HoReN is a parameter-preserving editor that wraps an MLP with a Hopfield codebook memory and scales to 50K sequential edits on ZsRE while maintaining performance above 0.93.
Zero-Shot Relation Extraction via Reading Comprehension
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
We show that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot. This reduction has several advantages: we can (1) learn relation-extraction models by extending recent neural reading-comprehension techniques, (2) build very large training sets for those models by combining relation-specific crowd-sourced questions with distant supervision, and even (3) do zero-shot learning by extracting new relation types that are only specified at test-time, for which we have no labeled training examples. Experiments on a Wikipedia slot-filling task demonstrate that the approach can generalize to new questions for known relation types with high accuracy, and that zero-shot generalization to unseen relation types is possible, at lower accuracy levels, setting the bar for future work on this task.
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
EQuANt extends QANet to SQuAD 2, achieving nearly twice the performance of a lightweight QANet baseline while also improving SQuAD 1.1 results via multi-task learning.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
A 2019 survey of machine reading comprehension corpora and methods.
citing papers explorer
-
HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing
HoReN is a parameter-preserving editor that wraps an MLP with a Hopfield codebook memory and scales to 50K sequential edits on ZsRE while maintaining performance above 0.93.
-
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
-
EQuANt (Enhanced Question Answer Network)
EQuANt extends QANet to SQuAD 2, achieving nearly twice the performance of a lightweight QANet baseline while also improving SQuAD 1.1 results via multi-task learning.
-
Retrieval-Augmented Generation for Large Language Models: A Survey
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
-
Machine Reading Comprehension: a Literature Review
A 2019 survey of machine reading comprehension corpora and methods.
- ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models