Semantic Tokens in Retrieval Augmented Generation
Joel Suro

TL;DR
This paper introduces a Comparative RAG system with an evaluator module that improves the reliability and accuracy of retrieval-augmented generation by ensuring retrieved data is semantically relevant and logically consistent.
Contribution
The work presents a novel evaluator module for RAG systems that enhances response reliability by comparing external recommendations with retrieved document chunks.
Findings
Improved accuracy and reliability in RAG outputs.
Enhanced semantic relevance and logical consistency.
Potential for scalable, high-precision question-answering.
Abstract
Retrieval-Augmented Generation (RAG) architectures have recently garnered significant attention for their ability to improve truth grounding and coherence in natural language processing tasks. However, the reliability of RAG systems in producing accurate answers diminishes as the volume of data they access increases. Even with smaller datasets, these systems occasionally fail to address simple queries. This issue arises from their dependence on state-of-the-art large language models (LLMs), which can introduce uncertainty into the system's outputs. In this work, I propose a novel Comparative RAG system that introduces an evaluator module to bridge the gap between probabilistic RAG systems and deterministically verifiable responses. The evaluator compares external recommendations with the retrieved document chunks, adding a decision-making layer that enhances the system's reliability.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSemantic Web and Ontologies
MethodsAttention Is All You Need · Refunds@Expedia|||How do I get a full refund from Expedia? · Linear Layer · Softmax · Linear Warmup With Linear Decay · Multi-Head Attention · Byte Pair Encoding · WordPiece · Dropout · Dense Connections
