Generate rather than Retrieve: Large Language Models are Strong Context Generators

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Very close Not relevant

   Generator-Retriever-Generator Approach for Open-Domain Question Answering

   Abdelrahman Abdallah, A. Jatowt · 2023 · cited 13 times · Not summarized yet

   Abstract

   Open-domain question answering (QA) tasks usually require the retrieval of relevant information from a large corpus to generate accurate answers. We propose a novel approach called Generator-Retriever-Generator (GRG) that combines document retrieval techniques with a large language model (LLM), by first prompting the model to generate contextual documents based on a given question. In parallel, a dual-encoder network retrieves documents that are relevant to the question from an external corpus. The generated and retrieved documents are then passed to the second LLM, which generates the final answer. By combining document retrieval and LLM generation, our approach addresses the challenges of …

2. Very close Cites this paper Uses this paper in depth Not relevant

   To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering

   Giacomo Frisoni, Alessio Cocchieri, Alex Presepi et al. · 2024 · Annual Meeting of the Association for Computational Linguistics · cited 36 times · Not summarized yet

   Abstract

   Medical open-domain question answering demands substantial access to specialized knowledge. Recent efforts have sought to decouple knowledge from model parameters, counteracting architectural scaling and allowing for training on common low-resource hardware. The retrieve-then-read paradigm has become ubiquitous, with model predictions grounded on relevant knowledge pieces from external repositories such as PubMed, textbooks, and UMLS. An alternative path, still under-explored but made possible by the advent of domain-specific large language models, entails constructing artificial contexts through prompting. As a result,"to generate or to retrieve"is the modern equivalent of Hamlet's dilemma.…

3. Very close Not relevant

   Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy

   Zhihong Shao, Yeyun Gong, Ye-Long Shen et al. · 2023 · Conference on Empirical Methods in Natural Language Processing · cited 626 times · Not summarized yet

   Abstract

   Large language models are powerful text processors and reasoners, but are still subject to limitations including outdated knowledge and hallucinations, which necessitates connecting them to the world. Retrieval-augmented large language models have raised extensive attention for grounding model generation on external knowledge. However, retrievers struggle to capture relevance, especially for queries with complex information needs. Recent work has proposed to improve relevance modeling by having large language models actively involved in retrieval, i.e., to improve retrieval with generation. In this paper, we show that strong performance can be achieved by a method we call Iter-RetGen, which …

4. Very close Cites this paper Uses this paper in depth Not relevant

   From Retrieval to Generation: Comparing Different Approaches

   Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani et al. · 2025 · arXiv.org · preprint, not peer reviewed · cited 6 times · Not summarized yet

   Abstract

   Knowledge-intensive tasks, particularly open-domain question answering (ODQA), document reranking, and retrieval-augmented language modeling, require a balance between retrieval accuracy and generative flexibility. Traditional retrieval models such as BM25 and Dense Passage Retrieval (DPR), efficiently retrieve from large corpora but often lack semantic depth. Generative models like GPT-4-o provide richer contextual understanding but face challenges in maintaining factual consistency. In this work, we conduct a systematic evaluation of retrieval-based, generation-based, and hybrid models, with a primary focus on their performance in ODQA and related retrieval-augmented tasks. Our results sho…

5. Very close Cites this paper Not relevant

   Retrieval-Generation Synergy Augmented Large Language Models

   Zhangyin Feng, Xiaocheng Feng, Dezhi Zhao et al. · 2024 · IEEE International Conference on Acoustics Speech and Signal Processing · cited 50 times · Not summarized yet

   Abstract

   Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two categories. One is to retrieve from an external knowledge base, and the other is to utilize large language models to generate documents. We propose an iterative retrieval-generation collaborative framework. It is not only able to leverage both parametric and non-parametric knowledge, but also helps to find the correct reasoning path through retrieval-generation interactions, which is very important for tasks that require multi-step reasoning. We conduct experim…

6. Very close Cites this paper Uses this paper in depth Not relevant

   Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering

   Zhengliang Shi, Shuo Zhang, Weiwei Sun et al. · 2024 · Annual Meeting of the Association for Computational Linguistics · cited 100 times · Not summarized yet

   Abstract

   Multi-Hop Question Answering (MHQA) tasks present a significant challenge for large language models (LLMs) due to the intensive knowledge required. Current solutions, like Retrieval-Augmented Generation, typically retrieve potential documents from an external corpus to read an answer. However, the performance of this retrieve-then-read paradigm is constrained by the retriever and the inevitable noise in the retrieved documents. To mitigate these challenges, we introduce a novel generate-then-ground (GenGround) framework, synergizing the parametric knowledge of LLMs and external documents to solve a multi-hop question. GenGround empowers LLMs to alternate two phases until the final answer is …

