CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control

ACL ARR 2025 February Submission1969 Authors

Abstract: Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive RAG enhances this approach by enabling dynamic retrieval during generation, activating retrieval only when the query exceeds LLM's internal knowledge. Existing methods primarily focus on detecting LLM's confidence via statistical uncertainty. Instead, we present the first attempts to solve adaptive RAG from a representation perspective and develop an inherent control-based framework, termed CtrlA. Specifically, we extract the features that represent the honesty and confidence directions of LLM and adopt them to control LLM behavior and guide retrieval timing decisions. We also design a simple yet effective query formulation strategy to support adaptive retrieval. Experiments show that CtrlA is superior to existing adaptive RAG methods on a diverse set of tasks. Honesty steering can effectively make LLMs more honest and confidence monitoring is a promising indicator of retrieval trigger.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: Retrieval-Augmented Generation, Large Language Model

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 1969