arXiv Machine Learning
Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 18
When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
arXiv:2608. 16515v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved context may be useful, irrelevant, or even misleading.
arXiv Machine Learning
Jun 2
Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG
arXiv:2606. 00432v1 Announce Type: new Abstract: As retrieval-augmented generation (RAG) systems scale, it becomes increasingly challenging to ensure faithful grounding in external evidence.
arXiv AI
Jun 15
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
arXiv:2505. 23277v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) often suffers from long and noisy retrieved contexts.
arXiv Computation and Language
2d ago
A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation
The paper proposes a new method for training large language models to handle long-context reasoning by combining Group Relative Policy Optimization (GRPO) with on‑policy distillation (OPD). It introduces a synthetic multilingual dataset called LongBlocks that tests multi‑hop reasoning, contextual grounding, and long‑form generation. Experiments show that the combined approach outperforms either GRPO or OPD alone while maintaining short‑context performance.
arXiv Computation and Language
Sep 1
Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems
arXiv:2608.30426v1 Announce Type: new Abstract: Current dialogue systems struggle with dynamic information retrieval, often leading to hallucinations and lower response accuracy. We address this by a...
arXiv AI
Jul 3
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
arXiv:2604. 02091v2 Announce Type: replace-cross Abstract: Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation.