします
  • 現在の事実確認方法は 長い文書の複合的なマルチホップ推論に苦戦し 計算コストが高くなります

研究 の 目的:

  • LLMの正確性を向上させるために設計された新しい事実チェックフレームワークであるGraphCheckを導入する.
  • マルチホップ推論の難しさや高い計算要求を含む既存の事実確認方法の限界に対処する.

主な方法:

  • GraphCheckは,知識グラフを抽出して,テキスト表現を豊かにします.
  • グラフ ニューラルネットワークはこれらのグラフをLLMのソフトプロンプトとして処理し,構造化された知識を統合します.
  • このフレームワークは,複雑な推論の連鎖を捉えるためにグラフベースの推論を採用しています.

主要な成果:

  • グラフチェックは,一般的および医療分野における7つのベンチマークで,全体的に7.1%の改善を示しました.
  • このフレームワークは,他の方法ではしばしば見逃されるマルチホップの推論の連鎖を効果的に捉えます.
  • GraphCheckは,非常に少ないパラメータで最先端のLLMに匹敵する性能を達成しました.

結論:

  • GraphCheckは,LLMの事実確認のための正確で効率的なソリューションを提供します.
  • このフレームワークは,特にエラーに敏感な領域において,事実の正確性を大幅に高めます.
  • GraphCheckは,既存の専門的な事実確認モデルに対して,計算効率の良い代替案を提示しています.