7. Very close Not relevant

   Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation on Large Language Models

   Ting-Jia Shen, Hao Wang, Chuan Qin et al. · 2025 · Big Data Mining and Analytics · cited 2 times · Not summarized yet

   Abstract

   Open-domain question answering (OpenQA) represents a cornerstone in natural language processing (NLP), primarily focused on extracting answers from unstructured textual data. With the rapid advancements in Large Language Models (LLMs), LLM-based OpenQA methods have reaped the benefits of emergent understanding and answering capabilities enabled by massive parameters compared to traditional methods. However, most of these methods encounter two critical challenges: how to integrate knowledge into LLMs effectively and how to adaptively generate results with specific answer formats for various task situations. To address these challenges, we propose a novel framework named GenKI, which aims to i…

8. Very close Cites this paper Not relevant

   Assessing “Implicit” Retrieval Robustness of Large Language Models

   Xiaoyu Shen, Rexhina Blloshmi, Da-Wei Zhu et al. · 2024 · Conference on Empirical Methods in Natural Language Processing · cited 9 times · Not summarized yet

   Abstract

   Retrieval-augmented generation has gained popularity as a framework to enhance large language models with external knowledge. However, its effectiveness hinges on the retrieval robustness of the model. If the model lacks retrieval robustness, its performance is constrained by the accuracy of the retriever, resulting in significant compromises when the retrieved context is irrelevant. In this paper, we evaluate the “implicit” retrieval robustness of various large language models, instructing them to directly output the final answer without explicitly judging the relevance of the retrieved context. Our findings reveal that fine-tuning on a mix of gold and distracting context significantly enha…

Prior work it builds on

1. Close Used in depth by this paper Not relevant

   Generated Knowledge Prompting for Commonsense Reasoning

   Jiacheng Liu, Alisa Liu, Ximing Lu et al. · 2021 · Computation and Language · cited 433 times · AI summary available

   Abstract

   Despite their ability to capture large amount of knowledge during pretraining, large-scale language models often benefit from incorporating external knowledge bases, especially on commonsense reasoning tasks. This motivates us to explore how we can best leverage knowledge elicited from language models themselves. We propose generating knowledge statements directly from a language model with a generic prompt format, then selecting the knowledge which maximizes prediction probability. Despite its simplicity, this approach improves performance of both off-the-shelf and finetuned language models on four commonsense reasoning tasks, improving the state-of-the-art on numerical commonsense (NumerSe…

2. Close Used in depth by this paper A method it uses Not relevant

   Few-shot Learning with Retrieval Augmented Language Models

   Gautier Izacard, Patrick Lewis, M. Lomeli et al. · 2022 · Journal of machine learning research · cited 1,478 times · AI summary available

   Abstract

   Large language models have shown impressive few-shot results on a wide range of tasks. However, when knowledge is key for such results, as is the case for tasks such as question answering and fact checking, massive parameter counts to store knowledge seem to be needed. Retrieval augmented models are known to excel at knowledge intensive tasks without the need for as many parameters, but it is unclear whether they work in few-shot settings. In this work we present Atlas, a carefully designed and pre-trained retrieval augmented language model able to learn knowledge intensive tasks with very few training examples. We perform evaluations on a wide range of tasks, including MMLU, KILT and Natura…

3. Close Used in depth by this paper A method it uses Not relevant

   Dense Passage Retrieval for Open-Domain Question Answering

   Vladimir Karpukhin, Barlas Oğuz, Sewon Min et al. · 2020 · Conference on Empirical Methods in Natural Language Processing · cited 7,804 times · AI summary available

   Abstract

   Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchm…

4. Close Not relevant

   Generation-Augmented Retrieval for Open-Domain Question Answering

   Yuning Mao, Peng-Cheng He, Xiao-Dong Liu et al. · 2020 · Annual Meeting of the Association for Computational Linguistics · cited 335 times · Not summarized yet

   Abstract

   We propose Generation-Augmented Retrieval (GAR) for answering open-domain questions, which augments a query through text generation of heuristically discovered relevant contexts without external resources as supervision. We demonstrate that the generated contexts substantially enrich the semantics of the queries and GAR with sparse representations (BM25) achieves comparable or better performance than state-of-the-art dense retrieval methods such as DPR. We show that generating diverse contexts for a query is beneficial as fusing their results consistently yields better retrieval accuracy. Moreover, as sparse and dense representations are often complementary, GAR can be easily combined with D…

