AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

A Retrieve-and-Edit Framework for Predicting Structured Outputs

Tatsunori B Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang

NeurIPS 2018 · Large language models › Language, safety and interpretability · approach: Controlled text generation · 100 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add retrieved-example editing to a Seq2Seq modelSeq2Seq · Python GitHub autocompleteBLEU: 19.2 -> 34.7Improved
Add retrieved-example editing instead of retrieval aloneTaskRetriever · Python GitHub autocompleteBLEU: 29.9 -> 34.7Improved
Use task-dependent output-reconstructing embeddings instead of bag-of-words embeddings (ablation)Python autocomplete retriever · Python GitHub autocompleteBLEU: 23.1 -> 29.9Improved
Train the encoder-decoder to reconstruct y rather than the input x (ablation)InputRetriever · Python GitHub autocompleteLongest completed length: 12.3 -> 13.5Improved
Train the encoder-decoder to reconstruct y rather than the input x (ablation)InputRetriever · Python GitHub autocompleteBLEU: 29.8 -> 29.9No clear effect
Add retrieve-and-edit to a sequence-to-sequence modelSequence-to-sequence · Hearthstone cardsBLEU: 60.4 -> 70.0Improved
Add retrieve-and-edit to a sequence-to-sequence modelSequence-to-sequence · Hearthstone cardsAccuracy: 1.5 -> 9.1Improved
Add identity-map data augmentation with probability 0.1 (ablation)Retrieve+Edit editor · Python GitHub autocomplete and Hearthstone cardsPerformanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy