Adaptive Retrieval-Augmented Generation for Conversational Systems
- URL: http://arxiv.org/abs/2407.21712v1
- Date: Wed, 31 Jul 2024 16:04:03 GMT
- Title: Adaptive Retrieval-Augmented Generation for Conversational Systems
- Authors: Xi Wang, Procheta Sen, Ruizhe Li, Emine Yilmaz,
- Abstract summary: This study investigates the need for each turn of system response to be augmented with external knowledge.
By leveraging human judgements on the binary choice of adaptive augmentation, we develop RAGate, a gating model.
- Score: 25.35137570524043
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Despite the success of integrating large language models into the development of conversational systems, many studies have shown the effectiveness of retrieving and augmenting external knowledge for informative responses. Hence, many existing studies commonly assume the always need for Retrieval Augmented Generation (RAG) in a conversational system without explicit control. This raises a research question about such a necessity. In this study, we propose to investigate the need for each turn of system response to be augmented with external knowledge. In particular, by leveraging human judgements on the binary choice of adaptive augmentation, we develop RAGate, a gating model, which models conversation context and relevant inputs to predict if a conversational system requires RAG for improved responses. We conduct extensive experiments on devising and applying RAGate to conversational models and well-rounded analyses of different conversational scenarios. Our experimental results and analysis indicate the effective application of RAGate in RAG-based conversational systems in identifying system responses for appropriate RAG with high-quality responses and a high generation confidence. This study also identifies the correlation between the generation's confidence level and the relevance of the augmented knowledge.
Related papers
- Enhancing Retrieval-Augmented Generation: A Study of Best Practices [16.246719783032436]
We develop advanced RAG system designs that incorporate query expansion, various novel retrieval strategies, and a novel Contrastive In-Context Learning RAG.
Our study systematically investigates key factors, including language model size, prompt design, document chunk size, knowledge base size, retrieval stride, query expansion techniques, and Focus Mode retrieving relevant context at sentence-level.
Our findings offer actionable insights for developing RAG systems, striking a balance between contextual richness and retrieval-generation efficiency.
arXiv Detail & Related papers (2025-01-13T15:07:55Z) - Unanswerability Evaluation for Retrieval Augmented Generation [74.3022365715597]
UAEval4RAG is a framework designed to evaluate whether RAG systems can handle unanswerable queries effectively.
We define a taxonomy with six unanswerable categories, and UAEval4RAG automatically synthesizes diverse and challenging queries.
arXiv Detail & Related papers (2024-12-16T19:11:55Z) - CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation [68.81271028921647]
We introduce CORAL, a benchmark designed to assess RAG systems in realistic multi-turn conversational settings.
CORAL includes diverse information-seeking conversations automatically derived from Wikipedia.
It supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling.
arXiv Detail & Related papers (2024-10-30T15:06:32Z) - Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning [49.3242278912771]
We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning)
The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs.
It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
arXiv Detail & Related papers (2024-05-31T14:23:49Z) - Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check [25.63538452425097]
We propose a conversation-level RAG approach, which incorporates fine-grained retrieval augmentation and self-check for conversational question answering.
In particular, our approach consists of three components, namely conversational question refiner, fine-grained retriever and self-check based response generator.
arXiv Detail & Related papers (2024-03-27T04:20:18Z) - UniRQR: A Unified Model for Retrieval Decision, Query, and Response
Generation in Internet-Based Knowledge Dialogue Systems [8.724141214921314]
Knowledge-based dialogue systems with internet retrieval can be typically segmented into three tasks: Retrieval Decision, Query Generation, and Response Generation.
Our work addresses this oversight by employing a single unified model facilitated by prompt and multi-task learning approaches.
By integrating these functions, our system leverages the full potential of pre-trained models and reduces the complexity and costs associated with deploying multiple models.
arXiv Detail & Related papers (2024-01-11T06:09:15Z) - PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded
Dialogue Systems [59.1250765143521]
Current knowledge-grounded dialogue systems often fail to align the generated responses with human-preferred qualities.
We propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework.
We demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history.
arXiv Detail & Related papers (2023-09-19T08:27:09Z) - Large Language Models for Information Retrieval: A Survey [58.30439850203101]
Information retrieval has evolved from term-based methods to its integration with advanced neural models.
Recent research has sought to leverage large language models (LLMs) to improve IR systems.
We delve into the confluence of LLMs and IR systems, including crucial aspects such as query rewriters, retrievers, rerankers, and readers.
arXiv Detail & Related papers (2023-08-14T12:47:22Z) - Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term
Importance Estimation and Neural Query Rewriting [56.268862325167575]
We tackle conversational passage retrieval (ConvPR) with query reformulation integrated into a multi-stage ad-hoc IR system.
We propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting.
For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals.
For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model.
arXiv Detail & Related papers (2020-05-05T14:30:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.