Challenge: Large pre-trained language models such as GPT-3.5 and GPT-4 have gained significant attention in natural language research due to limited computational resources or inaccessible parameters.
Approach: They propose a neural programmer-interpreter approach that preserves the domain generalization ability of LLMs while editing their output.
Outcome: The proposed framework significantly improves GPT-3.5’s performance in logical form-to-text conversion and low-resource machine translation, surpassing other state-of-the-art (SOTA) LLM post-editing methods in cross-domain settings.

Similar Papers

Leveraging GPT-4 for Automatic Translation Post-Editing (2023.findings-emnlp)

Copied to clipboard

Challenge: Neural Machine Translation models still require translation post-editing to rectify errors and enhance quality under critical settings.
Approach: They use GPT-4 to automatically post-edit NMT outputs across several language pairs . they show that GPT4 is adept at translation post- editing, producing meaningful edits .
Outcome: The proposed translation post-editor improves on state-of-the-art language models on English-Chinese, English-German, Chinese-English and German-English language pairs.
Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing (2024.naacl-long)

Copied to clipboard

Challenge: Large language models have demonstrated considerable success in various natural language processing tasks, but their performance in NMT tasks is still underexplored.
Approach: They propose to use LLMs as automatic post-editors rather than direct translators to improve BLEU and COMET performance.
Outcome: The proposed approach improves BLEU but COMET performance compared to in-context learning.
A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models.
Approach: They evaluate the performance of large language models and their generation strategies in 11 different languages using 3 NLP tasks and 4 open-source LLMs.
Outcome: The proposed generation strategies and their combinations yield strong results across 11 languages, including several extremely low-resource ones.
Editing Large Language Models: Problems, Methods, and Opportunities (2023.emnlp-main)

Copied to clipboard

Challenge: Recent advances in model editing for LLMs have created challenges and opportunities for the community.
Approach: They propose to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs.
Outcome: The proposed method alters behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs.
Self-Edit: Fault-Aware Code Editor for Code Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing Large language models (LLMs) have low pass rates and accuracy on competitive programming tasks.
Approach: They propose a generate-and-edit approach that uses execution results of generated code from LLMs to improve code quality on competitive programming tasks.
Outcome: The proposed method improves pass@1 by 89% on APPS-dev, 31% on apps-test, and 48% on HumanEval over nine popular code generation LLMs with parameter sizes ranging from 110M to 175B.
Automatic Input Rewriting Improves Translation with Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: LLMs can rewrite inputs but in machine translation, they are primarily used to re-write outputs via post-editing.
Approach: They propose to use LLMs to rewrite inputs automatically to improve machine translation (MT) they propose to simplify inputs and use quality estimation to assess translatability.
Outcome: The proposed methods can be improved by using quality estimation to assess translatability.
Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges (2024.acl-srw)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive zero-shot performance on a wide range of NLP tasks.
Approach: They propose to use large language models to augment extractive reading comprehension datasets by fine-tuning their annotations and comparing their performance to human annotators.
Outcome: The proposed model can be used to augment extractive reading comprehension datasets.
Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt.
Approach: They propose to refine a Large Language Model (LLM) with prompt-output pairs with equivalent semantics to achieve semantic consistency.
Outcome: The proposed method improves the semantic consistency and task performance of LLMs.
HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches treat instruction-based text editing as a generic text generation problem. Existing methods either over-edit or fail to apply modifications consistently.
Approach: They propose a framework that processes each editing request to best align with it.
Outcome: The proposed framework achieves 9% improvement over the state-of-the-art model.
Progressive Generation of Long Text with Pretrained Language Models (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for "long" text generation are limited to outputs of 50-200 tokens . however, our proposed ProGen generates coherent long passages of text in a progressive manner .
Approach: They propose a method for generating coherent long passages of text in a progressive manner . they first produce domain-specific content keywords and then refine them into complete passages . human evaluation validates that their proposed generation is more coherent .
Outcome: The proposed method produces domain-specific content keywords and refines them into complete passages in multiple stages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations