# IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions

arXiv: https://arxiv.org/abs/2311.18397 · HTML: https://mlsanity.com/paper/2311.18397/

## Key facts

- Cited by 15 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 10 of its 29 references that are in the map.
- First posted on arXiv 30 Nov 2023.

## 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, 10 of 10)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [UL2: Unifying Language Learning Paradigms](https://mlsanity.com/paper/2205.05131/) (2022)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [LAMBADA: Backward Chaining for Automated Reasoning in Natural Language](https://mlsanity.com/paper/2212.13894/) (2022)
- [Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering](https://mlsanity.com/paper/2210.03078/) (2022)

## Built on by (most cited first, 15 of 15)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs](https://mlsanity.com/paper/2507.09477/) (2025)
- [SurveyX: Academic Survey Automation via Large Language Models](https://mlsanity.com/paper/2502.14776/) (2025)
- [ConfusedPilot: Confused Deputy Risks in RAG-based LLMs](https://mlsanity.com/paper/2408.04870/) (2024)
- [RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking](https://mlsanity.com/paper/2504.01346/) (2025)
- [BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain](https://mlsanity.com/paper/2409.20075/) (2024)
- [Training Task Experts through Retrieval Based Distillation](https://mlsanity.com/paper/2407.05463/) (2024)
- [A Hierarchical Tree-based approach for creating Configurable and Static Deep Research Agent (Static-DRA)](https://mlsanity.com/paper/2512.03887/) (2025)
- [KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2603.11501/) (2026)
- [SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs](https://mlsanity.com/paper/2504.12633/) (2025)
- [WindVE: Collaborative CPU-NPU Vector Embedding](https://mlsanity.com/paper/2504.14941/) (2025)
- [Chain of Methodologies: Scaling Test Time Computation without Training](https://mlsanity.com/paper/2506.06982/) (2025)
- [PAGE: Prompt Augmentation for text Generation Enhancement](https://mlsanity.com/paper/2510.13880/) (2025)
- [SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems](https://mlsanity.com/paper/2512.12938/) (2025)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG), by incorporating external knowledge with parametric memory of language models, has become the state-of-the-art architecture for open-domain QA tasks. However, common knowledge bases are inherently constrained by limited coverage and noisy information, making retrieval-based approaches inadequate to answer implicit reasoning questions. In this paper, we propose an Induction-Augmented Generation (IAG) framework that utilizes inductive knowledge along with the retrieved documents for implicit reasoning. We leverage large language models (LLMs) for deriving such knowledge via a novel prompting method based on inductive reasoning patterns. On top of this, we implement two versions of IAG named IAG-GPT and IAG-Student, respectively. IAG-GPT directly utilizes the knowledge generated by GPT-3 for answer prediction, while IAG-Student gets rid of dependencies on GPT service at inference time by incorporating a student inductor model. The inductor is firstly trained via knowledge distillation and further optimized by back-propagating the generator feedback via differentiable beam scores. Experimental results show that IAG outperforms RAG baselines as well as ChatGPT on two Open-Domain QA tasks. Notably, our best models have won the first place in the official leaderboards of CSQA2.0 (since Nov 1, 2022) and StrategyQA (since Jan 8, 2023).