# Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables

arXiv: https://arxiv.org/abs/2502.09073 · HTML: https://mlsanity.com/paper/2502.09073/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 33 of its 63 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- Retrieval-augmented generation / [Conversational and speech RAG](https://mlsanity.com/rag/conversational-and-speech-rag/)

## Builds on (most cited first, 30 of 33)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1910.02923/) (2019)
- [Contextual Diversity for Active Learning](https://mlsanity.com/paper/2008.05723/) (2020)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [Influence Selection for Active Learning](https://mlsanity.com/paper/2108.09331/) (2021)
- [LLMaAA: Making Large Language Models as Active Annotators](https://mlsanity.com/paper/2310.19596/) (2023)
- [Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering](https://mlsanity.com/paper/2107.02331/) (2021)
- [Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers](https://mlsanity.com/paper/2107.05687/) (2021)
- [Active Learning Principles for In-Context Learning with Large Language Models](https://mlsanity.com/paper/2305.14264/) (2023)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models](https://mlsanity.com/paper/2402.10038/) (2024)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers](https://mlsanity.com/paper/2006.08344/) (2020)
- [Generative AI Text Classification using Ensemble LLM Approaches](https://mlsanity.com/paper/2309.07755/) (2023)
- [Batch Multi-Fidelity Active Learning with Budget Constraints](https://mlsanity.com/paper/2210.12704/) (2022)
- [Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation](https://mlsanity.com/paper/2406.12114/) (2024)
- [Active Learning for Sound Event Detection](https://mlsanity.com/paper/2002.05033/) (2020)
- [FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models](https://mlsanity.com/paper/2311.15614/) (2023)
- [Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue](https://mlsanity.com/paper/2105.10155/) (2021)
- [Dialog Policy Learning for Joint Clarification and Active Learning Queries](https://mlsanity.com/paper/2006.05456/) (2020)
- [Active Learning for Abstractive Text Summarization](https://mlsanity.com/paper/2301.03252/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Survey of the State-of-the-Art in Conversational Question Answering Systems](https://mlsanity.com/paper/2509.05716/) (2025)
- [AI-Driven Climate Policy Scenario Generation for Sub-Saharan Africa](https://mlsanity.com/paper/2505.18694/) (2025)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) is a key technique for leveraging external knowledge and reducing hallucinations in large language models (LLMs). However, RAG still struggles to fully prevent hallucinated responses. To address this, it is essential to identify samples prone to hallucination or guide LLMs toward correct responses, which experts then annotate to develop high-quality datasets for refining LLMs. However, the growing scarcity of such datasets makes their creation challenging. This paper proposes using the vast amount of conversations from widespread LLM usage to build these datasets, training LLMs to avoid hallucination-prone questions while accurately responding to manageable ones. Given the impracticality of expert-annotating all conversation records, the paper introduces AL4RAG, which uses active learning to select the most suitable conversation samples for annotation, optimizing performance within an annotation budget. Additionally, recognizing that traditional active learning methods are not fully compatible with RAG due to unsuitable distance metrics, we develop a novel sample distance measurement for RAG active learning. Extensive experiments show that our method consistently outperforms baselines across multiple metrics.