| Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation | May 22, 2025 | HallucinationImage Captioning | —Unverified | 0 |
| Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks | May 22, 2025 | HallucinationRAG | CodeCode Available | 0 |
| Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems | May 22, 2025 | Adversarial AttackHallucination | —Unverified | 0 |
| KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance | May 21, 2025 | HallucinationQuestion Answering | —Unverified | 0 |
| Multilingual Prompting for Improving LLM Generation Diversity | May 21, 2025 | DiversityHallucination | —Unverified | 0 |
| Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization | May 21, 2025 | Document SummarizationHallucination | —Unverified | 0 |
| HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving | May 21, 2025 | Autonomous DrivingHallucination | —Unverified | 0 |
| RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection | May 21, 2025 | HallucinationText Generation | —Unverified | 0 |
| NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction | May 21, 2025 | BenchmarkingHallucination | —Unverified | 0 |
| Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data Augmentation | May 21, 2025 | Data AugmentationDiversity | —Unverified | 0 |