SeeGULL Multilingual: A Multilingual Dataset of Stereotypes
다양한 언어 및 지역의 사회적 편견을 반영하는 SeeGULL Multilingual 다국어 스테레오타입 데이터셋을 구축하고 모델 평가에 활용한다.
DPOD: Domain-Specific Prompt Tuning for Multimodal Fake News Detection
다양한 도메인에 대한 도메인별 프롬프트 튜닝을 통한 다중 모달 가짜 뉴스 감지
RED-DOT: Multimodal Fact-Checking with Relevant Evidence Detection
Introducing Relevant Evidence Detection in Multimodal Fact-Checking to improve accuracy and performance.
GraphInstruct: Enhancing Large Language Models with Graph Understanding and Reasoning Capability
Large language models can be empowered with graph understanding and reasoning capabilities through the GraphInstruct benchmark.
Reinforcement Learning in Spatial Resource Allocation: A Comprehensive Survey
Reinforcement learning offers efficient solutions for spatial resource allocation problems by optimizing decision-making processes.
LLP-Bench: A Large Scale Tabular Benchmark for Learning from Label Proportions
LLP-Bench is the first large scale tabular LLP benchmark with diverse datasets, enabling systematic study and design of new LLP techniques.
MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model
MMoFusion proposes a Multi-modal Co-Speech Motion Generation Framework based on a Diffusion Model, ensuring authenticity and diversity in motion generation.
PHAnToM: Personality's Impact on Theory-of-Mind Reasoning in Large Language Models
Personality traits significantly affect ToM reasoning in LLMs, with the Dark Triad showing a larger impact than the Big Five OCEAN traits.
AS-ES Learning: Efficient CoT Learning in Small Models
AS-ES learning maximizes small models' potential in CoT-intensive tasks by segmenting CoT data for iterative generation.
OVEL: Online Video Entity Linking for Live Delivery Scenarios
Proposing the OVEL task for linking entities in online videos, utilizing a memory block managed by a Large Language Model for efficient entity linking.
© 2024 by Linnk AI