# Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2412.08519 · HTML: https://mlsanity.com/paper/2412.08519/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Query Rewriting for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2305.14283/) (2023)
- [FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research](https://mlsanity.com/paper/2405.13576/) (2024)
- [NV-Retriever: Improving text embedding models with effective hard-negative mining](https://mlsanity.com/paper/2407.15831/) (2024)
- [Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In](https://mlsanity.com/paper/2305.17331/) (2023)
- [Bridging the Preference Gap between Retrievers and LLMs](https://mlsanity.com/paper/2401.06954/) (2024)
- [Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.18676/) (2024)
- [Large Language Model Distilling Medication Recommendation Model](https://mlsanity.com/paper/2402.02803/) (2024)
- [A Survey on Human Preference Learning for Large Language Models](https://mlsanity.com/paper/2406.11191/) (2024)
- [Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models](https://mlsanity.com/paper/2403.01972/) (2024)
- [Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM](https://mlsanity.com/paper/2312.15450/) (2023)
- [Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG](https://mlsanity.com/paper/2409.07691/) (2024)
- [ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling](https://mlsanity.com/paper/2402.13542/) (2024)
- [Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup](https://mlsanity.com/paper/2312.05795/) (2023)

## Built on by (most cited first, 13 of 13)

- [Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning](https://mlsanity.com/paper/2505.14069/) (2025)
- [A Survey of Personalization: From RAG to Agent](https://mlsanity.com/paper/2504.10147/) (2025)
- [Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains](https://mlsanity.com/paper/2505.16014/) (2025)
- [MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search](https://mlsanity.com/paper/2604.17265/) (2026)
- [TAPO: Task-Referenced Adaptation for Prompt Optimization](https://mlsanity.com/paper/2501.06689/) (2025)
- [HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores](https://mlsanity.com/paper/2509.21336/) (2025)
- [The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models](https://mlsanity.com/paper/2512.16236/) (2025)
- [ZeroED: Hybrid Zero-shot Error Detection through Large Language Model Reasoning](https://mlsanity.com/paper/2504.05345/) (2025)
- [TabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representations](https://mlsanity.com/paper/2511.06582/) (2025)
- [Knowledge Distillation Must Account for What It Loses](https://mlsanity.com/paper/2604.25110/) (2026)
- [Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking](https://mlsanity.com/paper/2509.06472/) (2025)
- [When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval](https://mlsanity.com/paper/2606.01304/) (2026)
- [Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA](https://mlsanity.com/paper/2606.03728/) (2026)

## Abstract (arXiv)

The reranker and generator are two critical components in the Retrieval-Augmented Generation (i.e., RAG) pipeline, responsible for ranking relevant documents and generating responses. However, due to differences in pre-training data and objectives, there is an inevitable gap between the documents ranked as relevant by the reranker and those required by the generator to support answering the query. To address this gap, we propose RADIO, a novel and practical preference alignment framework with RAtionale DIstillatiOn. Specifically, we first propose a rationale extraction method that leverages the reasoning capabilities of Large Language Models (LLMs) to extract the rationales necessary for answering the query. Subsequently, a rationale-based alignment process is designed to rerank the documents based on the extracted rationales, and fine-tune the reranker to align the preferences. We conduct extensive experiments on two tasks across three datasets to demonstrate the effectiveness of our approach compared to baseline methods. Our code is released online to ease reproduction.