# Inference Scaling for Bridging Retrieval and Augmented Generation

arXiv: https://arxiv.org/abs/2412.10684 · HTML: https://mlsanity.com/paper/2412.10684/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 14 Dec 2024.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 21 of 21)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [RA-DIT: Retrieval-Augmented Dual Instruction Tuning](https://mlsanity.com/paper/2310.01352/) (2023)
- [Improving Passage Retrieval with Zero-Shot Question Generation](https://mlsanity.com/paper/2204.07496/) (2022)
- [Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization](https://mlsanity.com/paper/2406.16008/) (2024)
- [Bridging the Preference Gap between Retrievers and LLMs](https://mlsanity.com/paper/2401.06954/) (2024)
- [Eliminating Position Bias of Language Models: A Mechanistic Approach](https://mlsanity.com/paper/2407.01100/) (2024)
- [FIRST: Faster Improved Listwise Reranking with Single Token Decoding](https://mlsanity.com/paper/2406.15657/) (2024)
- [Questions Are All You Need to Train a Dense Passage Retriever](https://mlsanity.com/paper/2206.10658/) (2022)
- [Ragnar"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track](https://mlsanity.com/paper/2406.16828/) (2024)
- [Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration](https://mlsanity.com/paper/2305.15262/) (2023)

## Built on by (most cited first, 7 of 7)

- [A Survey of Scaling in Large Language Model Reasoning](https://mlsanity.com/paper/2504.02181/) (2025)
- [Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration](https://mlsanity.com/paper/2604.10150/) (2026)
- [RoToR: Towards More Reliable Responses for Order-Invariant Inputs](https://mlsanity.com/paper/2502.08662/) (2025)
- [Relevance to Utility: Process-Supervised Rewrite for RAG](https://mlsanity.com/paper/2509.15577/) (2025)
- [Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems](https://mlsanity.com/paper/2606.25533/) (2026)
- [The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search](https://mlsanity.com/paper/2608.23252/) (2026)
- [Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG](https://mlsanity.com/paper/2608.26379/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) has emerged as a popular approach to steering the output of a large language model (LLM) by incorporating retrieved contexts as inputs. However, existing work observed the generator bias, such that improving the retrieval results may negatively affect the outcome. In this work, we show such bias can be mitigated, from inference scaling, aggregating inference calls from the permuted order of retrieved contexts. The proposed Mixture-of-Intervention (MOI) explicitly models the debiased utility of each passage with multiple forward passes to construct a new ranking. We also show that MOI can leverage the retriever's prior knowledge to reduce the computational cost by minimizing the number of permutations considered and lowering the cost per LLM call. We showcase the effectiveness of MOI on diverse RAG tasks, improving ROUGE-L on MS MARCO and EM on HotpotQA benchmarks by ~7 points.