5. Close Not relevant

   UnitedQA: A Hybrid Approach for Open Domain Question Answering

   Hao Cheng, Ye-Long Shen, Xiao-Dong Liu et al. · 2021 · Annual Meeting of the Association for Computational Linguistics · cited 67 times · Not summarized yet

   Abstract

   To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively. In this paper, we study a hybrid approach for leveraging the strengths of both models. We apply novel techniques to enhance both extractive and generative readers built upon recent pretrained neural language models, and find that proper training methods can provide large improvement over previous state-of-the-art models. We demonstrate that a simple hybrid approach by combining answers from both readers can efficiently take advantages of extractive and generative answer inference strategies and outperforms single models as well as homogeneous ens…

Papers that cite it

1. Close Uses this paper in depth Not relevant

   A Survey on Retrieval-Augmented Text Generation for Large Language Models

   Yi-Zheng Huang, J. Huang · 2024 · ACM Computing Surveys · cited 212 times · Not summarized yet

   Abstract

   Retrieval-Augmented Generation (RAG) merges information retrieval (IR) techniques with deep learning advancements to address the static limitations of large language models (LLMs) by enabling the dynamic integration of up-to-date external information. This methodology, focusing primarily on the text domain, provides a cost-effective solution to the generation of plausible but possibly incorrect responses by LLMs, thereby enhancing the accuracy and reliability of their outputs through the use of real-world data. As RAG grows in complexity and incorporates multiple concepts that can influence its performance, this article organizes the RAG paradigm into four categories: pre-retrieval, retrieva…

2. Close Uses this paper in depth Not relevant

   Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering

   Huanxuan Liao, Shi-Zhu He, Yao Xu et al. · 2024 · International Conference on Computational Linguistics · cited 12 times · Not summarized yet

   Abstract

   Retrieval-Augmented-Generation and Generation-Augmented-Generation have been proposed to enhance the knowledge required for question answering with Large Language Models (LLMs) by leveraging richer context. However, the former relies on external resources, and both require incorporating explicit documents into the context, which increases execution costs and susceptibility to noise data during inference. Recent works indicate that LLMs model rich knowledge, but it is often not effectively activated and awakened. Inspired by this, we propose a novel knowledge-augmented framework, $\textbf{Awakening-Augmented-Generation}$ (AAG), which mimics the human ability to answer questions using only thi…

3. Close Uses this paper in depth Not relevant

   Retrieve What You Need: A Mutual Learning Framework for Open-domain Question Answering

   Dingmin Wang, Qiuyuan Huang, Matthew Jackson et al. · 2024 · Transactions of the Association for Computational Linguistics · cited 17 times · Not summarized yet

   Abstract

   An open-domain question answering (QA) system usually follows a retrieve-then-read paradigm, in which a retriever is used to retrieve relevant passages from a large corpus, and then a reader generates answers based on the retrieved passages and the original question. In this paper, we propose a simple and novel mutual learning framework to improve the performance of retrieve-then-read-style models via an intermediate module named the knowledge selector, which we train with reinforcement learning. The key benefits of our proposed intermediate module are: 1) no requirement for additional annotated question-passage pairs; 2) improvements in both retrieval and QA performance, as well as computat…

4. Close Uses this paper in depth Not relevant

   Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models

   Fei Wang, Xingchen Wan, Ruoxi Sun et al. · 2024 · Computation and Language · cited 93 times · AI summary available

   Abstract

   Retrieval-Augmented Generation (RAG), while effective in integrating external knowledge to address the limitations of large language models (LLMs), can be undermined by imperfect retrieval, which may introduce irrelevant, misleading, or even malicious information. Despite its importance, previous studies have rarely explored the behavior of RAG through joint analysis on how errors from imperfect retrieval attribute and propagate, and how potential conflicts arise between the LLMs' internal knowledge and external sources. We find that imperfect retrieval augmentation might be inevitable and quite harmful, through controlled analysis under realistic conditions. We identify the knowledge confli…

5. Close Uses this paper in depth Not relevant

   A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential

   Wei Tang, Yi-Xin Cao, Jia-Hao Ying et al. · 2024 · Annual Meeting of the Association for Computational Linguistics · cited 6 times · Not summarized yet

   Abstract

   Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models (LLMs). Targeting its bottleneck of retriever performance,"generate-then-read"pipeline is proposed to replace the retrieval stage with generation from the LLM itself. Although promising, this research direction is underexplored and still cannot work in the scenario when source knowledge is given. In this paper, we formalize a general"A + B"framework with varying combinations of foundation models and types for systematic investigation. We explore the efficacy of the base and chat versions of LLMs and found their different functionalities suitable for generator A and reader …