Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation
cs.LG
Submitted: 2025-08-04
Updated: 2026-09-06
Comments: updated experiments and presentation
DOI: 10.1007/978-3-032-37673-2_2
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Large Language Models Hallucination: A Comprehensive Survey
- Gemini: A Family of Highly Capable Multimodal Models
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
- The Faiss library
- How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings
- Instruction Induction: From Few Examples to Natural Language Task Descriptions
- From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
- Contrastive Decoding: Open-ended Text Generation as Optimization
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
- TruthfulQA: Measuring How Models Mimic Human Falsehoods
- Cross-Task Generalization via Natural Language Crowdsourcing Instructions
- GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation
- A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Gemma 2: Improving Open Language Models at a Practical Size
- p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Finetuned Language Models Are Zero-Shot Learners
- Qwen3 Technical Report
- Alleviating Hallucinations of Large Language Models through Induced Hallucinations
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks