Comments (1)
AkihikoWatanabe
commented on June 12, 2024
Aspect-basedなPDSに関して調査した研究。
たとえば、Wikipediaのクジラに関するページでは、biological taxonomy, physical dimensions, popular cultureのように、様々なアスペクトからテキストが記述されている。ユーザモデルは各アスペクトに対する嗜好の度合いで表され、それに従い生成される要約に含まれる各種アスペクトに関する情報の量が変化する。
UserStudyの結果、アスペクトベースなユーザモデルとよりfitした、擬似的なユーザモデルから生成された要約の方が、ユーザの要約に対するratingが上昇していくことを示した。
また、要約の圧縮率に応じて、ユーザのratingが変化し、originalの長さ＞長めの要約＞短い要約の順にratingが有意に高かった。要約が長すぎても、あるいは短すぎてもあまり良い評価は得られない（しかしながら、長すぎる要約は実はそこまで嫌いではないことをratingは示唆している）。
Genericな要約とPersonalizedな要約のfaitufulnessをスコアリングしてもらった結果、Genericな要約の方が若干高いスコアに。しかしながら有意差はない。実際、平均して83%のsentenceはGenericとPersonalizedでoverlapしている。faitufulnessの観点から、GenericとPersonalizedな要約の間に有意差はないことを示した。
museum等で応用することを検討
from paper_notes.
Related Issues (20)
- A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models, S. M Towhidul Islam Tonmoy+, N/A, arXiv'24
- Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models, Zixiang Chen+, N/A, arXiv'24
- LLaMA Pro: Progressive LLaMA with Block Expansion, Chengyue Wu+, N/A, arXiv'24 HOT 1
- Large Language Models Are State-of-the-Art Evaluators of Translation Quality, EAMT'23 HOT 1
- Experts, errors, and context: A large-scale study of human evaluation for machine translation, TACL'21 HOT 1
- BLEU might be Guilty but References are not Innocent, EMNLP'20 HOT 1
- G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment, Yang Liu+, N/A, arXiv'23 HOT 1
- INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback, Wenda Xu+, N/A, arXiv'23 HOT 2
- MM-LLMs: Recent Advances in MultiModal Large Language Models, Duzhen Zhang+, N/A, arXiv'24
- RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval, Parth Sarthi+, N/A, arXiv'24
- Self-Discover: Large Language Models Self-Compose Reasoning Structures, Pei Zhou+, N/A, arXiv'24
- Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks, Jongho Park+, N/A, arXiv'24
- RAGの性能を改善するための8つの戦略 HOT 1
- Scaling Laws for Fine-Grained Mixture of Experts, Jakub Krajewski+, N/A, arXiv'24
- The Consensus Game: Language Model Generation via Equilibrium Search, Athul Paul Jacob+, N/A, arXiv'23
- Dense Text Retrieval based on Pretrained Language Models: A Survey, Wayne Xin Zhao+, N/A, arXiv'22
- awesome-generative-information-retrieval
- Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance, Ziqi Yin+, N/A, arXiv'24
- User-LLM: Efficient LLM Contextualization with User Embeddings, Lin Ning+, N/A, arXiv'24 HOT 1
- Linear Transformers are Versatile In-Context Learners, Max Vladymyrov+, N/A, arXiv'24
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from paper_notes.