mlsanityData to 14 Oct 2026

KGI: An Integrated Framework for Knowledge Intensive Language Tasks

arXiv 2204.03985 ↗First posted 8 Apr 2022cs.CL cs.AI cs.LGcited by 3

On the map: Retrieval-augmented generation → Conversational and speech RAG

Abstract (arXiv)

In this paper, we present a system to showcase the capabilities of the latest state-of-the-art retrieval augmented generation models trained on knowledge-intensive language tasks, such as slot filling, open domain question answering, dialogue, and fact-checking. Moreover, given a user query, we show how the output from these different models can be combined to cross-examine the outputs of each other. Particularly, we show how accuracy in dialogue can be improved using the question answering model. We are also releasing all models used in the demo as a contribution of this paper. A short video demonstrating the system is available at https://ibm.box.com/v/emnlp2022-demo.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 16 references that are in the map. First posted on arXiv 8 Apr 2022.

Builds on

10 of 16 references.

References · 10

  1. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  2. 2017Billion-scale similarity search with GPUscited by 2,497
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  4. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  5. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  6. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  7. 2021The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpuscited by 60
  8. 2021Multi-task Retrieval for Knowledge-Intensive Taskscited by 44
  9. 2021Hindsight: Posterior-guided training of retrievers for improved open-ended generationcited by 38
  10. 2021Robust Retrieval Augmented Generation for Zero-shot Slot Fillingcited by 24

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 1.

3 papers.

  1. 2022A Survey on Knowledge-Enhanced Pre-trained Language Modelscited by 3
  2. 2022Knowledge Graph Induction enabling Recommending and Trend Analysis: A Corporate Research Community Use Casecited by 2
  3. 2024Science Checker Reloaded: A Bidirectional Paradigm for Transparency and Logical Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog
  2. 2022Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling
  3. 2023Retrieval-Generation Synergy Augmented Large Language Models
  4. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
  5. 2024RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering
  6. 2024Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering
  7. 2025Knowledge Graph-extended Retrieval Augmented Generation for Question Answering
  8. 2024E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation