SOTAVerified

Hallucination

Papers

Showing 5175 of 1816 papers

TitleStatusHype
Retrieval Head Mechanistically Explains Long-Context FactualityCode3
View Selection for 3D Captioning via Diffusion RankingCode3
Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language ModelsCode3
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon GenerationCode3
KnowAgent: Knowledge-Augmented Planning for LLM-Based AgentsCode3
EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language ModelsCode3
LLMDFA: Analyzing Dataflow in Code with Large Language ModelsCode3
PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language ModelsCode3
ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and RefinementCode3
PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language ModelsCode3
When Large Language Models Meet Vector Databases: A SurveyCode3
Evaluating Hallucinations in Chinese Large Language ModelsCode3
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language ModelsCode3
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on WikipediaCode3
Towards An End-to-End Framework for Flow-Guided Video InpaintingCode3
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative ModelsCode3
DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph RefinementCode2
FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning EvaluationCode2
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System CollaborationCode2
DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual UnderstandingCode2
Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective ResamplingCode2
Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge EnhancementCode2
RARE: Retrieval-Augmented Reasoning ModelingCode2
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language ModelsCode2
WMNav: Integrating Vision-Language Models into World Models for Object Goal NavigationCode2
Show:102550
← PrevPage 3 of 73Next →

No leaderboard results yet.