Retrieval-Augmented Generation
Grounding language models in retrieved, non-parametric memory; retrieve-then-generate systems.
A topic in the Science corpus, drawn from 180 papers.
Trusted voices in Retrieval-Augmented Generation
Ordered by the trust Retrieval-Augmented Generation's own network concentrates on each researcher, most first.
- Jason Aaron Edward Weston — trusted by 141 researchers here
- Sumit Chopra — trusted by 133 researchers here
- Antoine Bordes — trusted by 133 researchers here
- Gautier Izacard — trusted by 120 researchers here
- Edouard Grave — trusted by 120 researchers here
- Patrick Lewis — trusted by 73 researchers here
- Wen-tau Yih — trusted by 61 researchers here
- Vladimir Karpukhin — trusted by 53 researchers here
- Panupong Pasupat — trusted by 51 researchers here
- Kelvin Guu — trusted by 51 researchers here
- Ming-Wei Chang — trusted by 48 researchers here
- Zora Tung — trusted by 43 researchers here
Most-cited papers in Retrieval-Augmented Generation
Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020, Neural Information Processing Systems) — 16,110 citations
- Dense Passage Retrieval for Open-Domain Question Answering (2020, Conference on Empirical Methods in Natural Language Processing) — 6,334 citations
- Retrieval-Augmented Generation for Large Language Models: A Survey (2023) — 3,697 citations
- REALM: Retrieval-Augmented Language Model Pre-Training (2020, International Conference on Machine Learning) — 3,207 citations
- WebGPT: Browser-assisted question-answering with human feedback (2021) — 1,953 citations
- Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering (2020, Conference of the European Chapter of the Association for Computational Linguistics) — 1,909 citations
- Memory Networks (2014) — 1,867 citations
- Improving language models by retrieving from trillions of tokens (2021) — 1,785 citations
- When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories (2022) — 1,304 citations
- Few-shot Learning with Retrieval Augmented Language Models (2022, Journal of machine learning research) — 1,295 citations
- Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions (2022) — 1,143 citations
- Retrieval Augmentation Reduces Hallucination in Conversation (2021) — 1,126 citations
- REPLUG: Retrieval-Augmented Black-Box Language Models (2023) — 1,051 citations
- KILT: a Benchmark for Knowledge Intensive Language Tasks (2020) — 820 citations
- A Knowledge-Grounded Neural Conversation Model (2017) — 591 citations
- Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback (2023) — 530 citations
- RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation (2023) — 516 citations
- LeanDojo: Theorem Proving with Retrieval-Augmented Language Models (2023) — 514 citations
- PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text (2019) — 464 citations
- Transformer Memory as a Differentiable Search Index (2022) — 444 citations
- Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation (2018) — 436 citations
- Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning (2020) — 410 citations
- Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval (2021) — 395 citations
- Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge from External Sources (2015) — 392 citations
- TAPEX: Table Pre-training via Learning a Neural SQL Executor (2021) — 368 citations
- Generation-Augmented Retrieval for Open-Domain Question Answering (2020) — 323 citations
- Condenser: a Pre-training Architecture for Dense Retrieval (2021) — 308 citations
- MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (2024) — 304 citations
- Evaluation of Retrieval-Augmented Generation: A Survey (2024) — 292 citations
- Re-Imagen: Retrieval-Augmented Text-to-Image Generator (2022) — 260 citations
- Fine-grained Fact Verification with Kernel Graph Attention Network (2019) — 254 citations
- Explaining Answers with Entailment Trees (2021) — 232 citations
- Rethinking with Retrieval: Faithful Large Language Model Inference (2022) — 217 citations
- R3: Reinforced Ranker-Reader for Open-Domain Question Answering (2018) — 200 citations
- End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering (2021) — 192 citations
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue (2020) — 181 citations
- Reveal: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory (2022) — 178 citations
- Entities as Experts: Sparse Memory Access with Entity Supervision (2020) — 177 citations
- Internet-augmented language models through few-shot prompting for open-domain question answering (2022) — 177 citations
- Harvesting Paragraph-level Question-Answer Pairs from Wikipedia (2018) — 174 citations
- Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering (2019) — 173 citations
- Retrieval-Augmented Multimodal Language Modeling (2023) — 166 citations
- Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation (2024) — 165 citations
- Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (2019) — 152 citations
- Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion (2022) — 150 citations
- Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions (2016) — 148 citations
- Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks (2017) — 144 citations
- Retrieval-based Language Models and Applications (2023) — 142 citations
- Retrieval Augmented Visual Question Answering with Outside Knowledge (2022) — 137 citations
- Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading (2019) — 111 citations
Most active researchers
By papers in this topic: a volume measure, not trust.
- Wen-tau Yih — 5 papers
- Patrick Lewis — 4 papers
- Jianfeng Gao — 4 papers
- Akari Asai — 4 papers
- Rajarshi Das — 3 papers
- Jamie Callan — 3 papers
- Jason Aaron Edward Weston — 3 papers
- Michihiro Yasunaga — 3 papers
- Michel Galley — 3 papers
- Weizhu Chen — 3 papers
- Mostafa Dehghani — 3 papers
- Michael Lewis — 3 papers