Papers with Code 아카이브
Fact Verification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 40
Fact verification, also called "fact checking", is a process of verifying facts in natural text against a database of facts.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
CFEVER: A Chinese Fact Extraction and VERification Dataset
An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models
Are Large Language Models Table-based Fact-Checkers?
Large Language Model for Table Processing: A Survey
What Makes Medical Claims (Un)Verifiable? Analyzing Entity and Relation Properties for Fact Verification
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
Are Large Language Models Good Fact Checkers: A Preliminary Study
Learning to Filter Context for Retrieval-Augmented Generation
ChartCheck: Explainable Fact-Checking over Real-World Chart Images
An Empirical Study of Using ChatGPT for Fact Verification Task
XFEVER: Exploring Fact Verification across Languages
EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification
Language Models Hallucinate, but May Excel at Fact Verification
QA-NatVer: Question Answering for Natural Logic-based Fact Verification
From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification
KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification
From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Context
Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method
Unsupervised Pretraining for Fact Verification by Language Model Distillation
Investigating Zero- and Few-shot Generalization in Fact Verification
Structural Self-Supervised Objectives for Transformers
Findings of Factify 2: Multimodal Fake News Detection
Heuristic Heterogeneous Graph Reasoning Networks for Fact Verification
Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models
AlignScore: Evaluating Factual Consistency with a Unified Alignment Function
Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy
Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering
FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering
Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification
Growing and Serving Large Open-domain Knowledge Graphs
FactKG: Fact Verification via Reasoning on Knowledge Graphs
Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact Verification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.