Robust Retrieval Augmented Generation for Zero-shot Slot Filling

By Michael R. Glass, Gaetano Rossiello, Md. Faisal Mahbub Chowdhury, Alfio Massimiliano Gliozzo. 2021

38 citations recorded by the source corpus.

Automatically inducing high quality knowledge graphs from a given collection of documents still remains a challenging problem in AI. One way to make headway for this problem is through advancements in a related task known as slot filling. In this task, given an entity query in form of [Entity, Slot, ?], a system is asked to ‘fill’ the slot by generating or extracting the missing value exploiting evidence extracted from relevant passage(s) in the given document collection. The recent works in the field try to solve this task in an end-to-end fashion using retrieval-based language models. In this paper, we present a novel approach to zero-shot slot filling that extends dense passage retrieval with hard negatives and robust training procedures for retrieval augmented generation models. Our model reports large improvements on both T-REx and zsRE slot filling datasets, improving both passage retrieval and slot value generation, and ranking at the top-1 position in the KILT leaderboard. Moreover, we demonstrate the robustness of our system showing its domain adaptation capability on a new variant of the TACRED dataset for slot filling, through a combination of zero/few-shot learning. We release the source code and pre-trained models.

Subfields: Artificial Intelligence, Retrieval-Augmented Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Retrieval-Augmented Generation

Citations in the corpus

Re2G: Retrieve, Rerank, Generate (2022, methodology): “Knowledge Graph Induction (KGI) [Glass et al., 2021] combines DPR and RAG models, both trained with task and dataset speciﬁc training.”
Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling (2022, methodology): “In the first section (lines 1-4) we show related works, which also report KILT-based scores: RAG (Lewis et al., 2020), as evaluated by Petroni et al. (2021); DPR + FiD (Piktus et al., 2021); KGI (Glass et al., 2021); and Re2G (Anonymous, 2022).”
Retrieval-Augmented Generation for Large Language Models: A Survey (2023, background): “Improving RAG’s resistance to such adversarial or counterfactual inputs is gaining research momentum and has become a key performance metric [Yu et al. , 2023a, Glass et al. , 2021, Baek et al. , 2023].”
Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks (2021, background): “They achieve competitive performance across different knowledge-intensive NLP tasks (Izacard and Grave, 2021b; Glass et al., 2021; Paranjape et al., 2021; Park et al., 2021; Borgeaud et al., 2021).”